{"version":"4.44.1","mode":"blocks","app_id":15274913120264077432,"dev_mode":false,"analytics_enabled":true,"components":[{"id":1,"type":"markdown","props":{"value":"# OpenVLM Leaderboard\n### Welcome to the OpenVLM Leaderboard! On this leaderboard we share the evaluation results of VLMs obtained by the OpenSource Framework:\n### [*VLMEvalKit*: A Toolkit for Evaluating Large Vision-Language Models](https://github.com/open-compass/VLMEvalKit) 🏆\n### Currently, OpenVLM Leaderboard covers 285 different VLMs (including GPT-4v, Gemini, QwenVLPlus, LLaVA, etc.) and 31 different multi-modal benchmarks. \n\nThis leaderboard was last updated: 2025.09.17 13:29:16. \n\nOpenVLM Leaderboard only includes open-source VLMs or API models that are publicly available. To add your own model to the leaderboard, please create a PR in [VLMEvalKit](https://github.com/open-compass/VLMEvalKit) to support your VLM and then we will help with the evaluation and updating the leaderboard. For any questions or concerns, please feel free to contact us at [opencompass, duanhaodong]@pjlab.org.cn.","show_label":true,"rtl":false,"latex_delimiters":[{"left":"$$","right":"$$","display":true}],"visible":true,"elem_classes":[],"sanitize_html":true,"line_breaks":false,"header_links":false,"show_copy_button":false,"name":"markdown","_selectable":false},"skip_api":false,"component_class_id":"0f35515b9a3362b42bb6721c836157a0","key":null,"api_info":{"type":"string"},"example_inputs":"# Hello!"},{"id":2,"type":"tabs","props":{"visible":true,"elem_classes":["tab-buttons"],"name":"tabs"},"skip_api":true,"component_class_id":"3e4202431baca71099b95e73fb9d900c","key":null},{"id":3,"type":"tabitem","props":{"label":"🏅 OpenVLM Main Leaderboard","visible":true,"interactive":true,"id":0,"elem_id":"main","name":"tab"},"skip_api":true,"component_class_id":"18f46968e2b273dc5dbda0fe78433d7e","key":null},{"id":4,"type":"markdown","props":{"value":"## Main Evaluation Results\n\n- Metrics:\n - Avg Score: The average score on all VLM Benchmarks (normalized to 0 - 100, the higher the better). \n - Avg Rank: The average rank on all VLM Benchmarks (the lower the better). \n - Avg Score & Rank are calculated based on selected benchmark. **When results for some selected benchmarks are missing, Avg Score / Rank will be None!!!** \n- By default, we present the overall evaluation results based on 8 VLM benchmarks, sorted by the descending order of Avg Score. \n - The following datasets are included in the main results: MMBench_V11, MMStar, MMMU_VAL, MathVista, OCRBench, AI2D, HallusionBench, MMVet. \n - Detailed evaluation results for each dataset (included or not included in main) are provided in the consequent tabs. ","show_label":true,"rtl":false,"latex_delimiters":[{"left":"$$","right":"$$","display":true}],"visible":true,"elem_classes":[],"sanitize_html":true,"line_breaks":false,"header_links":false,"show_copy_button":false,"name":"markdown","_selectable":false},"skip_api":false,"component_class_id":"0f35515b9a3362b42bb6721c836157a0","key":null,"api_info":{"type":"string"},"example_inputs":"# Hello!"},{"id":5,"type":"checkboxgroup","props":{"choices":[["Avg Score","Avg Score"],["Avg Rank","Avg Rank"],["MMBench_V11","MMBench_V11"],["MMStar","MMStar"],["MME","MME"],["MMMU_VAL","MMMU_VAL"],["MathVista","MathVista"],["OCRBench","OCRBench"],["AI2D","AI2D"],["HallusionBench","HallusionBench"],["SEEDBench_IMG","SEEDBench_IMG"],["MMVet","MMVet"],["LLaVABench","LLaVABench"],["CCBench","CCBench"],["RealWorldQA","RealWorldQA"],["POPE","POPE"],["ScienceQA_TEST","ScienceQA_TEST"],["SEEDBench2_Plus","SEEDBench2_Plus"],["MMT-Bench_VAL","MMT-Bench_VAL"],["BLINK","BLINK"]],"value":["Avg Score","Avg Rank","MMBench_V11","MMStar","MMMU_VAL","MathVista","OCRBench","AI2D","HallusionBench","MMVet"],"type":"value","label":"Evaluation Dimension","show_label":true,"container":true,"min_width":160,"interactive":true,"visible":true,"elem_classes":[],"name":"checkboxgroup","_selectable":false},"skip_api":false,"component_class_id":"0635a5d3bf87369f1c2c1c69f8a3d0cc","key":null,"api_info":{"items":{"enum":["Avg Score","Avg Rank","MMBench_V11","MMStar","MME","MMMU_VAL","MathVista","OCRBench","AI2D","HallusionBench","SEEDBench_IMG","MMVet","LLaVABench","CCBench","RealWorldQA","POPE","ScienceQA_TEST","SEEDBench2_Plus","MMT-Bench_VAL","BLINK"],"type":"string"},"title":"Checkbox Group","type":"array"},"example_inputs":["Avg Score"]},{"id":6,"type":"row","props":{"variant":"default","visible":true,"equal_height":true,"show_progress":false,"name":"row"},"skip_api":true,"component_class_id":"b5cf3d15e2293fb5ccc071d7b8d69f64","key":null},{"id":7,"type":"textbox","props":{"value":"Input the Model Name (fuzzy, case insensitive)","lines":1,"max_lines":20,"label":"Model Name","show_label":true,"container":true,"min_width":160,"interactive":true,"visible":true,"autofocus":false,"autoscroll":true,"elem_classes":[],"type":"text","rtl":false,"show_copy_button":false,"name":"textbox","_selectable":false},"skip_api":false,"component_class_id":"d0491bb0fbd427bdb2a4549c4d1ac869","key":null,"api_info":{"type":"string"},"example_inputs":"Hello!!"},{"id":8,"type":"checkboxgroup","props":{"choices":[["<4B","<4B"],["4B-10B","4B-10B"],["10B-20B","10B-20B"],["20B-40B","20B-40B"],[">40B",">40B"],["Unknown","Unknown"]],"value":["<4B","4B-10B","10B-20B","20B-40B",">40B","Unknown"],"type":"value","label":"Model Size","show_label":true,"container":true,"min_width":160,"interactive":true,"visible":true,"elem_classes":[],"name":"checkboxgroup","_selectable":false},"skip_api":false,"component_class_id":"0635a5d3bf87369f1c2c1c69f8a3d0cc","key":null,"api_info":{"items":{"enum":["<4B","4B-10B","10B-20B","20B-40B",">40B","Unknown"],"type":"string"},"title":"Checkbox Group","type":"array"},"example_inputs":["<4B"]},{"id":9,"type":"checkboxgroup","props":{"choices":[["API","API"],["OpenSource","OpenSource"]],"value":["API","OpenSource"],"type":"value","label":"Model Type","show_label":true,"container":true,"min_width":160,"interactive":true,"visible":true,"elem_classes":[],"name":"checkboxgroup","_selectable":false},"skip_api":false,"component_class_id":"0635a5d3bf87369f1c2c1c69f8a3d0cc","key":null,"api_info":{"items":{"enum":["API","OpenSource"],"type":"string"},"title":"Checkbox Group","type":"array"},"example_inputs":["API"]},{"id":10,"type":"form","props":{"scale":3,"min_width":480,"name":"form"},"skip_api":true,"component_class_id":"43cda85c6ff7a5dd8f83d29496b014ee","key":null},{"id":11,"type":"dataframe","props":{"value":{"headers":["Rank","Method","Param (B)","Language Model","Vision Model","Eval Date","Avg Score","Avg Rank","MMBench_V11","MMStar","MMMU_VAL","MathVista","OCRBench","AI2D","HallusionBench","MMVet"],"data":[[1,"SenseNova-V6-5-Pro",null,"","","2025/09/03",82.2,6.12,87.3,76.1,77.0,82.8,885,90.2,66.7,89.4],[2,"CongRong-v2.0",null,"","","2025/05/20",80.7,4.88,88.1,75.3,75.6,76.8,927,90.0,63.2,83.9],[3,"SenseNova-V6-Pro",null,"","","2025/05/05",80.4,7.12,88.0,73.7,70.4,76.9,895,89.2,67.1,88.2],[4,"Gemini-2.5-Pro",null,"","","2025/04/07",80.1,9.38,88.3,73.6,74.7,80.9,862,89.5,64.1,83.3],[5,"GPT-5-20250807",null,"","","2025/08/14",79.9,18.38,86.6,75.7,81.8,81.9,807,89.5,65.2,77.6],[6,"JT-VL-Chat-V3.0",null,"","","2025/08/04",79.9,11.88,87.5,82.1,68.7,72.8,950,88.3,64.4,80.3],[7,"InternVL3-78B",78.4,"Qwen2.5-72B","InternViT-6B-v2.5","2025/04/14",79.1,8.75,87.7,73.4,72.2,79.0,908,89.8,59.1,80.7],[8,"BlueLM-2.6-3B",3.0,"","","2025/09/17",78.4,19.62,86.4,80.1,62.4,82.3,881,86.1,63.1,78.5],[9,"GPT-5-mini-20250807",null,"","","2025/08/14",78.0,23.0,86.2,73.2,78.7,79.2,828,86.7,62.5,74.6],[10,"InternVL3-38B",38.4,"Qwen2.5-32B","InternViT-6B-v2.5","2025/04/14",77.8,16.25,86.8,72.6,69.7,76.3,886,88.7,58.4,81.1],[11,"Step-1o",null,"","","2025/01/13",77.7,16.62,87.3,69.3,69.9,74.7,926,89.1,55.8,82.8],[12,"SenseNova",null,"","","2024/12/12",77.4,17.88,85.7,72.7,69.6,78.4,894,87.8,57.4,78.2],[13,"InternVL2.5-78B-MPO",78.0,"Qwen-2.5-72B","InternViT-6B-v2.5","2024/12/29",77.0,17.0,87.7,72.1,68.2,76.6,909,89.2,58.1,73.5],[14,"GLM-4v-Plus-20250111",null,"","","2025/01/25",76.7,20.0,85.9,72.5,69.9,73.5,908,86.7,58.5,75.7],[15,"Ovis2-34B",34.9,"Qwen2.5-32B","AIMv2-1B","2025/02/18",76.5,20.0,86.5,69.2,66.7,76.1,894,88.3,58.8,77.1],[16,"HunYuan-Standard-Vision",null,"","","2025/01/15",76.3,27.62,83.6,72.9,70.7,66.1,861,93.2,57.7,79.9],[17,"Qwen2.5-VL-72B",73.4,"Qwen2.5-72B","QwenViT","2025/02/02",76.1,23.12,87.8,70.5,68.2,74.2,882,88.5,54.6,76.9],[18,"GPT-4.1-20250414",null,"","","2025/04/16",75.9,30.12,86.6,69.8,74.0,70.4,834,85.9,58.5,78.8],[19,"TeleMM",null,"","","2024/12/31",75.9,26.88,79.9,70.8,66.6,75.7,891,88.5,60.6,75.7],[20,"R-4B",4.82,"Qwen3-4B","SigLip-400M","2025/08/11",75.5,30.62,82.8,72.6,64.7,78.0,837,86.2,60.0,76.2],[21,"ChatGPT-4o-latest",null,"","","2025/04/07",75.4,32.38,86.0,70.2,72.9,71.6,822,86.3,57.0,76.9],[22,"InternVL2.5-38B-MPO",38.0,"Qwen-2.5-32B","InternViT-6B-v2.5","2024/12/28",75.3,24.75,85.4,70.1,63.8,73.6,894,87.9,59.7,72.6],[23,"GPT-4.5",null,"","","2025/03/26",75.3,30.75,83.4,69.3,72.1,70.5,845,87.2,60.0,75.3],[24,"BailingMM-Pro-0120",81.0,"Bailing-80B","SigLIP-400M","2025/01/25",75.2,26.38,87.1,69.4,59.2,72.3,894,87.2,59.4,77.6],[25,"InternVL3-14B",15.1,"Qwen2.5-14B","InternViT-300M-v2.5","2025/04/14",75.2,31.75,83.6,68.9,64.8,74.4,877,86.0,55.9,80.5],[26,"Qwen2.5-VL-32B",33.5,"Qwen2.5-32B","QwenViT","2025/07/02",74.8,33.38,84.0,70.3,68.9,72.8,856,85.4,58.4,72.9],[27,"Qwen2-VL-72B",73.4,"Qwen2-72B","QwenViT","2024/10/28",74.8,29.5,85.9,68.6,64.3,69.7,888,88.3,58.7,73.9],[28,"Qwen-VL-Max-0809",72.0,"Qwen2-72B","QwenViT","2024/09/12",74.4,32.0,85.8,69.2,64.6,68.3,881,88.1,59.2,72.3],[29,"Kimi-VL-A3B-Thinking-2506",16.4,"Moonlight-16B-A3B","MoonViT","2025/07/02",74.3,44.62,80.1,70.0,62.9,79.5,823,83.1,59.8,77.0],[30,"InternVL3-8B",7.94,"Qwen2.5-7B","InternViT-300M-v2.5","2025/04/14",73.6,44.12,82.1,68.7,62.2,70.5,884,85.1,49.0,82.8],[31,"SAIL-VL-1.6-8B",8.33,"Qwen2.5-7B","AIMv2 Huge","2025/04/24",73.6,35.62,84.0,69.5,55.4,74.2,905,87.5,54.4,73.3],[32,"Gemini-2.0-Pro",null,"","","2025/02/27",73.3,43.88,83.0,68.5,72.6,71.3,863,84.8,49.8,70.4],[33,"Ovis2-16B",16.2,"Qwen2.5-14B","AIMv2 Huge","2025/02/18",73.3,37.25,85.7,67.2,60.7,73.7,879,86.3,56.8,68.4],[34,"InternVL2.5-38B",38.0,"Qwen-2.5-32B","InternViT-6B-v2.5","2024/12/10",73.3,39.25,85.4,68.5,63.2,72.4,841,87.6,57.9,67.2],[35,"Taiyi",null,"","","2024/12/11",73.0,41.75,84.8,69.0,60.4,72.6,820,90.8,56.8,67.9],[36,"VARCO-VISION-2.0-14B",15.2,"Qwen3-14B","SigLIP-400M","2025/08/04",72.6,44.38,83.7,66.9,61.9,73.2,869,85.7,53.2,68.9],[37,"Ola-7b",8.88,"Qwen2.5-7B","Oryx-ViT","2025/02/05",72.6,47.12,84.3,70.8,57.0,68.4,822,86.1,53.5,78.6],[38,"InternVL3-9B",9.14,"InternLM3-8B","InternViT-300M-v2.5","2025/04/14",72.6,47.12,82.2,67.4,59.4,69.0,881,85.2,50.8,78.4],[39,"Gemini-2.0-Flash",null,"","","2025/01/02",72.6,55.75,71.0,69.4,69.9,70.4,851,83.1,58.0,73.6],[40,"WeThink-Qwen2.5VL-7B",8.29,"Qwen2.5-7B","QwenViT","2025/05/26",72.5,48.0,81.8,64.2,61.0,71.6,890,84.0,55.3,73.2],[41,"SAIL-VL-1.5-8B",7.95,"Qwen2.5-7B","InternViT-300B","2025/04/23",72.4,43.0,82.1,69.7,54.3,73.4,889,87.5,54.5,69.0],[42,"Step-1.5V",null,"Step-1.5","stepencoder","2024/10/11",72.4,44.62,82.0,65.1,61.2,69.4,886,87.5,54.3,71.3],[43,"GPT-5-nano-20250807",null,"","","2025/08/14",72.2,60.62,79.2,68.3,72.6,73.1,747,81.4,60.9,67.4],[44,"Gemini-1.5-Pro-002",null,"","","2024/12/02",72.2,56.0,82.8,67.1,68.6,67.9,770,83.3,55.9,74.6],[45,"InternVL2.5-26B-MPO",26.0,"InternLM2.5-20B","InternViT-6B-v2.5","2024/12/28",72.1,43.62,84.2,67.7,56.4,71.5,905,86.2,52.4,68.1],[46,"GPT-4o (1120, detail-high)",null,"","","2024/12/02",72.0,55.12,84.3,65.1,70.7,60.0,806,84.9,56.2,74.5],[47,"Ovis2-8B",8.94,"Qwen2.5-7B","AIMv2 Huge","2025/02/18",71.8,45.88,83.6,64.6,57.4,71.8,891,86.6,56.3,65.1],[48,"GPT-4o (0806, detail-high)",null,"","","2024/08/08",71.6,62.0,80.5,64.7,69.9,62.9,805,84.7,54.2,75.1],[49,"BailingMM-Lite-1203",21.0,"Bailing-20B","SigLIP-400M","2024/12/08",71.5,50.12,83.4,67.3,50.9,74.5,852,86.0,60.1,64.9],[50,"MUG-U-7B",7.0,"","","2025/03/19",71.5,48.62,81.8,66.6,54.3,74.8,911,88.9,51.3,63.0],[51,"GLM-4v-Plus",null,"","","2024/12/11",71.4,54.88,80.3,66.3,61.7,68.8,843,85.1,55.6,69.1],[52,"Ovis1.6-Gemma2-27B",28.9,"Gemma2-27B","SigLIP-400M","2024/11/29",71.3,51.62,82.2,63.5,60.3,70.2,856,86.6,54.1,68.0],[53,"InternVL2-Llama3-76B",76.0,"Llama-3-70B-Instruct","InternViT-6B","2024/07/19",71.0,53.25,85.5,67.1,58.3,65.6,842,87.6,55.4,64.4],[54,"InternVL2.5-26B",26.0,"InternLM2.5-20B","InternViT-6B-v2.5","2024/12/10",71.0,52.0,84.6,66.5,56.0,68.2,854,86.2,55.8,65.4],[55,"Qwen2.5-VL-7B",8.29,"Qwen2.5-7B","QwenViT","2025/02/02",70.9,55.5,82.2,64.1,58.0,68.1,888,84.3,51.9,69.7],[56,"GPT-4o (0513, detail-high)",null,"","","2024/05/31",70.9,61.62,82.2,63.9,69.2,61.8,815,84.6,55.0,69.1],[57,"BlueLM-2.5-3B",2.9,"BlueLM-base-3B","Siglip2-So400M","2025/07/16",70.8,64.88,74.6,67.8,58.7,76.7,838,83.1,60.0,61.7],[58,"Claude3.5-Sonnet-20241022",null,"","","2024/11/06",70.6,67.25,81.7,65.1,66.4,65.3,798,81.2,55.5,70.1],[59,"InternVL2.5-8B-MPO",8.0,"InternLM2.5-7B","InternViT-300M-v2.5","2024/12/28",70.3,58.88,82.0,65.2,54.8,67.9,882,84.5,51.7,68.1],[60,"MiniCPM-o-2.6",8.67,"Qwen2.5-7B","SigLIP-400M","2025/01/21",70.2,60.75,80.6,63.3,50.9,73.3,889,86.1,51.1,67.2],[61,"Claude3.7-Sonnet",null,"","","2025/02/27",70.1,71.0,79.7,65.1,71.0,66.8,701,82.5,55.4,70.0],[62,"Ovis2-4B",4.62,"Qwen2.5-3B","AIMv2 Huge","2025/02/18",69.8,62.88,81.4,61.9,49.0,69.6,911,85.7,53.8,65.5],[63,"abab7-preview",null,"","","2024/12/11",69.7,70.25,82.0,66.0,64.8,67.5,794,82.3,51.7,63.7],[64,"InternVL2-40B",40.0,"Nous-Hermes-2-Yi-34B","InternViT-6B","2024/07/11",69.7,61.5,85.0,64.7,55.2,64.3,833,86.8,56.5,61.8],[65,"valley2_dpo",8.88,"Qwen2.5-7B","SigLIP-400M","2025/05/30",69.3,67.62,81.8,61.9,58.4,68.7,858,83.0,52.4,62.3],[66,"Ovis-U1-3B",3.64,"Qwen3-1.7B","aimv2-large-path14-448","2025/07/20",69.3,69.62,77.9,61.3,50.6,68.9,881,85.6,55.8,66.0],[67,"Kimi-VL-A3B-Instruct",16.4,"Moonlight-16B-A3B","MoonViT","2025/04/14",69.1,70.12,80.8,62.0,57.8,66.0,871,84.5,48.4,66.1],[68,"GPT-4.1-mini-20250414",null,"","","2025/04/16",68.9,79.38,80.9,60.9,55.0,70.9,840,76.0,49.3,74.3],[69,"Gemini-1.5-Flash-002",null,"","","2024/12/02",68.9,73.5,81.3,64.4,60.7,63.7,733,84.4,53.9,69.7],[70,"Ovis1.6-Gemma2-9B",10.2,"Gemma2-9B-It","SigLIP-400M","2024/09/19",68.8,73.88,80.5,62.9,55.0,67.3,830,84.4,52.2,65.0],[71,"InternVL2.5-78B",78.0,"Qwen-2.5-72B","InternViT-6B-v2.5","2024/12/10",68.3,57.5,87.5,69.5,70.0,70.6,853,89.1,57.4,16.9],[72,"InternVL2.5-8B",8.0,"InternLM2.5-7B","InternViT-300M-v2.5","2024/12/10",68.1,76.38,82.5,63.2,56.2,64.5,821,84.6,49.0,62.8],[73,"LLaVA-OneVision-72B",73.0,"Qwen2-72B","SigLIP-400M","2024/09/19",68.0,74.75,84.5,65.8,56.6,68.4,741,86.2,47.9,60.6],[74,"Claude3.5-Sonnet",null,"","","2024/06/24",67.9,87.12,78.5,62.2,65.9,61.8,788,80.2,49.9,66.0],[75,"Ristretto-3B",3.84,"Qwen2.5-3B","SigLIP-400M","2025/04/01",67.7,79.25,80.2,62.8,51.3,67.6,847,84.2,50.2,60.7],[76,"NVLM-D-72B",79.4,"Qwen2-72B","InternViT-6B","2024/10/19",67.6,85.12,78.5,63.7,60.8,64.0,849,80.1,49.7,58.9],[77,"LLaVA-OneVision-72B (SI)",73.0,"Qwen2-72B","SigLIP-400M","2024/09/19",67.6,78.62,82.6,65.3,55.7,67.1,763,85.5,49.0,59.1],[78,"Gemma3-27B",27.4,"Gemma3-27B","SigLIP-400M","2025/03/19",67.4,91.25,78.9,59.6,64.8,59.8,753,81.4,48.8,71.0],[79,"POINTS1.5-Qwen2.5-7B",8.3,"Qwen-2.5-7B","NaViT","2024/12/06",67.4,85.38,80.7,61.1,53.8,66.4,832,81.4,50.0,62.2],[80,"Valley-Eagle",8.9,"Qwen2.5-7B","Qwen-ViT
SigLIP-400M","2024/12/29",67.4,85.0,80.7,60.9,57.0,64.6,842,82.5,48.0,61.3],[81,"InternVL2.5-4B-MPO",4.0,"Qwen-2.5-3B","InternViT-300M-v2.5","2024/12/28",67.2,88.12,77.8,61.0,51.8,64.1,879,81.5,47.5,66.0],[82,"valley2",8.88,"Qwen2.5-7B","SigLIP-400M","2025/05/30",67.1,86.88,81.0,60.0,56.8,61.7,845,82.8,47.6,62.1],[83,"Qwen2-VL-7B",8.0,"Qwen2-7B","QwenViT","2024/09/12",67.1,85.62,81.0,60.7,53.7,61.6,843,83.0,50.4,61.8],[84,"SAIL-VL-1.5-2B",2.47,"Qwen2.5-1.5B","AIMv2 Huge","2025/04/23",67.0,85.12,78.5,62.6,46.4,67.0,891,83.7,50.0,58.8],[85,"bailingMM-mini",17.0,"bailing-mini","bailingMM-encoder-1B
InternViT-6B","2024/10/24",67.0,85.62,82.2,61.3,50.0,70.8,835,83.5,45.4,59.2],[86,"grok-2-vision-1212",null,"","","2025/03/03",66.9,81.38,82.9,65.2,67.1,66.6,555,81.2,51.7,65.2],[87,"VARCO-VISION-14B",15.2,"Qwen2.5-14B","SigLIP-400M","2025/01/02",66.8,86.25,81.2,64.1,56.3,67.6,815,83.9,46.8,53.0],[88,"GPT-4o (0513, detail-low)",null,"","","2024/05/15",66.7,91.12,82.8,61.6,62.8,57.2,735,77.4,51.7,66.5],[89,"DeepSeek-VL2",27.5,"DeepSeekMoE-27B","SigLIP-400M","2025/01/01",66.4,92.0,81.2,61.9,54.0,63.9,809,83.8,45.3,60.0],[90,"InternVL2-26B",26.0,"InternLM2-20B","InternViT-6B","2024/07/11",66.4,89.75,81.2,61.0,50.7,59.6,825,84.5,51.5,60.0],[91,"QTuneVL1.5-3B",3.75,"Qwen2.5-3B","QwenViT","2025/08/11",66.1,96.5,77.3,57.1,53.4,64.4,839,81.2,49.0,62.8],[92,"BlueLM-V-3B",3.0,"BlueLM-3B","SigLIP-400M","2024/10/30",66.1,90.25,82.7,62.3,45.1,60.9,829,85.3,48.0,61.8],[93,"Qwen-VL-Plus-0809",null,"","","2024/09/17",65.9,98.0,74.9,59.9,53.2,61.2,843,82.9,51.1,59.6],[94,"Kimi-VL-A3B-Thinking",16.4,"Moonlight-16B-A3B","MoonViT","2025/04/23",65.9,102.12,68.3,60.8,50.7,67.6,825,77.5,52.3,67.4],[95,"MiMo-VL-7B",8.31,"Mimo-7B","Qwen2.5-ViT","2025/07/02",65.6,101.62,80.7,38.9,26.4,77.4,829,82.8,63.8,72.2],[96,"CongRong",null,"","","2024/06/26",65.5,100.12,80.7,60.6,48.3,61.1,827,82.4,50.6,57.5],[97,"Ovis2-2B",2.46,"Qwen2.5-1.5B","AIMv2 Large","2025/02/18",65.2,101.5,76.9,56.7,45.6,64.1,873,82.7,50.2,58.3],[98,"MiniCPM-V-2.6",8.0,"Qwen2-7B","SigLIP-400M","2024/08/08",65.2,100.88,78.0,57.5,49.8,60.8,852,82.1,48.1,60.0],[99,"InternVL2.5-4B",4.0,"Qwen-2.5-3B","InternViT-300M-v2.5","2024/12/10",65.1,105.38,78.2,58.7,51.8,60.8,820,81.4,46.6,61.5],[100,"moonshot-v1-8k",null,"","","2025/03/03",65.0,105.88,76.5,60.1,57.7,66.9,790,81.8,46.1,52.0],[101,"InternVL2-8B-MPO-CoT",8.0,"InternLM2.5-7B","InternViT-300M","2024/11/25",64.9,105.38,75.7,62.2,48.1,65.9,830,83.4,45.1,55.7],[102,"Phi-4-MultiModal",5.57,"Phi-4-Mini","SigLIP-400M","2025/03/13",64.7,105.38,77.2,58.9,56.0,65.8,844,83.0,40.5,51.9],[103,"QTuneVL1.5-2B",2.09,"Qwen2.5-1.5B","InternViT-300M-v2.5","2025/08/11",64.6,107.88,77.8,60.8,48.7,56.1,858,78.6,43.4,65.9],[104,"InternVL2-8B-MPO",8.0,"InternLM2.5-7B","InternViT-300M","2024/11/25",64.6,107.0,76.5,62.5,48.0,65.8,769,83.4,47.7,55.8],[105,"InternVL3-2B",2.09,"Qwen2.5-1.5B","InternViT-300M-v2.5","2025/04/14",64.5,110.38,78.0,61.1,48.7,57.6,831,78.6,41.9,67.0],[106,"Gemini-1.5-Pro",null,"","","2024/06/10",64.5,112.75,73.9,59.1,60.6,58.3,754,79.1,45.6,64.0],[107,"DeepSeek-VL2-Small",16.1,"DeepSeekMoE-16B","SigLIP-400M","2025/01/01",64.5,106.75,79.9,57.5,49.7,61.9,832,81.7,43.8,58.6],[108,"Qwen2.5-VL-3B",3.75,"Qwen2.5-3B","QwenViT","2025/02/02",64.5,109.0,76.8,56.3,51.2,61.2,828,81.4,46.6,60.0],[109,"RBDash-v1.5",79.0,"Qwen2-72B","CLIP ViT-L/14
InternViT-6B","2024/11/17",64.5,96.62,81.3,63.5,59.9,61.5,657,85.0,49.1,50.0],[110,"Step-1.5V-mini",null,"","","2024/12/11",64.5,110.12,79.7,54.7,51.7,57.8,773,81.3,46.7,66.5],[111,"InternVL2-8B",8.0,"InternLM2.5-7B","InternViT-300M","2024/07/11",64.1,108.88,79.4,61.5,51.2,58.3,794,83.6,45.0,54.3],[112,"GPT-4o-mini (0718, detail-high)",null,"","","2024/07/20",64.1,115.5,76.0,54.8,60.0,52.5,785,77.8,46.1,66.9],[113,"Molmo-72B",73.3,"Qwen2-72B","CLIP ViT-L/14","2024/10/28",64.0,107.25,79.5,63.3,52.8,55.2,701,83.4,46.6,61.1],[114,"Ovis1.5-Gemma2-9B",11.4,"Gemma2-9B-It","SigLIP-400M","2024/08/04",64.0,108.38,77.3,58.1,49.7,65.6,752,84.5,48.2,53.8],[115,"Aria",25.3,"Aria-MoE","SigLIP-400M","2024/12/05",64.0,113.0,77.4,60.7,54.0,62.4,734,82.7,44.8,56.9],[116,"Yi-Vision",null,"","","2024/08/03",63.9,114.38,76.3,60.5,60.3,57.8,701,78.2,50.3,57.6],[117,"GPT-4v (0409, detail-high)",null,"","","2024/05/15",63.5,113.38,79.8,56.0,61.7,55.2,656,78.6,43.9,67.5],[118,"Gemini-1.5-Flash",null,"","","2024/09/16",63.5,115.75,76.9,55.8,58.2,51.3,753,78.5,48.5,63.2],[119,"Llama-3.2-90B-Vision-Instruct",88.6,"Llama-3.1-70B","","2024/10/19",63.4,121.88,77.3,55.3,60.3,58.2,783,69.5,44.1,64.1],[120,"VITA-1.5",8.3,"Qwen2-7B","InternViT-300M","2025/01/01",63.3,118.12,76.8,60.2,52.6,66.2,741,79.2,44.6,52.7],[121,"Gemma3-12B",12.2,"Gemma3-12B","SigLIP-400M","2025/03/19",62.8,121.62,74.6,56.1,55.2,56.1,702,78.1,47.2,64.9],[122,"MMAlaya2",26.0,"InternLM2-20B","InternViT-6B","2024/08/27",62.6,119.62,80.2,58.1,46.9,54.1,727,80.8,49.3,58.5],[123,"POINTS-Qwen2.5-7B",8.3,"Qwen-2.5-7B","CLIP ViT-L/14","2024/10/19",62.5,119.75,78.0,60.9,51.4,63.1,717,81.2,45.6,47.9],[124,"OmChat-v2.0-13B",13.0,"Qwen2-7B","InternViT-6B","2024/08/22",62.0,124.0,79.5,58.2,49.6,57.2,728,77.8,48.4,52.6],[125,"Ovis1.5-Llama3-8B",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/07/29",62.0,126.0,76.6,57.3,48.3,63.3,744,82.5,42.3,50.9],[126,"InternVL-Chat-V1.5",26.0,"InternLM2-20B","InternViT-6B","2024/04/17",61.9,125.88,79.7,57.1,46.8,56.1,720,80.6,47.4,55.4],[127,"LLaVA-CoT",11.0,"","","2025/01/05",61.9,126.88,72.9,54.9,53.7,52.5,755,78.7,47.7,59.5],[128,"POINTS-Yi-1.5-9B",9.5,"Yi-1.5-9B","CLIP ViT-L/14","2024/10/11",61.7,125.75,78.4,56.9,47.6,63.2,719,78.8,47.8,49.2],[129,"Flash-VL-2B-Dynamic-ISS",2.53,"Qwen-2.5-1.5B-Instruct","SigLIP2-400M-512","2025/05/30",61.6,128.75,75.8,53.8,45.6,61.7,844,74.4,48.5,48.6],[130,"Ovis1.6-Llama3.2-3B",4.1,"Llama-3.2-3B","SigLIP-400M","2024/10/24",61.4,136.12,74.1,52.0,46.7,58.9,801,77.8,43.8,57.6],[131,"LLaVA-OneVision-7B (SI)",8.0,"Qwen2-7B","SigLIP-400M","2024/09/17",61.2,128.38,76.8,56.7,46.8,58.6,697,82.8,47.5,50.6],[132,"InternLM-XComposer2.5",8.0,"InternLM2-7B","CLIP ViT-L/14","2024/07/11",61.1,129.25,79.4,59.9,42.9,64.0,686,81.6,43.1,49.3],[133,"Long-VITA-16K",14.0,"Qwen2.5-14B","InternViT-300M","2025/06/13",61.1,129.75,76.3,60.1,53.9,64.8,761,80.9,45.5,31.0],[134,"Pixtral-12B",13.0,"Nemo-12B","ViT-400M","2024/09/16",61.0,133.75,72.7,54.5,51.1,56.3,685,79.0,47.0,58.5],[135,"SAIL-VL-2B",2.1,"Qwen2.5-1.5B","InternViT-300M","2024/12/25",61.0,133.25,73.7,56.5,44.1,62.8,831,77.4,45.9,44.2],[136,"InternVL2.5-2B-MPO",2.0,"InternLM2.5-1.8B","InternViT-300M-v2.5","2024/12/28",60.9,137.75,70.7,54.9,44.6,53.4,838,75.1,40.7,64.2],[137,"GLM-4v",null,"","","2024/05/20",60.8,134.88,78.6,53.2,45.6,45.9,814,76.1,44.9,60.7],[138,"InternVL2-4B",4.0,"Phi-3","InternViT-300M","2024/07/11",60.6,137.38,73.6,53.9,48.3,58.5,784,79.0,42.4,50.9],[139,"LLaVA-OneVision-7B",8.0,"Qwen2-7B","SigLIP-400M","2024/09/16",60.2,132.88,80.9,61.9,47.9,62.6,622,82.4,31.6,51.9],[140,"GPT-4v (0409, detail-low)",null,"","","2024/05/15",60.0,133.75,78.8,52.9,62.3,51.8,526,76.1,41.6,63.6],[141,"InternVL2.5-2B",2.0,"InternLM2.5-1.8B","InternViT-300M-v2.5","2024/12/10",59.9,144.88,70.9,54.3,43.2,51.1,802,74.9,42.3,62.6],[142,"QTuneVL1-2B",2.21,"InternLM2.5-1.8B","InternViT-300M-v2.5","2025/05/05",59.9,142.5,71.1,53.6,44.7,48.8,806,75.2,42.4,63.0],[143,"Ovis2-1B",1.27,"Qwen2.5-0.5B","AIMv2 Large","2025/02/18",59.6,146.12,68.3,52.1,36.1,59.4,890,76.4,45.2,50.0],[144,"Aquila-VL-2B",2.2,"Qwen-2.5-1.5B","SigLIP-400M","2024/10/24",59.4,145.0,75.2,54.9,46.9,59.1,773,75.1,43.0,43.8],[145,"GLM-4v-9B",9.0,"GLM-4-9B","EVA-02-5B","2024/06/14",59.2,150.0,67.9,54.8,46.9,52.2,776,71.2,45.0,58.0],[146,"VARCO-VISION-2.0-1.7B",2.12,"Qwen3-1.7B","SigLIP-400M","2025/08/04",59.2,151.12,72.8,52.5,44.2,55.8,808,75.2,38.6,53.4],[147,"MiniCPM-Llama3-V2.5",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/05/27",58.8,149.12,72.0,51.8,45.8,54.5,725,78.4,42.4,52.8],[148,"InternLM-XComposer2-4KHD",7.0,"InternLM2-7B","CLIP ViT-L/14","2024/06/09",58.8,147.5,76.5,55.3,39.7,59.5,675,81.0,42.5,48.2],[149,"granite-vision-3.3-2b",2.98,"granite-3.1-2b-instruct","SigLIP2-400M","2025/06/20",58.7,150.75,68.2,51.9,39.0,60.2,820,76.6,47.0,45.0],[150,"VILA1.5-40B",40.0,"Yi-34B","InternViT-6B","2024/08/25",58.5,141.25,79.7,55.2,55.1,49.7,581,77.8,40.9,51.2],[151,"Qwen-VL-Max",null,"QwenLM","","2024/02/02",58.4,148.88,74.6,49.5,52.0,43.6,684,75.7,41.2,61.8],[152,"Cambrian-34B",34.0,"Nous-Hermes-2-Yi-34B","CLIP ViT-L/14","2024/07/18",58.3,143.5,77.8,54.2,50.4,50.9,591,79.5,41.6,53.2],[153,"WeMM",7.0,"InternLM2-7B","SigLIP-400M","2024/06/09",58.3,145.12,75.7,57.0,45.3,54.9,628,77.9,47.5,45.0],[154,"DeepSeek-VL2-Tiny",3.4,"DeepSeekMoE-3B","SigLIP-400M","2025/01/01",58.1,156.38,70.9,49.8,42.9,54.0,805,74.6,39.6,52.5],[155,"granite-vision-3.2-2b",2.98,"granite-3.1-2b-instruct","SigLip","2025/06/20",57.9,156.38,70.8,54.6,39.0,59.7,790,78.6,40.7,40.5],[156,"Llama-3.2-11B-Vision-Instruct",11.0,"Llama-3.1-8B","","2024/10/07",57.7,158.5,65.8,49.8,48.0,47.7,753,77.3,40.3,57.6],[157,"GPT-4.1-nano-20250414",null,"","","2025/04/16",57.5,162.0,62.4,47.5,57.6,53.7,710,68.0,36.9,62.8],[158,"Molmo-7B-D",8.0,"Qwen2-7B","CLIP ViT-L/14","2024/10/12",57.4,148.25,70.9,56.1,49.1,48.7,656,81.0,46.4,41.5],[159,"Qwen2-VL-2B",2.0,"Qwen2-1.5B","QwenViT","2024/09/12",57.3,158.88,72.2,47.5,42.2,48.0,797,74.7,42.4,51.5],[160,"granite-vision-3.1-2b-preview",2.98,"granite-3.1-2b-instruct","SigLip","2025/06/20",57.3,162.25,69.2,56.1,35.4,60.5,783,77.7,41.4,39.6],[161,"GPT-4v (1106, detail-low)",null,"","","2023/12/23",57.2,151.38,73.8,49.7,53.8,49.4,516,75.9,46.5,56.8],[162,"InternLM-XComposer2",7.0,"InternLM2-7B","CLIP ViT-L/14","2024/01/26",57.1,150.62,77.6,56.2,41.4,59.8,532,81.2,41.0,46.7],[163,"InternVL3-1B",0.94,"Qwen2.5-0.5B","InternViT-300M-v2.5","2025/04/14",57.0,165.12,68.2,52.3,43.2,46.9,798,69.7,37.2,58.7],[164,"RekaFlash",null,"","","2024/05/07",56.5,163.38,73.0,50.2,44.8,47.7,692,75.6,39.2,52.5],[165,"GPT-4v (1106, detail-high)",null,"","","2024/04/22",56.4,163.5,65.5,50.4,59.3,48.4,678,71.4,39.3,49.0],[166,"Mini-InternVL-Chat-4B-V1.5",4.0,"Phi-3","InternViT-300M","2024/06/10",56.3,161.5,69.7,53.1,45.1,55.0,639,77.0,43.0,43.6],[167,"Idefics3-8B-Llama3",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/08/27",56.3,157.5,73.5,55.0,46.6,58.7,550,76.5,43.7,41.7],[168,"CogVLM2-19B-Chat",19.0,"Llama-3-8B-Instruct","EVA2-CLIP-E","2024/05/31",56.3,164.75,70.7,50.5,42.6,38.7,757,73.4,41.3,57.8],[169,"Gemini-1.0-Pro",null,"","","2023/12/23",56.1,163.75,69.7,38.6,49.0,46.5,680,72.9,45.7,58.6],[170,"XinYuan-VL-2B-Instruct",2.0,"Qwen2-1.5B","QwenViT","2024/09/27",55.9,168.0,75.2,52.3,42.9,47.7,780,74.2,34.9,42.3],[171,"Ross-Qwen2-7B",8.2,"Qwen2-7B","CLIP ViT-L/14","2025/01/17",55.9,158.25,75.4,53.9,49.0,52.5,553,79.4,38.7,43.2],[172,"Eagle-X5-34B-Chat",36.8,"Yi-34B","Clip-448
ConvNeXT-1024
SAM-1024
DET-1024
Pix2Struct-1024","2024/11/29",55.8,156.12,75.8,55.5,51.2,52.7,495,80.8,38.1,42.4],[173,"Gemma3-4B",4.3,"Gemma3-4B","SigLIP-400M","2025/03/19",55.4,170.75,66.4,47.9,47.3,46.3,660,70.7,40.8,57.8],[174,"LLaVA-Next-Yi-34B",34.8,"Yi-34B","CLIP ViT-L/14","2024/03/25",55.1,164.25,77.8,51.6,48.8,40.5,574,78.9,34.8,50.7],[175,"InternVL2.5-1B",1.0,"Qwen-2.5-0.5B","InternViT-300M-v2.5","2024/12/10",54.9,176.38,66.5,51.3,41.2,47.1,774,69.0,39.4,47.2],[176,"InternVL2.5-1B-MPO",1.0,"Qwen-2.5-0.5B","InternViT-300M-v2.5","2024/12/28",54.8,176.25,65.8,49.5,40.3,47.7,843,68.5,34.8,47.2],[177,"Claude3-Opus",null,"","","2024/03/28",54.4,176.5,59.1,45.7,54.9,46.1,694,70.6,37.8,51.7],[178,"VITA",47.0,"Mixtral-8x7B","InternViT-300M","2025/01/20",54.2,173.62,69.8,46.6,47.6,44.5,683,72.8,41.0,43.2],[179,"H2OVL-2B",2.2,"H2O-DANUBE2-1.8B","InternViT-300M","2024/10/31",54.1,186.0,64.8,48.9,36.3,56.9,778,70.9,35.9,41.1],[180,"InternVL2-2B",2.0,"InternLM2-1.8B","InternViT-300M","2024/07/11",54.1,182.62,69.6,49.8,36.3,47.0,781,74.1,38.0,39.7],[181,"MiniMonkey",2.2,"InternLM2-1.8B","InternViT-300M","2024/09/26",54.0,182.62,68.9,50.4,35.0,45.6,804,74.8,38.7,38.0],[182,"Phi-3-Vision",4.2,"Phi-3","CLIP ViT-L/14","2024/05/31",53.6,177.62,65.2,47.7,46.1,44.8,637,78.4,39.0,44.1],[183,"Claude3-Sonnet",null,"","","2024/03/28",53.5,180.25,63.9,44.2,47.4,45.0,646,69.9,41.3,51.7],[184,"Cambrian-13B",13.0,"Vicuna-v1.5-13B","CLIP ViT-L/14","2024/07/29",53.4,181.62,67.5,47.1,41.6,47.7,610,73.6,39.4,48.9],[185,"Phi-3.5-Vision",4.0,"Phi-3.5","CLIP ViT-L/14","2024/08/28",53.0,178.75,67.4,47.5,44.6,43.3,599,77.8,40.5,43.2],[186,"IDEFICS2-8B",8.0,"Mistral-7B","SigLIP-400M","2024/04/26",53.0,182.62,68.9,49.5,45.2,52.5,626,72.3,39.1,34.0],[187,"Cambrian-8B",8.0,"Vicuna-v1.5-7B","CLIP ViT-L/14","2024/07/11",52.9,185.0,68.2,50.7,41.8,48.1,614,74.6,30.6,48.0],[188,"HawkVL-2B",2.44,"Qwen2.5-1.5B","QwenViT","2025/06/16",52.8,186.12,64.5,48.1,43.6,43.3,763,66.6,40.9,38.9],[189,"Llama-3-MixSense-v1.1",8.0,"Llama-3-8B-Instruct","Florence-2-Large-FT","2024/08/21",52.8,183.38,71.9,53.1,39.3,50.4,577,72.4,36.2,41.1],[190,"Qwen-VL-Plus",null,"QwenLM","","2024/01/10",52.3,190.0,66.2,39.7,39.8,38.2,726,65.7,40.6,55.7],[191,"SmolVLM2",2.25,"SmolLM2-1.7M","SigLIP-400M","2025/03/13",52.2,191.12,61.1,46.0,41.6,51.5,725,69.7,40.6,34.9],[192,"Vintern-3B-beta",3.7,"Qwen-2.5-3B","InternViT-300M","2024/10/24",52.0,185.12,66.6,47.5,46.7,43.6,618,69.1,43.2,37.8],[193,"Molmo-7B-O",8.0,"Qwen2-7B","CLIP ViT-L/14","2024/10/20",52.0,186.38,62.9,50.1,42.2,43.9,616,75.7,39.4,40.6],[194,"LLaVA-Next-Qwen-32B",33.0,"Qwen-1.5-32B","SigLIP-400M","2024/08/08",51.2,180.88,76.8,48.5,41.8,39.6,384,75.5,39.3,50.0],[195,"XGen-MM-Instruct-Interleave-v1.5",4.4,"Phi-3","SigLIP-400M","2024/09/06",51.1,188.88,69.8,48.4,40.9,40.6,551,74.2,39.8,40.2],[196,"Eagle-X5-13B",15.0,"Vicuna-v1.5-13B","Clip-448
ConvNeXT-1024
SAM-1024
DET-1024
Pix2Struct-1024","2024/09/26",50.8,193.12,67.6,43.7,39.7,40.8,574,77.2,37.8,42.6],[197,"Claude3-Haiku",null,"","","2024/03/28",50.6,195.88,57.1,38.1,49.7,42.6,658,65.6,39.2,46.4],[198,"XGen-MM-Instruct-DPO-v1.5",4.4,"Phi-3","SigLIP-400M","2024/09/06",50.2,196.25,70.3,47.2,40.1,40.1,541,72.0,37.0,41.0],[199,"Janus-Pro-7B",7.42,"DeepSeek-7B","SigLIP-400M","2025/02/02",50.2,197.25,59.1,46.5,41.6,42.5,595,68.1,39.5,45.1],[200,"Mini-InternVL-Chat-2B-V1.5",2.0,"InternLM2-1.8B","InternViT-300M","2024/06/10",49.8,204.62,65.2,46.7,37.4,41.3,652,69.7,37.3,35.5],[201,"LLaVA-Next-Llama3",8.0,"Llama-3-8B-Instruct","CLIP ViT-L/14","2024/07/29",49.7,198.38,69.8,43.9,43.1,37.7,531,72.8,33.1,44.4],[202,"VILA1.5-13B",13.0,"Vicuna-v1.5-13B","SigLIP-400M","2024/08/25",49.5,196.12,68.5,44.2,41.1,42.3,460,69.9,39.3,45.0],[203,"Mantis-8B-Idefics2",8.0,"Mistral-7B","SigLIP-400M","2024/08/08",49.4,201.25,69.7,44.8,41.6,41.2,542,67.3,37.1,39.3],[204,"XVERSE-V-13B",13.0,"XVERSE-13B","CLIP ViT-L/14","2024/05/10",49.4,201.62,66.3,49.3,44.1,45.1,489,70.6,33.3,37.8],[205,"Falcon2-VLM-11B",11.4,"Falcon2-11B","CLIP ViT-L/14","2024/10/30",48.7,203.5,67.2,45.4,39.1,37.6,491,77.9,35.9,37.2],[206,"LLaVA-Next-Interleave-7B-DPO",8.0,"Qwen-1.5-7B","SigLIP-400M","2024/07/29",48.4,201.88,71.3,45.3,40.1,35.3,460,72.9,36.8,39.8],[207,"Bunny-Llama3-8B",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/07/18",48.4,200.75,72.9,45.4,43.4,35.2,444,69.4,37.7,39.1],[208,"Monkey-Chat",9.8,"Qwen-7B","ViT-BigHuge","2024/01/16",48.4,204.88,67.3,40.7,40.7,36.0,534,68.5,39.3,41.0],[209,"InternVL2-1B",1.0,"Qwen2-0.5B","InternViT-300M","2024/07/11",48.4,214.62,59.7,45.6,36.7,40.4,755,63.8,34.3,31.5],[210,"360VL-70B",70.0,"Llama-3-70B-Instruct","CLIP ViT-L/14","2024/05/25",48.2,196.25,75.0,48.1,53.4,37.9,397,71.9,34.8,24.7],[211,"SmolVLM-Instruct",2.3,"SmolLM2-1.7B","SigLIP-400M","2025/01/27",48.1,210.25,57.4,41.7,38.8,43.6,656,64.2,39.5,33.8],[212,"CogVLM-17B-Chat",17.0,"Vicuna-v1.5-7B","EVA2-CLIP-E","2024/01/03",47.9,212.0,58.8,39.9,37.3,35.3,590,63.3,35.4,54.5],[213,"MiniCPM-V-2",2.8,"MiniCPM-2.4B","SigLIP-400M","2024/04/15",47.9,212.38,65.8,39.1,38.2,39.8,605,62.9,36.1,41.0],[214,"LLaVA-Next-Vicuna-13B",13.4,"Vicuna-v1.5-13B","CLIP ViT-L/14","2024/03/25",47.7,212.62,66.5,40.4,37.3,35.1,537,72.2,31.8,44.9],[215,"Emu3_chat",8.49,"","","2025/01/26",47.5,219.0,52.7,46.6,33.9,47.6,667,71.5,31.7,29.1],[216,"LLaVA-Next-Interleave-7B",8.0,"Qwen-1.5-7B","SigLIP-400M","2024/08/08",47.5,205.25,71.1,44.5,41.7,34.0,411,73.8,34.8,39.1],[217,"Eagle-X5-7B",9.0,"Vicuna-v1.5-7B","Clip-448
ConvNeXT-1024
SAM-1024
DET-1024
Pix2Struct-1024","2024/09/26",47.4,213.88,64.0,41.7,37.6,38.8,551,73.6,35.4,33.3],[218,"InternLM-XComposer2-1.8B",2.0,"InternLM2-1.8B","CLIP ViT-L/14","2024/06/09",47.0,215.75,68.6,46.4,29.7,50.3,447,71.1,33.7,31.2],[219,"RekaEdge",null,"","","2024/05/31",46.7,215.5,60.1,39.6,42.4,37.5,506,67.4,35.1,40.5],[220,"PaliGemma-3B-mix-448",3.0,"Gemma-2B","SigLIP-400M","2024/05/17",46.5,222.62,65.6,48.3,34.9,28.5,614,68.3,32.2,33.1],[221,"DeepSeek-VL-7B",7.3,"DeekSeek-7B","SAM-B
SigLIP-L","2024/03/21",46.2,216.12,70.7,40.5,38.3,37.2,435,65.3,34.5,39.7],[222,"OmniLMM-12B",12.0,"Zephyr-7B-β","EVA-02-5B","2024/02/07",46.2,213.88,64.3,39.6,41.8,35.2,420,63.3,35.8,47.4],[223,"MolmoE-1B",7.2,"OLMoE-1B-7B-0924","CLIP ViT-L/14","2024/10/21",46.1,220.12,52.4,43.1,33.9,37.6,547,71.0,38.0,37.8],[224,"LLaVA-Next-Mistral-7B",7.6,"Mistral-7B","CLIP ViT-L/14","2024/03/25",45.8,225.38,63.1,38.4,37.0,34.9,531,69.0,29.1,42.2],[225,"LLaVA-LLaMA-3-8B",8.0,"Llama-3-8B-Instruct","CLIP ViT-L/14","2024/05/07",45.6,220.88,64.3,46.1,39.2,40.6,420,69.9,28.7,34.1],[226,"Qwen-VL-Chat",9.6,"Qwen-7B","ViT-G/16","2023/08/24",45.2,224.0,59.1,34.5,37.0,35.3,488,63.0,36.8,47.3],[227,"SmolVLM-Instruct-DPO",2.3,"SmolLM2-1.7B","SigLIP-400M","2025/01/27",44.8,222.5,55.4,39.2,39.7,42.9,500,62.2,39.8,29.3],[228,"LLaVA-Next-Vicuna-7B",7.1,"Vicuna-v1.5-7B","CLIP ViT-L/14","2024/03/25",44.8,231.0,63.0,37.6,37.6,32.5,532,67.0,27.6,40.2],[229,"Slime-8B",8.0,"Llama-3-8B-Instruct","CLIP ViT-L/14","2024/09/14",44.2,219.75,66.3,43.5,38.8,41.8,233,68.5,31.8,40.0],[230,"Llama-3-VILA1.5-8B",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/08/25",44.0,225.62,57.9,39.7,37.4,37.4,438,58.8,35.3,41.9],[231,"Monkey",9.8,"Qwen-7B","ViT-BigHuge","2024/01/11",43.9,232.0,55.0,37.0,38.9,33.5,514,62.5,34.9,38.1],[232,"LLaVA-InternLM2-20B (QLoRA)",20.2,"InternLM2-20B","CLIP ViT-L/14","2024/01/17",43.8,226.12,71.4,41.9,39.4,28.5,400,65.4,26.4,37.2],[233,"Yi-VL-34B",34.6,"Yi-34B","CLIP ViT-H/14","2024/01/25",43.5,220.5,67.8,40.5,45.1,31.6,290,65.9,35.3,32.7],[234,"H2OVL-800M",0.83,"H2O-DANUBE3-500M","InternViT-300M","2024/10/31",43.5,234.25,47.7,39.5,32.1,39.8,754,53.5,29.6,30.2],[235,"TransCore-M",13.4,"PCITransGPT-13B","CLIP ViT-L/14","2024/04/16",43.2,232.0,67.8,35.6,41.0,32.5,405,64.1,27.3,36.9],[236,"LLaVA-InternLM2-7B (QLoRA)",8.1,"InternLM2-7B","CLIP ViT-L/14","2024/01/17",43.1,229.88,71.0,38.3,40.1,28.9,402,63.6,26.7,35.9],[237,"Moondream2",1.9,"SigLIP-400M","Phi-1.5","2024/10/20",43.0,233.25,48.1,42.1,29.3,33.8,585,58.8,33.0,40.4],[238,"Mantis-8B-siglip-llama3",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/08/08",42.9,228.38,64.6,41.3,41.1,32.7,347,60.4,34.2,34.4],[239,"Vintern-1B-v2",3.7,"Qwen2-0.5B","InternViT-300M","2024/11/16",42.6,237.25,53.4,39.0,31.6,33.1,627,56.5,37.7,26.4],[240,"ShareGPT4V-13B",13.4,"Vicuna-v1.5-13B","CLIP ViT-L/14","2023/12/08",42.5,235.88,65.2,38.3,36.6,29.4,398,61.4,28.4,41.1],[241,"LLaVA-OneVision-0.5B",1.0,"Qwen2-0.5B","SigLIP-400M","2024/09/16",42.5,243.12,56.8,37.7,32.7,35.9,583,59.4,27.9,31.5],[242,"VILA1.5-3B",3.0,"Sheared-LLaMA-2.7B","SigLIP-400M","2024/08/25",42.1,238.75,58.8,40.6,34.2,31.8,437,57.9,31.2,38.8],[243,"LLaVA-v1.5-13B (QLoRA)",13.4,"Vicuna-v1.5-13B","CLIP ViT-L/14","2023/12/28",41.6,241.25,64.8,40.1,35.2,28.5,407,61.3,26.2,35.9],[244,"Slime-13B",13.0,"Vicuna-v1.5-13B","CLIP ViT-L/14","2024/09/14",41.4,235.75,59.8,39.4,36.4,34.5,245,66.0,32.1,38.9],[245,"Parrot-7B",8.0,"Qwen2-7B","CLIP ViT-L/14","2024/08/22",41.4,236.0,69.0,39.1,36.7,27.2,334,60.9,35.2,29.8],[246,"SmolVLM-500M",0.51,"SmolLM2-360M","ViT-93M","2025/01/27",41.3,241.25,41.9,38.3,33.6,39.8,609,59.2,31.1,25.7],[247,"LLaVA-OneVision-0.5B (SI)",1.0,"Qwen2-0.5B","SigLIP-400M","2024/09/17",41.3,244.25,50.3,37.5,36.2,32.7,565,53.5,31.7,32.2],[248,"Yi-VL-6B",6.6,"Yi-6B","CLIP ViT-H/14","2024/01/25",41.1,235.62,64.2,37.7,40.3,29.7,290,59.8,36.0,32.1],[249,"MiniCPM-V",3.0,"MiniCPM-2.4B","SigLIP-400M","2024/02/07",41.0,239.0,60.5,38.6,38.3,30.6,366,56.3,36.2,31.1],[250,"SmolVLM2-500M",0.51,"SmolLM2-360M","ViT-93M","2025/03/13",40.9,244.12,41.6,38.2,34.1,37.5,609,57.3,27.7,29.9],[251,"abab6.5s",null,"","","2024/12/11",40.9,247.62,57.7,32.1,34.0,23.5,622,52.0,33.4,32.2],[252,"Janus-1.3B",2.1,"DeepSeek-1B","SigLIP-400M","2024/10/24",40.2,248.12,50.3,37.6,31.2,33.7,482,52.8,30.3,37.5],[253,"Slime-7B",7.0,"Vicuna-v1.5-7B","CLIP ViT-L/14","2024/09/14",39.9,243.0,58.7,37.3,36.6,36.9,211,61.9,32.8,33.9],[254,"ShareCaptioner",8.0,"InternLM-7B","EVA-G","2024/01/03",39.8,245.5,60.8,38.4,36.3,29.5,322,56.7,34.2,30.1],[255,"ShareGPT4V-7B",7.2,"Vicuna-v1.5-7B","CLIP ViT-L/14","2023/12/08",39.8,247.88,61.6,35.7,37.2,26.6,371,58.0,28.6,33.4],[256,"LLaVA-InternLM-7B (QLoRA)",7.6,"InternLM-7B","CLIP ViT-L/14","2023/12/28",39.8,247.25,65.0,35.5,36.9,27.1,347,58.0,28.9,32.4],[257,"DeepSeek-VL-1.3B",2.0,"DeekSeek-1B","SAM-B
SigLIP-L","2024/03/21",39.7,249.62,63.8,39.9,33.8,30.7,413,51.5,27.6,29.2],[258,"AKI-4B",4.33,"Phi-3.5","SigLIP-400M","2025/03/25",39.4,246.38,55.6,37.8,36.3,28.5,308,56.5,33.9,36.2],[259,"LLaVA-v1.5-13B",13.4,"Vicuna-v1.5-13B","CLIP ViT-L/14","2023/10/05",39.3,249.75,60.6,34.3,37.0,27.7,337,61.1,24.5,35.6],[260,"Emu2_chat",37.0,"Llama-33B","EVA-02-CLIP-E-plus","2024/01/17",39.2,248.75,52.8,40.7,35.0,31.3,436,49.7,29.5,31.0],[261,"SmolVLM-Synthetic",2.3,"SmolLM2-1.7B","SigLIP-400M","2025/01/27",38.6,246.38,43.1,34.9,38.6,31.5,461,50.8,34.8,29.3],[262,"Mantis-8B-clip-llama3",8.0,"Llama-3-8B-Instruct","CLIP ViT-L/14","2024/08/08",38.5,245.38,62.6,38.3,40.2,30.4,200,56.6,31.3,28.6],[263,"LLaVA-v1.5-7B (QLoRA)",7.2,"Vicuna-v1.5-7B","CLIP ViT-L/14","2023/12/28",38.4,256.5,62.1,34.6,33.7,25.4,385,55.9,25.2,32.2],[264,"mPLUG-Owl2",8.2,"Llama-2-7B","CLIP ViT-L/14","2023/11/10",37.8,253.5,60.8,34.8,34.7,25.5,255,55.7,29.4,35.7],[265,"LLaVA-v1.5-7B",7.2,"Vicuna-v1.5-7B","CLIP ViT-L/14","2023/10/05",36.9,258.5,53.1,33.1,35.7,25.5,318,55.5,27.6,32.9],[266,"SmolVLM-256M",0.26,"SmolLM2-135M","ViT-93M","2025/01/27",34.4,259.25,26.9,34.5,28.9,37.0,527,46.4,27.9,21.1],[267,"Mantis-8B-Fuyu",8.0,"Fuyu-8B","","2024/09/07",34.2,262.75,38.0,34.4,30.8,30.2,366,46.8,29.8,27.3],[268,"Moondream1",1.9,"SigLIP-400M","Phi-1.5","2024/09/26",33.2,265.75,39.1,35.3,31.4,24.7,309,49.1,29.2,26.0],[269,"MMAlaya",7.8,"Alaya-7B-Chat","EVA-G","2024/01/29",33.1,265.38,56.2,34.3,32.0,22.9,223,42.3,32.9,22.2],[270,"InternLM-XComposer",8.0,"InternLM-7B","EVA-G","2023/09/26",31.9,252.0,25.9,6.9,35.6,29.9,290,56.9,36.0,35.2],[271,"IDEFICS-80B-Instruct",80.0,"Llama-65B","CLIP ViT-H/14","2023/07/25",31.6,262.88,27.9,26.1,24.0,28.9,283,54.8,23.4,39.7],[272,"LLaVA-v1-7B",7.2,"Llama-7B","CLIP ViT-L/14","2023/04/17",31.3,269.25,38.7,27.1,34.1,25.4,269,48.3,21.6,28.3],[273,"InstructBLIP-7B",8.0,"Vicuna-7B","EVA-G","2023/05/11",31.1,265.12,28.4,32.7,30.6,24.6,276,40.6,31.2,33.1],[274,"SmolVLM2-256M",0.26,"SmolLM2-135M","ViT-93M","2025/03/13",30.8,262.5,6.5,30.9,29.0,34.0,566,39.2,24.3,25.5],[275,"Qwen-VL",9.6,"Qwen-7B","ViT-G/16","2023/08/24",28.3,270.38,32.9,32.5,29.6,18.1,127,57.7,29.9,13.0],[276,"IDEFICS-9B-Instruct",9.0,"Llama-7B","CLIP ViT-H/14","2023/07/25",27.2,273.62,27.4,21.6,18.4,25.1,252,42.2,27.3,30.0],[277,"VisualGLM",8.0,"ChatGLM 6B","EVA-CLIP","2023/05/17",26.7,276.12,35.7,25.9,29.9,23.9,170,41.2,25.0,14.8],[278,"PandaGPT-13B",14.0,"Vicuna-13B","ImageBind ViT-H/14","2023/05/25",26.5,273.5,34.5,25.6,32.9,25.6,36,50.3,20.0,19.6],[279,"Chameleon-30B",30.0,"","","2024/07/29",26.5,268.88,32.7,31.8,38.8,23.8,27,53.7,18.6,9.7],[280,"OpenFlamingo v2",9.0,"MPT 7B","CLIP ViT-L/14","2023/06/28",22.8,276.0,7.9,26.9,28.8,19.9,149,31.7,29.4,23.3],[281,"MiniGPT-4-v1-7B",8.0,"Vicuna-7B","EVA-G","2023/04/20",21.9,275.62,20.8,16.3,23.6,21.3,172,28.4,31.9,15.6],[282,"Kosmos2",1.7,"","","2024/10/19",21.0,279.0,1.1,24.9,23.7,24.5,244,25.6,19.8,23.7],[283,"Chameleon-7B",7.0,"","","2024/07/29",21.0,280.62,19.8,31.1,22.4,22.5,5,46.0,17.1,8.3],[284,"MiniGPT-4-v2",8.0,"Llama-2-13B","EVA-G","2023/10/27",18.4,277.25,3.2,21.3,25.0,24.0,31,30.5,30.0,10.5],[285,"KoreaDeep-VLM-OCR-32B",32.0,"","","2026/02/13",null,null,null,null,null,null,864,null,null,null]],"metadata":null},"headers":["1","2","3"],"row_count":[1,"dynamic"],"col_count":[3,"dynamic"],"datatype":["number","html","number","html","html","str","number","number","number","number","number","number","number","number","number","number"],"type":"pandas","latex_delimiters":[{"left":"$$","right":"$$","display":true}],"show_label":true,"height":500,"min_width":160,"interactive":false,"visible":true,"elem_classes":[],"wrap":true,"line_breaks":true,"column_widths":[],"name":"dataframe","_selectable":false},"skip_api":false,"component_class_id":"6a51bb3357f2e94c40fb8d4fbe06aa8e","key":null,"api_info":{"properties":{"headers":{"items":{"type":"string"},"title":"Headers","type":"array"},"data":{"items":{"items":{},"type":"array"},"title":"Data","type":"array"},"metadata":{"anyOf":[{"additionalProperties":{"anyOf":[{"items":{},"type":"array"},{"type":"null"}]},"type":"object"},{"type":"null"}],"default":null,"title":"Metadata"}},"required":["headers","data"],"title":"DataframeData","type":"object"},"example_inputs":{"headers":["a","b"],"data":[["foo","bar"]]}},{"id":12,"type":"form","props":{"scale":0,"min_width":0,"name":"form"},"skip_api":true,"component_class_id":"43cda85c6ff7a5dd8f83d29496b014ee","key":null},{"id":13,"type":"tabitem","props":{"label":"🔍 About","visible":true,"interactive":true,"id":1,"elem_id":"about","name":"tab"},"skip_api":true,"component_class_id":"18f46968e2b273dc5dbda0fe78433d7e","key":null},{"id":14,"type":"markdown","props":{"value":"![LOGO](http://opencompass.openxlab.space/utils/MMLB.jpg)\n\nA Toolkit for Evaluating Large Vision-Language Models. \n\n[![][github-contributors-shield]][github-contributors-link] • [![][github-forks-shield]][github-forks-link] • [![][github-stars-shield]][github-stars-link] • [![][github-issues-shield]][github-issues-link] • [![][github-license-shield]][github-license-link]\n\nEnglish | [简体中文](/docs/zh-CN/README_zh-CN.md) | [日本語](/docs/ja/README_ja.md)\n\n🏆 OC Learderboard •\n🏗️Quickstart •\n📊Datasets & Models •\n🛠️Development \n\n🤗 HF Leaderboard •\n🤗 Evaluation Records •\n🤗 HF Video Leaderboard •\n\n🔊 Discord •\n📝 Report •\n🎯Goal •\n🖊️Citation \n\n\n**VLMEvalKit** (the python package name is **vlmeval**) is an **open-source evaluation toolkit** of **large vision-language models (LVLMs)**. It enables **one-command evaluation** of LVLMs on various benchmarks, without the heavy workload of data preparation under multiple repositories. In VLMEvalKit, we adopt **generation-based evaluation** for all LVLMs, and provide the evaluation results obtained with both **exact matching** and **LLM-based answer extraction**.\n\n## Recent Codebase Changes\n- **[2025-09-12]** **Major Update: Improved Handling for Models with Thinking Mode**\n\n A new feature in [PR 1229](https://github.com/open-compass/VLMEvalKit/pull/1175) that improves support for models with thinking mode. VLMEvalKit now allows for the use of a custom `split_thinking` function. **We strongly recommend this for models with thinking mode to ensure the accuracy of evaluation**. To use this new functionality, please enable the Environment Variable: `SPLIT_THINK=True`. By default, the function will parse content within `...` tags and store it in the `thinking` key of the output. For more advanced customization, you can also create a `split_think` function for model. Please see the InternVL implementation for an example.\n- **[2025-09-12]** **Major Update: Improved Handling for Long Response(More than 16k/32k)**\n\n A new feature in [PR 1229](https://github.com/open-compass/VLMEvalKit/pull/1175) that improves support for models with long response outputs. VLMEvalKit can now save prediction files in TSV format. **Since individual cells in an `.xlsx` file are limited to 32,767 characters, we strongly recommend using this feature for models that generate long responses (e.g., exceeding 16k or 32k tokens) to prevent data truncation.** To use this new functionality, please enable the Environment Variable: `PRED_FORMAT=tsv`.\n- **[2025-08-04]** In [PR 1175](https://github.com/open-compass/VLMEvalKit/pull/1175), we refine the `can_infer_option` and `can_infer_text`, which increasingly route the evaluation to LLM choice extractors and empirically leads to slight performance improvement for MCQ benchmarks.\n\n## 🆕 News\n\n- **[2026-04-08]** Supported [**Video-MME-v2**](https://github.com/MME-Benchmarks/Video-MME-v2). Video-MME-v2 is an authoritative benchmark towards the next stage in video understanding evaluation. 🔥🔥🔥\n- **[2025-07-07]** Supported [**SeePhys**](https://seephys.github.io/), which is a ​full spectrum multimodal benchmark for evaluating physics reasoning across different knowledge levels. thanks to [**Quinn777**](https://github.com/Quinn777) 🔥🔥🔥\n- **[2025-07-02]** Supported [**OvisU1**](https://huggingface.co/AIDC-AI/Ovis-U1-3B), thanks to [**liyang-7**](https://github.com/liyang-7) 🔥🔥🔥\n- **[2025-06-16]** Supported [**PhyX**](https://phyx-bench.github.io/), a benchmark aiming to assess capacity for physics-grounded reasoning in visual scenarios. 🔥🔥🔥\n- **[2025-05-24]** To facilitate faster evaluations for large-scale or thinking models, **VLMEvalKit supports multi-node distributed inference** using **LMDeploy** (supports *InternVL Series, QwenVL Series, LLaMa4*) or **VLLM**(supports *QwenVL Series, LLaMa4*). You can activate this feature by adding the ```use_lmdeploy``` or ```use_vllm``` flag to your custom model configuration in [config.py](vlmeval/config.py) . Leverage these tools to significantly speed up your evaluation workflows 🔥🔥🔥\n- **[2025-05-24]** Supported Models: **InternVL3 Series, Gemini-2.5-Pro, Kimi-VL, LLaMA4, NVILA, Qwen2.5-Omni, Phi4, SmolVLM2, Grok, SAIL-VL-1.5, WeThink-Qwen2.5VL-7B, Bailingmm, VLM-R1, Taichu-VLR**. Supported Benchmarks: **HLE-Bench, MMVP, MM-AlignBench, Creation-MMBench, MM-IFEval, OmniDocBench, OCR-Reasoning, EMMA, ChaXiv，MedXpertQA, Physics, MSEarthMCQ, MicroBench, MMSci, VGRP-Bench, wildDoc, TDBench, VisuLogic, CVBench, LEGO-Puzzles, Video-MMLU, QBench-Video, MME-CoT, VLM2Bench, VMCBench, MOAT, Spatial457 Benchmark**. Please refer to [**VLMEvalKit Features**](https://aicarrier.feishu.cn/wiki/Qp7wwSzQ9iK1Y6kNUJVcr6zTnPe?table=tblsdEpLieDoCxtb) for more details. Thanks to all contributors 🔥🔥🔥\n- **[2025-02-20]** Supported Models: **InternVL2.5 Series, Qwen2.5VL Series, QVQ-72B, Doubao-VL, Janus-Pro-7B, MiniCPM-o-2.6, InternVL2-MPO, LLaVA-CoT, Hunyuan-Standard-Vision, Ovis2, Valley, SAIL-VL, Ross, Long-VITA, EMU3, SmolVLM**. Supported Benchmarks: **MMMU-Pro, WeMath, 3DSRBench, LogicVista, VL-RewardBench, CC-OCR, CG-Bench, CMMMU, WorldSense**. Thanks to all contributors 🔥🔥🔥\n- **[2024-12-11]** Supported [**NaturalBench**](https://huggingface.co/datasets/BaiqiL/NaturalBench), a vision-centric VQA benchmark (NeurIPS'24) that challenges vision-language models with simple questions about natural imagery.\n- **[2024-12-02]** Supported [**VisOnlyQA**](https://github.com/psunlpgroup/VisOnlyQA/), a benchmark for evaluating the visual perception capabilities 🔥🔥🔥\n- **[2024-11-26]** Supported [**Ovis1.6-Gemma2-27B**](https://huggingface.co/AIDC-AI/Ovis1.6-Gemma2-27B), thanks to [**runninglsy**](https://github.com/runninglsy) 🔥🔥🔥\n- **[2024-11-25]** Create a new flag `VLMEVALKIT_USE_MODELSCOPE`. By setting this environment variable, you can download the video benchmarks supported from [**modelscope**](https://www.modelscope.cn) 🔥🔥🔥\n\n## 🏗️ QuickStart\n\nSee [[QuickStart](/docs/en/Quickstart.md) | [快速开始](/docs/zh-CN/Quickstart.md)] for a quick start guide.\n\n## 📊 Datasets, Models, and Evaluation Results\n\n### Evaluation Results\n\n**The performance numbers on our official multi-modal leaderboards can be downloaded from here!**\n\n[**OpenVLM Leaderboard**](https://huggingface.co/spaces/opencompass/open_vlm_leaderboard): [**Download All DETAILED Results**](http://opencompass.openxlab.space/assets/OpenVLM.json).\n\nCheck **Supported Benchmarks** Tab in [**VLMEvalKit Features**](https://aicarrier.feishu.cn/wiki/Qp7wwSzQ9iK1Y6kNUJVcr6zTnPe?table=tblsdEpLieDoCxtb) to view all supported image & video benchmarks (70+).\n\nCheck **Supported LMMs** Tab in [**VLMEvalKit Features**](https://aicarrier.feishu.cn/wiki/Qp7wwSzQ9iK1Y6kNUJVcr6zTnPe?table=tblsdEpLieDoCxtb) to view all supported LMMs, including commercial APIs, open-source models, and more (200+).\n\n**Transformers Version Recommendation:**\n\nNote that some VLMs may not be able to run under certain transformer versions, we recommend the following settings to evaluate each VLM:\n\n- **Please use** `transformers==4.33.0` **for**: `Qwen series`, `Monkey series`, `InternLM-XComposer Series`, `mPLUG-Owl2`, `OpenFlamingo v2`, `IDEFICS series`, `VisualGLM`, `MMAlaya`, `ShareCaptioner`, `MiniGPT-4 series`, `InstructBLIP series`, `PandaGPT`, `VXVERSE`.\n- **Please use** `transformers==4.36.2` **for**: `Moondream1`.\n- **Please use** `transformers==4.37.0` **for**: `LLaVA series`, `ShareGPT4V series`, `TransCore-M`, `LLaVA (XTuner)`, `CogVLM Series`, `EMU2 Series`, `Yi-VL Series`, `MiniCPM-[V1/V2]`, `OmniLMM-12B`, `DeepSeek-VL series`, `InternVL series`, `Cambrian Series`, `VILA Series`, `Llama-3-MixSenseV1_1`, `Parrot-7B`, `PLLaVA Series`.\n- **Please use** `transformers==4.40.0` **for**: `IDEFICS2`, `Bunny-Llama3`, `MiniCPM-Llama3-V2.5`, `360VL-70B`, `Phi-3-Vision`, `WeMM`.\n- **Please use** `transformers==4.42.0` **for**: `AKI`.\n- **Please use** `transformers==4.44.0` **for**: `Moondream2`, `H2OVL series`.\n- **Please use** `transformers==4.45.0` **for**: `Aria`.\n- **Please use** `transformers==4.48.0` (or `4.46.0`) **for**: `LLaVA-Next series` (e.g., `llava-hf/llava-v1.6-vicuna-7b-hf`).\n- **Please use** `transformers==latest` **for**: `PaliGemma-3B`, `Chameleon series`, `Video-LLaVA-7B-HF`, `Ovis series`, `Mantis series`, `MiniCPM-V2.6`, `OmChat-v2.0-13B-sinlge-beta`, `Idefics-3`, `GLM-4v-9B`, `VideoChat2-HD`, `RBDash_72b`, `Llama-3.2 series`, `Kosmos series`.\n- **Please use** `transformers==4.50.3` (or `4.46.1` or `4.51` or `4.53`) **for**: `Molmo series`.\n- **Please use** `transformers>=5.2.0` **for**: `Qwen3.5 series`.\n\n**Torchvision Version Recommendation:**\n\nNote that some VLMs may not be able to run under certain torchvision versions, we recommend the following settings to evaluate each VLM:\n\n- **Please use** `torchvision>=0.16` **for**: `Moondream series` and `Aria`\n\n**Flash-attn Version Recommendation:**\n\nNote that some VLMs may not be able to run under certain flash-attention versions, we recommend the following settings to evaluate each VLM:\n\n- **Please use** `pip install flash-attn --no-build-isolation` **for**: `Aria`\n\n```python\n# Demo\nfrom vlmeval.config import supported_VLM\nmodel = supported_VLM['idefics_9b_instruct']()\n# Forward Single Image\nret = model.generate(['assets/apple.jpg', 'What is in this image?'])\nprint(ret) # The image features a red apple with a leaf on it.\n# Forward Multiple Images\nret = model.generate(['assets/apple.jpg', 'assets/apple.jpg', 'How many apples are there in the provided images? '])\nprint(ret) # There are two apples in the provided images.\n```\n\n## 🛠️ Development Guide\n\nTo develop custom benchmarks, VLMs, or simply contribute other codes to **VLMEvalKit**, please refer to [[Development_Guide](/docs/en/Development.md) | [开发指南](/docs/zh-CN/Development.md)].\n\n**Call for contributions**\n\nTo promote the contribution from the community and share the corresponding credit (in the next report update):\n\n- All Contributions will be acknowledged in the report.\n- Contributors with 3 or more major contributions (implementing an MLLM, benchmark, or major feature) can join the author list of [VLMEvalKit Technical Report](https://www.arxiv.org/abs/2407.11691) on ArXiv. Eligible contributors can create an issue or dm kennyutc in [VLMEvalKit Discord Channel](https://discord.com/invite/evDT4GZmxN).\n\nHere is a [contributor list](/docs/en/Contributors.md) we curated based on the records.\n\n## 🎯 The Goal of VLMEvalKit\n\n**The codebase is designed to:**\n\n1. Provide an **easy-to-use**, **opensource evaluation toolkit** to make it convenient for researchers & developers to evaluate existing LVLMs and make evaluation results **easy to reproduce**.\n2. Make it easy for VLM developers to evaluate their own models. To evaluate the VLM on multiple supported benchmarks, one just need to **implement a single `generate_inner()` function**, all other workloads (data downloading, data preprocessing, prediction inference, metric calculation) are handled by the codebase.\n\n**The codebase is not designed to:**\n\n1. Reproduce the exact accuracy number reported in the original papers of all **3rd party benchmarks**. The reason can be two-fold:\n 1. VLMEvalKit uses **generation-based evaluation** for all VLMs (and optionally with **LLM-based answer extraction**). Meanwhile, some benchmarks may use different approaches (SEEDBench uses PPL-based evaluation, *eg.*). For those benchmarks, we compare both scores in the corresponding result. We encourage developers to support other evaluation paradigms in the codebase.\n 2. By default, we use the same prompt template for all VLMs to evaluate on a benchmark. Meanwhile, **some VLMs may have their specific prompt templates** (some may not covered by the codebase at this time). We encourage VLM developers to implement their own prompt template in VLMEvalKit, if that is not covered currently. That will help to improve the reproducibility.\n\n## 🖊️ Citation\n\nIf you find this work helpful, please consider to **star🌟** this repo. Thanks for your support!\n\n[![Stargazers repo roster for @open-compass/VLMEvalKit](https://reporoster.com/stars/open-compass/VLMEvalKit)](https://github.com/open-compass/VLMEvalKit/stargazers)\n\nIf you use VLMEvalKit in your research or wish to refer to published OpenSource evaluation results, please use the following BibTeX entry and the BibTex entry corresponding to the specific VLM / benchmark you used.\n\n```bib\n@inproceedings{duan2024vlmevalkit,\n title={Vlmevalkit: An open-source toolkit for evaluating large multi-modality models},\n author={Duan, Haodong and Yang, Junming and Qiao, Yuxuan and Fang, Xinyu and Chen, Lin and Liu, Yuan and Dong, Xiaoyi and Zang, Yuhang and Zhang, Pan and Wang, Jiaqi and others},\n booktitle={Proceedings of the 32nd ACM International Conference on Multimedia},\n pages={11198--11201},\n year={2024}\n}\n```\n\n

🔝Back to top

\n\n[github-contributors-link]: https://github.com/open-compass/VLMEvalKit/graphs/contributors\n[github-contributors-shield]: https://img.shields.io/github/contributors/open-compass/VLMEvalKit?color=c4f042&labelColor=black&style=flat-square\n[github-forks-link]: https://github.com/open-compass/VLMEvalKit/network/members\n[github-forks-shield]: https://img.shields.io/github/forks/open-compass/VLMEvalKit?color=8ae8ff&labelColor=black&style=flat-square\n[github-issues-link]: https://github.com/open-compass/VLMEvalKit/issues\n[github-issues-shield]: https://img.shields.io/github/issues/open-compass/VLMEvalKit?color=ff80eb&labelColor=black&style=flat-square\n[github-license-link]: https://github.com/open-compass/VLMEvalKit/blob/main/LICENSE\n[github-license-shield]: https://img.shields.io/github/license/open-compass/VLMEvalKit?color=white&labelColor=black&style=flat-square\n[github-stars-link]: https://github.com/open-compass/VLMEvalKit/stargazers\n[github-stars-shield]: https://img.shields.io/github/stars/open-compass/VLMEvalKit?color=ffcb47&labelColor=black&style=flat-square","show_label":true,"rtl":false,"latex_delimiters":[{"left":"$$","right":"$$","display":true}],"visible":true,"elem_classes":[],"sanitize_html":true,"line_breaks":false,"header_links":false,"show_copy_button":false,"name":"markdown","_selectable":false},"skip_api":false,"component_class_id":"0f35515b9a3362b42bb6721c836157a0","key":null,"api_info":{"type":"string"},"example_inputs":"# Hello!"},{"id":15,"type":"tabitem","props":{"label":"📊 SEEDBench_IMG Leaderboard","visible":true,"interactive":true,"id":2,"elem_id":"SEEDBench_IMG","name":"tab"},"skip_api":true,"component_class_id":"18f46968e2b273dc5dbda0fe78433d7e","key":null},{"id":16,"type":"markdown","props":{"value":"## SEEDBench_IMG Scores (ChatGPT Answer Extraction / Official Leaderboard)\n\n- **Overall**: The overall accuracy across all questions with **ChatGPT answer matching**.\n- **Overall (official)**: SEEDBench_IMG acc on the official leaderboard (if applicable). ","show_label":true,"rtl":false,"latex_delimiters":[{"left":"$$","right":"$$","display":true}],"visible":true,"elem_classes":[],"sanitize_html":true,"line_breaks":false,"header_links":false,"show_copy_button":false,"name":"markdown","_selectable":false},"skip_api":false,"component_class_id":"0f35515b9a3362b42bb6721c836157a0","key":null,"api_info":{"type":"string"},"example_inputs":"# Hello!"},{"id":17,"type":"checkboxgroup","props":{"choices":[["Overall","Overall"],["Overall (official)","Overall (official)"],["Instance Attributes","Instance Attributes"],["Instance Identity","Instance Identity"],["Instance Interaction","Instance Interaction"],["Instance Location","Instance Location"],["Instances Counting","Instances Counting"],["Scene Understanding","Scene Understanding"],["Spatial Relation","Spatial Relation"],["Text Understanding","Text Understanding"],["Visual Reasoning","Visual Reasoning"]],"value":["Overall","Overall (official)"],"type":"value","label":"SEEDBench_IMG CheckBoxes","show_label":true,"container":true,"min_width":160,"interactive":true,"visible":true,"elem_classes":[],"name":"checkboxgroup","_selectable":false},"skip_api":false,"component_class_id":"0635a5d3bf87369f1c2c1c69f8a3d0cc","key":null,"api_info":{"items":{"enum":["Overall","Overall (official)","Instance Attributes","Instance Identity","Instance Interaction","Instance Location","Instances Counting","Scene Understanding","Spatial Relation","Text Understanding","Visual Reasoning"],"type":"string"},"title":"Checkbox Group","type":"array"},"example_inputs":["Overall"]},{"id":18,"type":"row","props":{"variant":"default","visible":true,"equal_height":true,"show_progress":false,"name":"row"},"skip_api":true,"component_class_id":"b5cf3d15e2293fb5ccc071d7b8d69f64","key":null},{"id":19,"type":"textbox","props":{"value":"Input the Model Name (fuzzy, case insensitive)","lines":1,"max_lines":20,"label":"Model Name","show_label":true,"container":true,"min_width":160,"interactive":true,"visible":true,"autofocus":false,"autoscroll":true,"elem_classes":[],"type":"text","rtl":false,"show_copy_button":false,"name":"textbox","_selectable":false},"skip_api":false,"component_class_id":"d0491bb0fbd427bdb2a4549c4d1ac869","key":null,"api_info":{"type":"string"},"example_inputs":"Hello!!"},{"id":20,"type":"checkboxgroup","props":{"choices":[["<4B","<4B"],["4B-10B","4B-10B"],["10B-20B","10B-20B"],["20B-40B","20B-40B"],[">40B",">40B"],["Unknown","Unknown"]],"value":["<4B","4B-10B","10B-20B","20B-40B",">40B","Unknown"],"type":"value","label":"Model Size","show_label":true,"container":true,"min_width":160,"interactive":true,"visible":true,"elem_classes":[],"name":"checkboxgroup","_selectable":false},"skip_api":false,"component_class_id":"0635a5d3bf87369f1c2c1c69f8a3d0cc","key":null,"api_info":{"items":{"enum":["<4B","4B-10B","10B-20B","20B-40B",">40B","Unknown"],"type":"string"},"title":"Checkbox Group","type":"array"},"example_inputs":["<4B"]},{"id":21,"type":"checkboxgroup","props":{"choices":[["API","API"],["OpenSource","OpenSource"]],"value":["API","OpenSource"],"type":"value","label":"Model Type","show_label":true,"container":true,"min_width":160,"interactive":true,"visible":true,"elem_classes":[],"name":"checkboxgroup","_selectable":false},"skip_api":false,"component_class_id":"0635a5d3bf87369f1c2c1c69f8a3d0cc","key":null,"api_info":{"items":{"enum":["API","OpenSource"],"type":"string"},"title":"Checkbox Group","type":"array"},"example_inputs":["API"]},{"id":22,"type":"form","props":{"scale":3,"min_width":480,"name":"form"},"skip_api":true,"component_class_id":"43cda85c6ff7a5dd8f83d29496b014ee","key":null},{"id":23,"type":"dataframe","props":{"value":{"headers":["Rank","Method","Param (B)","Language Model","Vision Model","Eval Date","Overall","Overall (official)"],"data":[[1,"Qwen2.5-VL-72B",73.4,"Qwen2.5-72B","QwenViT","2025/02/02",79.5,"N/A"],[2,"InternVL3-78B",78.4,"Qwen2.5-72B","InternViT-6B-v2.5","2025/04/14",78.7,"N/A"],[3,"InternVL3-38B",38.4,"Qwen2.5-32B","InternViT-6B-v2.5","2025/04/14",78.3,"N/A"],[4,"InternVL2.5-26B-MPO",26.0,"InternLM2.5-20B","InternViT-6B-v2.5","2024/12/28",78.3,"N/A"],[5,"InternVL2.5-38B-MPO",38.0,"Qwen-2.5-32B","InternViT-6B-v2.5","2024/12/28",78.0,"N/A"],[6,"GPT-4.1-20250414",null,"","","2025/04/16",78.0,"N/A"],[7,"Qwen-VL-Max-0809",72.0,"Qwen2-72B","QwenViT","2024/09/12",77.9,"N/A"],[8,"Qwen2-VL-72B",73.4,"Qwen2-72B","QwenViT","2024/10/28",77.9,"N/A"],[9,"Ovis2-16B",16.2,"Qwen2.5-14B","AIMv2 Huge","2025/02/18",77.7,"N/A"],[10,"Step-1o",null,"","","2025/01/13",77.7,"N/A"],[11,"GPT-4.1-mini-20250414",null,"","","2025/04/16",77.6,"N/A"],[12,"Ovis2-34B",34.9,"Qwen2.5-32B","AIMv2-1B","2025/02/18",77.6,"N/A"],[13,"InternVL2-Llama3-76B",76.0,"Llama-3-70B-Instruct","InternViT-6B","2024/07/19",77.6,"N/A"],[14,"RBDash-v1.5",79.0,"Qwen2-72B","CLIP ViT-L/14
InternViT-6B","2024/11/17",77.5,"N/A"],[15,"LLaVA-OneVision-72B",73.0,"Qwen2-72B","SigLIP-400M","2024/09/19",77.5,"N/A"],[16,"InternVL3-14B",15.1,"Qwen2.5-14B","InternViT-300M-v2.5","2025/04/14",77.5,"N/A"],[17,"InternVL2-40B",40.0,"Nous-Hermes-2-Yi-34B","InternViT-6B","2024/07/11",77.4,"N/A"],[18,"MUG-U-7B",7.0,"","","2025/03/19",77.3,"N/A"],[19,"Ovis2-8B",8.94,"Qwen2.5-7B","AIMv2 Huge","2025/02/18",77.2,"N/A"],[20,"GPT-4o (0513, detail-high)",null,"","","2024/05/31",77.1,"N/A"],[21,"InternVL3-8B",7.94,"Qwen2.5-7B","InternViT-300M-v2.5","2025/04/14",77.1,"N/A"],[22,"DeepSeek-VL2",27.5,"DeepSeekMoE-27B","SigLIP-400M","2025/01/01",77.0,"N/A"],[23,"Qwen2.5-VL-7B",8.29,"Qwen2.5-7B","QwenViT","2025/02/02",77.0,"N/A"],[24,"InternVL2.5-78B-MPO",78.0,"Qwen-2.5-72B","InternViT-6B-v2.5","2024/12/29",77.0,"N/A"],[25,"DeepSeek-VL2-Small",16.1,"DeepSeekMoE-16B","SigLIP-400M","2025/01/01",76.9,"N/A"],[26,"InternVL3-9B",9.14,"InternLM3-8B","InternViT-300M-v2.5","2025/04/14",76.8,"N/A"],[27,"Kimi-VL-A3B-Instruct",16.4,"Moonlight-16B-A3B","MoonViT","2025/04/14",76.8,"N/A"],[28,"abab7-preview",null,"","","2024/12/11",76.8,"N/A"],[29,"InternVL2.5-8B-MPO",8.0,"InternLM2.5-7B","InternViT-300M-v2.5","2024/12/28",76.8,"N/A"],[30,"CongRong",null,"","","2024/06/26",76.8,"N/A"],[31,"Ovis1.6-Gemma2-27B",28.9,"Gemma2-27B","SigLIP-400M","2024/11/29",76.8,"N/A"],[32,"Llama-3.2-90B-Vision-Instruct",88.6,"Llama-3.1-70B","","2024/10/19",76.8,"N/A"],[33,"GPT-4o (0806, detail-high)",null,"","","2024/08/08",76.7,"N/A"],[34,"GLM-4v-Plus-20250111",null,"","","2025/01/25",76.7,"N/A"],[35,"LLaVA-OneVision-7B",8.0,"Qwen2-7B","SigLIP-400M","2024/09/16",76.7,"N/A"],[36,"VARCO-VISION-14B",15.2,"Qwen2.5-14B","SigLIP-400M","2025/01/02",76.6,"N/A"],[37,"Ovis1.6-Gemma2-9B",10.2,"Gemma2-9B-It","SigLIP-400M","2024/09/19",76.5,"N/A"],[38,"GLM-4v-Plus",null,"","","2024/12/11",76.5,"N/A"],[39,"Qwen-VL-Plus-0809",null,"","","2024/09/17",76.4,"N/A"],[40,"GPT-4o (0513, detail-low)",null,"","","2024/05/15",76.4,"N/A"],[41,"VILA1.5-40B",40.0,"Yi-34B","InternViT-6B","2024/08/25",76.3,"N/A"],[42,"InternVL2-26B",26.0,"InternLM2-20B","InternViT-6B","2024/07/11",76.3,"N/A"],[43,"Taiyi",null,"","","2024/12/11",76.3,"N/A"],[44,"grok-2-vision-1212",null,"","","2025/03/03",76.3,"N/A"],[45,"Ovis2-4B",4.62,"Qwen2.5-3B","AIMv2 Huge","2025/02/18",76.2,"N/A"],[46,"OmChat-v2.0-13B",13.0,"Qwen2-7B","InternViT-6B","2024/08/22",76.2,"N/A"],[47,"Gemini-1.5-Pro",null,"","","2024/06/10",76.0,"N/A"],[48,"Qwen2-VL-7B",8.0,"Qwen2-7B","QwenViT","2024/09/12",76.0,"N/A"],[49,"MMAlaya2",26.0,"InternLM2-20B","InternViT-6B","2024/08/27",75.9,"N/A"],[50,"WeMM",7.0,"InternLM2-7B","SigLIP-400M","2024/06/09",75.9,"N/A"],[51,"LLaVA-Next-Yi-34B",34.8,"Yi-34B","CLIP ViT-L/14","2024/03/25",75.7,"N/A"],[52,"Step-1.5V",null,"Step-1.5","stepencoder","2024/10/11",75.7,"N/A"],[53,"NVLM-D-72B",79.4,"Qwen2-72B","InternViT-6B","2024/10/19",75.5,"N/A"],[54,"MiniCPM-o-2.6",8.67,"Qwen2.5-7B","SigLIP-400M","2025/01/21",75.5,"N/A"],[55,"Eagle-X5-34B-Chat",36.8,"Yi-34B","Clip-448
ConvNeXT-1024
SAM-1024
DET-1024
Pix2Struct-1024","2024/11/29",75.5,"N/A"],[56,"InternVL2-8B",8.0,"InternLM2.5-7B","InternViT-300M","2024/07/11",75.4,"N/A"],[57,"Ovis1.5-Llama3-8B",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/07/29",75.4,"N/A"],[58,"Cambrian-34B",34.0,"Nous-Hermes-2-Yi-34B","CLIP ViT-L/14","2024/07/18",75.4,"N/A"],[59,"LLaVA-OneVision-7B (SI)",8.0,"Qwen2-7B","SigLIP-400M","2024/09/17",75.4,"N/A"],[60,"InternLM-XComposer2.5",8.0,"InternLM2-7B","CLIP ViT-L/14","2024/07/11",75.4,"N/A"],[61,"moonshot-v1-8k",null,"","","2025/03/03",75.2,"N/A"],[62,"BlueLM-V-3B",3.0,"BlueLM-3B","SigLIP-400M","2024/10/30",75.2,"N/A"],[63,"InternVL-Chat-V1.5",26.0,"InternLM2-20B","InternViT-6B","2024/04/17",75.2,"N/A"],[64,"Llama-3-MixSense-v1.1",8.0,"Llama-3-8B-Instruct","Florence-2-Large-FT","2024/08/21",75.2,"N/A"],[65,"POINTS1.5-Qwen2.5-7B",8.3,"Qwen-2.5-7B","NaViT","2024/12/06",75.1,"N/A"],[66,"GLM-4v",null,"","","2024/05/20",75.1,"N/A"],[67,"Ovis1.5-Gemma2-9B",11.4,"Gemma2-9B-It","SigLIP-400M","2024/08/04",75.1,"N/A"],[68,"InternVL3-2B",2.09,"Qwen2.5-1.5B","InternViT-300M-v2.5","2025/04/14",75.0,"N/A"],[69,"LLaVA-Next-Qwen-32B",33.0,"Qwen-1.5-32B","SigLIP-400M","2024/08/08",75.0,"N/A"],[70,"Gemini-1.5-Flash",null,"","","2024/09/16",75.0,"N/A"],[71,"InternVL2-8B-MPO",8.0,"InternLM2.5-7B","InternViT-300M","2024/11/25",74.9,"N/A"],[72,"InternLM-XComposer2",7.0,"InternLM2-7B","CLIP ViT-L/14","2024/01/26",74.9,"N/A"],[73,"InternVL2.5-4B-MPO",4.0,"Qwen-2.5-3B","InternViT-300M-v2.5","2024/12/28",74.8,"N/A"],[74,"POINTS-Yi-1.5-9B",9.5,"Yi-1.5-9B","CLIP ViT-L/14","2024/10/11",74.8,"N/A"],[75,"POINTS-Qwen2.5-7B",8.3,"Qwen-2.5-7B","CLIP ViT-L/14","2024/10/19",74.8,"N/A"],[76,"Step-1.5V-mini",null,"","","2024/12/11",74.8,"N/A"],[77,"InternVL2-8B-MPO-CoT",8.0,"InternLM2.5-7B","InternViT-300M","2024/11/25",74.7,"N/A"],[78,"InternLM-XComposer2-4KHD",7.0,"InternLM2-7B","CLIP ViT-L/14","2024/06/09",74.6,"N/A"],[79,"Molmo-7B-D",8.0,"Qwen2-7B","CLIP ViT-L/14","2024/10/12",74.6,"N/A"],[80,"SAIL-VL-2B",2.1,"Qwen2.5-1.5B","InternViT-300M","2024/12/25",74.6,"N/A"],[81,"Ovis1.6-Llama3.2-3B",4.1,"Llama-3.2-3B","SigLIP-400M","2024/10/24",74.5,"N/A"],[82,"Ovis2-2B",2.46,"Qwen2.5-1.5B","AIMv2 Large","2025/02/18",74.4,"N/A"],[83,"BailingMM-Lite-1203",21.0,"Bailing-20B","SigLIP-400M","2024/12/08",74.4,"N/A"],[84,"Claude3.7-Sonnet",null,"","","2025/02/27",74.3,"N/A"],[85,"VITA-1.5",8.3,"Qwen2-7B","InternViT-300M","2025/01/01",74.1,"N/A"],[86,"CogVLM2-19B-Chat",19.0,"Llama-3-8B-Instruct","EVA2-CLIP-E","2024/05/31",74.1,"N/A"],[87,"Qwen2.5-VL-3B",3.75,"Qwen2.5-3B","QwenViT","2025/02/02",74.0,"N/A"],[88,"Eagle-X5-13B",15.0,"Vicuna-v1.5-13B","Clip-448
ConvNeXT-1024
SAM-1024
DET-1024
Pix2Struct-1024","2024/09/26",74.0,"N/A"],[89,"MiniCPM-V-2.6",8.0,"Qwen2-7B","SigLIP-400M","2024/08/08",74.0,"N/A"],[90,"Aquila-VL-2B",2.2,"Qwen-2.5-1.5B","SigLIP-400M","2024/10/24",73.9,"N/A"],[91,"granite-vision-3.2-2b",2.98,"granite-3.1-2b-instruct","SigLip","2025/06/20",73.9,"N/A"],[92,"Idefics3-8B-Llama3",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/08/27",73.8,"N/A"],[93,"Ross-Qwen2-7B",8.2,"Qwen2-7B","CLIP ViT-L/14","2025/01/17",73.7,"N/A"],[94,"Eagle-X5-7B",9.0,"Vicuna-v1.5-7B","Clip-448
ConvNeXT-1024
SAM-1024
DET-1024
Pix2Struct-1024","2024/09/26",73.6,"N/A"],[95,"Yi-Vision",null,"","","2024/08/03",73.6,"N/A"],[96,"XinYuan-VL-2B-Instruct",2.0,"Qwen2-1.5B","QwenViT","2024/09/27",73.5,"N/A"],[97,"Bunny-Llama3-8B",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/07/18",73.5,"N/A"],[98,"Cambrian-8B",8.0,"Vicuna-v1.5-7B","CLIP ViT-L/14","2024/07/11",73.3,"N/A"],[99,"InternVL2.5-2B-MPO",2.0,"InternLM2.5-1.8B","InternViT-300M-v2.5","2024/12/28",73.2,"N/A"],[100,"Phi-4-MultiModal",5.57,"Phi-4-Mini","SigLIP-400M","2025/03/13",73.2,"N/A"],[101,"InternVL2-4B",4.0,"Phi-3","InternViT-300M","2024/07/11",73.2,"N/A"],[102,"HunYuan-Standard-Vision",null,"","","2025/01/15",73.2,"N/A"],[103,"Cambrian-13B",13.0,"Vicuna-v1.5-13B","CLIP ViT-L/14","2024/07/29",73.2,"N/A"],[104,"360VL-70B",70.0,"Llama-3-70B-Instruct","CLIP ViT-L/14","2024/05/25",73.1,"N/A"],[105,"Gemma3-27B",27.4,"Gemma3-27B","SigLIP-400M","2025/03/19",73.1,"N/A"],[106,"BailingMM-Pro-0120",81.0,"Bailing-80B","SigLIP-400M","2025/01/25",73.0,"N/A"],[107,"GPT-4v (0409, detail-high)",null,"","","2024/05/15",73.0,"N/A"],[108,"GPT-4o-mini (0718, detail-high)",null,"","","2024/07/20",72.8,"N/A"],[109,"Aria",25.3,"Aria-MoE","SigLIP-400M","2024/12/05",72.7,"N/A"],[110,"VILA1.5-13B",13.0,"Vicuna-v1.5-13B","SigLIP-400M","2024/08/25",72.7,"N/A"],[111,"Qwen-VL-Max",null,"QwenLM","","2024/02/02",72.7,"N/A"],[112,"Molmo-7B-O",8.0,"Qwen2-7B","CLIP ViT-L/14","2024/10/20",72.7,"N/A"],[113,"Llama-3.2-11B-Vision-Instruct",11.0,"Llama-3.1-8B","","2024/10/07",72.7,"N/A"],[114,"LLaVA-Next-Llama3",8.0,"Llama-3-8B-Instruct","CLIP ViT-L/14","2024/07/29",72.5,"N/A"],[115,"XVERSE-V-13B",13.0,"XVERSE-13B","CLIP ViT-L/14","2024/05/10",72.4,"N/A"],[116,"LLaVA-Next-Mistral-7B",7.6,"Mistral-7B","CLIP ViT-L/14","2024/03/25",72.4,"N/A"],[117,"Qwen2-VL-2B",2.0,"Qwen2-1.5B","QwenViT","2024/09/12",72.4,"N/A"],[118,"MiniCPM-Llama3-V2.5",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/05/27",72.3,"N/A"],[119,"GPT-4v (1106, detail-high)",null,"","","2024/04/22",72.3,"N/A"],[120,"DeepSeek-VL2-Tiny",3.4,"DeepSeekMoE-3B","SigLIP-400M","2025/01/01",72.3,"N/A"],[121,"XGen-MM-Instruct-Interleave-v1.5",4.4,"Phi-3","SigLIP-400M","2024/09/06",72.2,"N/A"],[122,"Mini-InternVL-Chat-4B-V1.5",4.0,"Phi-3","InternViT-300M","2024/06/10",72.2,"N/A"],[123,"Claude3.5-Sonnet",null,"","","2024/06/24",72.2,"N/A"],[124,"granite-vision-3.3-2b",2.98,"granite-3.1-2b-instruct","SigLIP2-400M","2025/06/20",72.1,"N/A"],[125,"LLaVA-Next-Interleave-7B",8.0,"Qwen-1.5-7B","SigLIP-400M","2024/08/08",72.0,"N/A"],[126,"GPT-4v (0409, detail-low)",null,"","","2024/05/15",72.0,"N/A"],[127,"TransCore-M",13.4,"PCITransGPT-13B","CLIP ViT-L/14","2024/04/16",72.0,"N/A"],[128,"IDEFICS2-8B",8.0,"Mistral-7B","SigLIP-400M","2024/04/26",71.9,"N/A"],[129,"GPT-4.1-nano-20250414",null,"","","2025/04/16",71.8,"N/A"],[130,"H2OVL-2B",2.2,"H2O-DANUBE2-1.8B","InternViT-300M","2024/10/31",71.8,"N/A"],[131,"XGen-MM-Instruct-DPO-v1.5",4.4,"Phi-3","SigLIP-400M","2024/09/06",71.8,"N/A"],[132,"Ovis2-1B",1.27,"Qwen2.5-0.5B","AIMv2 Large","2025/02/18",71.7,"N/A"],[133,"GPT-4v (1106, detail-low)",null,"","","2023/12/23",71.6,"N/A"],[134,"Pixtral-12B",13.0,"Nemo-12B","ViT-400M","2024/09/16",71.5,"N/A"],[135,"OmniLMM-12B",12.0,"Zephyr-7B-β","EVA-02-5B","2024/02/07",71.5,"N/A"],[136,"LLaVA-Next-Vicuna-13B",13.4,"Vicuna-v1.5-13B","CLIP ViT-L/14","2024/03/25",71.4,"N/A"],[137,"SmolVLM2",2.25,"SmolLM2-1.7M","SigLIP-400M","2025/03/13",71.3,"N/A"],[138,"LLaVA-Next-Interleave-7B-DPO",8.0,"Qwen-1.5-7B","SigLIP-400M","2024/07/29",71.3,"N/A"],[139,"LLaVA-InternLM2-7B (QLoRA)",8.1,"InternLM2-7B","CLIP ViT-L/14","2024/01/17",71.2,"N/A"],[140,"Mantis-8B-Idefics2",8.0,"Mistral-7B","SigLIP-400M","2024/08/08",71.2,"N/A"],[141,"InternVL3-1B",0.94,"Qwen2.5-0.5B","InternViT-300M-v2.5","2025/04/14",71.2,"N/A"],[142,"Falcon2-VLM-11B",11.4,"Falcon2-11B","CLIP ViT-L/14","2024/10/30",71.2,"N/A"],[143,"GLM-4v-9B",9.0,"GLM-4-9B","EVA-02-5B","2024/06/14",71.1,"N/A"],[144,"Gemma3-12B",12.2,"Gemma3-12B","SigLIP-400M","2025/03/19",71.0,"N/A"],[145,"MiniMonkey",2.2,"InternLM2-1.8B","InternViT-300M","2024/09/26",71.0,"N/A"],[146,"InternVL2-2B",2.0,"InternLM2-1.8B","InternViT-300M","2024/07/11",70.9,"N/A"],[147,"Phi-3-Vision",4.2,"Phi-3","CLIP ViT-L/14","2024/05/31",70.9,"N/A"],[148,"InternLM-XComposer2-1.8B",2.0,"InternLM2-1.8B","CLIP ViT-L/14","2024/06/09",70.8,"N/A"],[149,"Gemini-1.0-Pro",null,"","","2023/12/23",70.7,"N/A"],[150,"ShareGPT4V-13B",13.4,"Vicuna-v1.5-13B","CLIP ViT-L/14","2023/12/08",70.6,"70.8 (Gen)"],[151,"InternVL2.5-1B-MPO",1.0,"Qwen-2.5-0.5B","InternViT-300M-v2.5","2024/12/28",70.4,"N/A"],[152,"LLaVA-InternLM2-20B (QLoRA)",20.2,"InternLM2-20B","CLIP ViT-L/14","2024/01/17",70.2,"N/A"],[153,"Janus-Pro-7B",7.42,"DeepSeek-7B","SigLIP-400M","2025/02/02",70.1,"N/A"],[154,"DeepSeek-VL-7B",7.3,"DeekSeek-7B","SAM-B
SigLIP-L","2024/03/21",70.1,"N/A"],[155,"Parrot-7B",8.0,"Qwen2-7B","CLIP ViT-L/14","2024/08/22",70.1,"N/A"],[156,"LLaVA-LLaMA-3-8B",8.0,"Llama-3-8B-Instruct","CLIP ViT-L/14","2024/05/07",70.1,"N/A"],[157,"Vintern-3B-beta",3.7,"Qwen-2.5-3B","InternViT-300M","2024/10/24",70.0,"N/A"],[158,"Slime-8B",8.0,"Llama-3-8B-Instruct","CLIP ViT-L/14","2024/09/14",69.8,"N/A"],[159,"Phi-3.5-Vision",4.0,"Phi-3.5","CLIP ViT-L/14","2024/08/28",69.7,"N/A"],[160,"LLaVA-Next-Vicuna-7B",7.1,"Vicuna-v1.5-7B","CLIP ViT-L/14","2024/03/25",69.6,"N/A"],[161,"PaliGemma-3B-mix-448",3.0,"Gemma-2B","SigLIP-400M","2024/05/17",69.6,"N/A"],[162,"Mini-InternVL-Chat-2B-V1.5",2.0,"InternLM2-1.8B","InternViT-300M","2024/06/10",69.5,"N/A"],[163,"ShareGPT4V-7B",7.2,"Vicuna-v1.5-7B","CLIP ViT-L/14","2023/12/08",69.3,"69.7 (Gen)"],[164,"Emu3_chat",8.49,"","","2025/01/26",69.2,"N/A"],[165,"Emu2_chat",37.0,"Llama-33B","EVA-02-CLIP-E-plus","2024/01/17",68.9,"N/A"],[166,"Monkey-Chat",9.8,"Qwen-7B","ViT-BigHuge","2024/01/16",68.9,"N/A"],[167,"CogVLM-17B-Chat",17.0,"Vicuna-v1.5-7B","EVA2-CLIP-E","2024/01/03",68.8,"N/A"],[168,"Slime-13B",13.0,"Vicuna-v1.5-13B","CLIP ViT-L/14","2024/09/14",68.7,"N/A"],[169,"Mantis-8B-siglip-llama3",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/08/08",68.5,"N/A"],[170,"SmolVLM-Instruct",2.3,"SmolLM2-1.7B","SigLIP-400M","2025/01/27",68.5,"N/A"],[171,"RekaEdge",null,"","","2024/05/31",68.4,"N/A"],[172,"LLaVA-v1.5-13B",13.4,"Vicuna-v1.5-13B","CLIP ViT-L/14","2023/10/05",68.2,"68.2 (Gen)"],[173,"Yi-VL-34B",34.6,"Yi-34B","CLIP ViT-H/14","2024/01/25",68.1,"N/A"],[174,"VILA1.5-3B",3.0,"Sheared-LLaMA-2.7B","SigLIP-400M","2024/08/25",68.0,"N/A"],[175,"MolmoE-1B",7.2,"OLMoE-1B-7B-0924","CLIP ViT-L/14","2024/10/21",67.9,"N/A"],[176,"LLaVA-v1.5-13B (QLoRA)",13.4,"Vicuna-v1.5-13B","CLIP ViT-L/14","2023/12/28",67.9,"N/A"],[177,"Yi-VL-6B",6.6,"Yi-6B","CLIP ViT-H/14","2024/01/25",67.5,"N/A"],[178,"MiniCPM-V-2",2.8,"MiniCPM-2.4B","SigLIP-400M","2024/04/15",67.1,"N/A"],[179,"Slime-7B",7.0,"Vicuna-v1.5-7B","CLIP ViT-L/14","2024/09/14",67.0,"N/A"],[180,"AKI-4B",4.33,"Phi-3.5","SigLIP-400M","2025/03/25",66.8,"N/A"],[181,"LLaVA-OneVision-0.5B",1.0,"Qwen2-0.5B","SigLIP-400M","2024/09/16",66.6,"N/A"],[182,"LLaVA-v1.5-7B (QLoRA)",7.2,"Vicuna-v1.5-7B","CLIP ViT-L/14","2023/12/28",66.4,"N/A"],[183,"SmolVLM-Instruct-DPO",2.3,"SmolLM2-1.7B","SigLIP-400M","2025/01/27",66.3,"N/A"],[184,"InternLM-XComposer",8.0,"InternLM-7B","EVA-G","2023/09/26",66.1,"N/A"],[185,"DeepSeek-VL-1.3B",2.0,"DeekSeek-1B","SAM-B
SigLIP-L","2024/03/21",66.0,"N/A"],[186,"Mantis-8B-clip-llama3",8.0,"Llama-3-8B-Instruct","CLIP ViT-L/14","2024/08/08",65.8,"N/A"],[187,"LLaVA-v1.5-7B",7.2,"Vicuna-v1.5-7B","CLIP ViT-L/14","2023/10/05",65.8,"N/A"],[188,"LLaVA-InternLM-7B (QLoRA)",7.6,"InternLM-7B","CLIP ViT-L/14","2023/12/28",65.7,"N/A"],[189,"Qwen-VL-Plus",null,"QwenLM","","2024/01/10",65.7,"N/A"],[190,"MiniCPM-V",3.0,"MiniCPM-2.4B","SigLIP-400M","2024/02/07",65.6,"N/A"],[191,"Gemma3-4B",4.3,"Gemma3-4B","SigLIP-400M","2025/03/19",65.5,"N/A"],[192,"InternVL2-1B",1.0,"Qwen2-0.5B","InternViT-300M","2024/07/11",65.2,"N/A"],[193,"Llama-3-VILA1.5-8B",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/08/25",65.0,"N/A"],[194,"Claude3-Sonnet",null,"","","2024/03/28",65.0,"N/A"],[195,"Qwen-VL-Chat",9.6,"Qwen-7B","ViT-G/16","2023/08/24",64.8,"65.4 (PPL)"],[196,"mPLUG-Owl2",8.2,"Llama-2-7B","CLIP ViT-L/14","2023/11/10",64.5,"64.1 (Not Given)"],[197,"Monkey",9.8,"Qwen-7B","ViT-BigHuge","2024/01/11",64.3,"N/A"],[198,"Claude3-Opus",null,"","","2024/03/28",64.0,"N/A"],[199,"Moondream1",1.9,"SigLIP-400M","Phi-1.5","2024/09/26",63.6,"N/A"],[200,"Claude3-Haiku",null,"","","2024/03/28",63.3,"N/A"],[201,"Janus-1.3B",2.1,"DeepSeek-1B","SigLIP-400M","2024/10/24",62.9,"N/A"],[202,"abab6.5s",null,"","","2024/12/11",62.3,"N/A"],[203,"SmolVLM2-500M",0.51,"SmolLM2-360M","ViT-93M","2025/03/13",62.2,"N/A"],[204,"SmolVLM-500M",0.51,"SmolLM2-360M","ViT-93M","2025/01/27",62.2,"N/A"],[205,"LLaVA-OneVision-0.5B (SI)",1.0,"Qwen2-0.5B","SigLIP-400M","2024/09/17",62.1,"N/A"],[206,"Claude3.5-Sonnet-20241022",null,"","","2024/11/06",61.7,"N/A"],[207,"ShareCaptioner",8.0,"InternLM-7B","EVA-G","2024/01/03",61.2,"N/A"],[208,"H2OVL-800M",0.83,"H2O-DANUBE3-500M","InternViT-300M","2024/10/31",60.2,"N/A"],[209,"Mantis-8B-Fuyu",8.0,"Fuyu-8B","","2024/09/07",59.3,"N/A"],[210,"SmolVLM-Synthetic",2.3,"SmolLM2-1.7B","SigLIP-400M","2025/01/27",59.2,"N/A"],[211,"MMAlaya",7.8,"Alaya-7B-Chat","EVA-G","2024/01/29",57.5,"N/A"],[212,"SmolVLM-256M",0.26,"SmolLM2-135M","ViT-93M","2025/01/27",54.0,"N/A"],[213,"Qwen-VL",9.6,"Qwen-7B","ViT-G/16","2023/08/24",52.5,"62.3 (PPL)"],[214,"IDEFICS-80B-Instruct",80.0,"Llama-65B","CLIP ViT-H/14","2023/07/25",52.0,"53.2 (Not Given)"],[215,"LLaVA-v1-7B",7.2,"Llama-7B","CLIP ViT-L/14","2023/04/17",50.4,"N/A"],[216,"Chameleon-30B",30.0,"","","2024/07/29",48.5,"N/A"],[217,"PandaGPT-13B",14.0,"Vicuna-13B","ImageBind ViT-H/14","2023/05/25",47.6,"N/A"],[218,"VisualGLM",8.0,"ChatGLM 6B","EVA-CLIP","2023/05/17",47.0,"N/A"],[219,"IDEFICS-9B-Instruct",9.0,"Llama-7B","CLIP ViT-H/14","2023/07/25",45.0,"44.5 (Not Given)"],[220,"InstructBLIP-7B",8.0,"Vicuna-7B","EVA-G","2023/05/11",44.5,"58.8 (PPL)"],[221,"SmolVLM2-256M",0.26,"SmolLM2-135M","ViT-93M","2025/03/13",42.7,"N/A"],[222,"MiniGPT-4-v1-7B",8.0,"Vicuna-7B","EVA-G","2023/04/20",31.6,"47.4 (PPL)"],[223,"Chameleon-7B",7.0,"","","2024/07/29",30.5,"N/A"],[224,"MiniGPT-4-v2",8.0,"Llama-2-13B","EVA-G","2023/10/27",29.4,"N/A"],[225,"OpenFlamingo v2",9.0,"MPT 7B","CLIP ViT-L/14","2023/06/28",28.8,"42.7 (PPL)"],[226,"Kosmos2",1.7,"","","2024/10/19",25.1,"N/A"]],"metadata":null},"headers":["1","2","3"],"row_count":[1,"dynamic"],"col_count":[3,"dynamic"],"datatype":["number","html","number","html","html","str","number","number"],"type":"pandas","latex_delimiters":[{"left":"$$","right":"$$","display":true}],"show_label":true,"height":500,"min_width":160,"interactive":false,"visible":true,"elem_classes":[],"wrap":true,"line_breaks":true,"column_widths":[],"name":"dataframe","_selectable":false},"skip_api":false,"component_class_id":"6a51bb3357f2e94c40fb8d4fbe06aa8e","key":null,"api_info":{"properties":{"headers":{"items":{"type":"string"},"title":"Headers","type":"array"},"data":{"items":{"items":{},"type":"array"},"title":"Data","type":"array"},"metadata":{"anyOf":[{"additionalProperties":{"anyOf":[{"items":{},"type":"array"},{"type":"null"}]},"type":"object"},{"type":"null"}],"default":null,"title":"Metadata"}},"required":["headers","data"],"title":"DataframeData","type":"object"},"example_inputs":{"headers":["a","b"],"data":[["foo","bar"]]}},{"id":24,"type":"textbox","props":{"value":"SEEDBench_IMG","lines":1,"max_lines":20,"label":"SEEDBench_IMG","show_label":true,"container":true,"min_width":160,"visible":false,"autofocus":false,"autoscroll":true,"elem_classes":[],"type":"text","rtl":false,"show_copy_button":false,"name":"textbox","_selectable":false},"skip_api":false,"component_class_id":"d0491bb0fbd427bdb2a4549c4d1ac869","key":null,"api_info":{"type":"string"},"example_inputs":"Hello!!"},{"id":25,"type":"form","props":{"scale":0,"min_width":0,"name":"form"},"skip_api":true,"component_class_id":"43cda85c6ff7a5dd8f83d29496b014ee","key":null},{"id":26,"type":"form","props":{"scale":0,"min_width":0,"name":"form"},"skip_api":true,"component_class_id":"43cda85c6ff7a5dd8f83d29496b014ee","key":null},{"id":27,"type":"tabitem","props":{"label":"📊 CCBench Leaderboard","visible":true,"interactive":true,"id":3,"elem_id":"CCBench","name":"tab"},"skip_api":true,"component_class_id":"18f46968e2b273dc5dbda0fe78433d7e","key":null},{"id":28,"type":"markdown","props":{"value":"## CCBench Evaluation Results \n\n- We adopt Circular Eval for benchmarks in MMBench series, you can check https://arxiv.org/pdf/2307.06281.pdf for the detailed definition of Circular Eval. ","show_label":true,"rtl":false,"latex_delimiters":[{"left":"$$","right":"$$","display":true}],"visible":true,"elem_classes":[],"sanitize_html":true,"line_breaks":false,"header_links":false,"show_copy_button":false,"name":"markdown","_selectable":false},"skip_api":false,"component_class_id":"0f35515b9a3362b42bb6721c836157a0","key":null,"api_info":{"type":"string"},"example_inputs":"# Hello!"},{"id":29,"type":"checkboxgroup","props":{"choices":[["Overall","Overall"],["Sketch Reasoning","Sketch Reasoning"],["Historical Figure","Historical Figure"],["Calligraphy Painting","Calligraphy Painting"],["Scenery Building","Scenery Building"],["Food Clothes","Food Clothes"],["Cultural Relic","Cultural Relic"],["Traditional Show","Traditional Show"]],"value":["Overall"],"type":"value","label":"CCBench CheckBoxes","show_label":true,"container":true,"min_width":160,"interactive":true,"visible":true,"elem_classes":[],"name":"checkboxgroup","_selectable":false},"skip_api":false,"component_class_id":"0635a5d3bf87369f1c2c1c69f8a3d0cc","key":null,"api_info":{"items":{"enum":["Overall","Sketch Reasoning","Historical Figure","Calligraphy Painting","Scenery Building","Food Clothes","Cultural Relic","Traditional Show"],"type":"string"},"title":"Checkbox Group","type":"array"},"example_inputs":["Overall"]},{"id":30,"type":"row","props":{"variant":"default","visible":true,"equal_height":true,"show_progress":false,"name":"row"},"skip_api":true,"component_class_id":"b5cf3d15e2293fb5ccc071d7b8d69f64","key":null},{"id":31,"type":"textbox","props":{"value":"Input the Model Name (fuzzy, case insensitive)","lines":1,"max_lines":20,"label":"Model Name","show_label":true,"container":true,"min_width":160,"interactive":true,"visible":true,"autofocus":false,"autoscroll":true,"elem_classes":[],"type":"text","rtl":false,"show_copy_button":false,"name":"textbox","_selectable":false},"skip_api":false,"component_class_id":"d0491bb0fbd427bdb2a4549c4d1ac869","key":null,"api_info":{"type":"string"},"example_inputs":"Hello!!"},{"id":32,"type":"checkboxgroup","props":{"choices":[["<4B","<4B"],["4B-10B","4B-10B"],["10B-20B","10B-20B"],["20B-40B","20B-40B"],[">40B",">40B"],["Unknown","Unknown"]],"value":["<4B","4B-10B","10B-20B","20B-40B",">40B","Unknown"],"type":"value","label":"Model Size","show_label":true,"container":true,"min_width":160,"interactive":true,"visible":true,"elem_classes":[],"name":"checkboxgroup","_selectable":false},"skip_api":false,"component_class_id":"0635a5d3bf87369f1c2c1c69f8a3d0cc","key":null,"api_info":{"items":{"enum":["<4B","4B-10B","10B-20B","20B-40B",">40B","Unknown"],"type":"string"},"title":"Checkbox Group","type":"array"},"example_inputs":["<4B"]},{"id":33,"type":"checkboxgroup","props":{"choices":[["API","API"],["OpenSource","OpenSource"]],"value":["API","OpenSource"],"type":"value","label":"Model Type","show_label":true,"container":true,"min_width":160,"interactive":true,"visible":true,"elem_classes":[],"name":"checkboxgroup","_selectable":false},"skip_api":false,"component_class_id":"0635a5d3bf87369f1c2c1c69f8a3d0cc","key":null,"api_info":{"items":{"enum":["API","OpenSource"],"type":"string"},"title":"Checkbox Group","type":"array"},"example_inputs":["API"]},{"id":34,"type":"form","props":{"scale":3,"min_width":480,"name":"form"},"skip_api":true,"component_class_id":"43cda85c6ff7a5dd8f83d29496b014ee","key":null},{"id":35,"type":"dataframe","props":{"value":{"headers":["Rank","Method","Param (B)","Language Model","Vision Model","Eval Date","Overall"],"data":[[1,"InternVL2.5-78B-MPO",78.0,"Qwen-2.5-72B","InternViT-6B-v2.5","2024/12/29",86.9],[2,"InternVL2.5-2B-MPO",2.0,"InternLM2.5-1.8B","InternViT-300M-v2.5","2024/12/28",86.1],[3,"InternVL3-78B",78.4,"Qwen2.5-72B","InternViT-6B-v2.5","2025/04/14",83.5],[4,"InternVL2.5-8B-MPO",8.0,"InternLM2.5-7B","InternViT-300M-v2.5","2024/12/28",82.9],[5,"InternVL2.5-4B-MPO",4.0,"Qwen-2.5-3B","InternViT-300M-v2.5","2024/12/28",82.2],[6,"Step-1o",null,"","","2025/01/13",81.4],[7,"InternVL2-Llama3-76B",76.0,"Llama-3-70B-Instruct","InternViT-6B","2024/07/19",81.2],[8,"InternVL3-38B",38.4,"Qwen2.5-32B","InternViT-6B-v2.5","2025/04/14",80.6],[9,"InternVL2-40B",40.0,"Nous-Hermes-2-Yi-34B","InternViT-6B","2024/07/11",80.2],[10,"InternVL2.5-26B-MPO",26.0,"InternLM2.5-20B","InternViT-6B-v2.5","2024/12/28",79.8],[11,"InternVL3-1B",0.94,"Qwen2.5-0.5B","InternViT-300M-v2.5","2025/04/14",78.4],[12,"InternVL2.5-1B-MPO",1.0,"Qwen-2.5-0.5B","InternViT-300M-v2.5","2024/12/28",78.2],[13,"InternVL3-9B",9.14,"InternLM3-8B","InternViT-300M-v2.5","2025/04/14",78.0],[14,"InternVL3-8B",7.94,"Qwen2.5-7B","InternViT-300M-v2.5","2025/04/14",77.8],[15,"MiniMonkey",2.2,"InternLM2-1.8B","InternViT-300M","2024/09/26",77.3],[16,"InternVL3-14B",15.1,"Qwen2.5-14B","InternViT-300M-v2.5","2025/04/14",77.1],[17,"InternVL2-8B",8.0,"InternLM2.5-7B","InternViT-300M","2024/07/11",77.1],[18,"InternVL2-1B",1.0,"Qwen2-0.5B","InternViT-300M","2024/07/11",76.3],[19,"InternVL2.5-38B-MPO",38.0,"Qwen-2.5-32B","InternViT-6B-v2.5","2024/12/28",75.9],[20,"InternVL3-2B",2.09,"Qwen2.5-1.5B","InternViT-300M-v2.5","2025/04/14",75.3],[21,"InternVL2-8B-MPO",8.0,"InternLM2.5-7B","InternViT-300M","2024/11/25",74.7],[22,"InternVL2-2B",2.0,"InternLM2-1.8B","InternViT-300M","2024/07/11",74.7],[23,"BlueLM-V-3B",3.0,"BlueLM-3B","SigLIP-400M","2024/10/30",74.3],[24,"Step-1.5V",null,"Step-1.5","stepencoder","2024/10/11",74.3],[25,"InternVL2-8B-MPO-CoT",8.0,"InternLM2.5-7B","InternViT-300M","2024/11/25",74.3],[26,"Qwen2.5-VL-72B",73.4,"Qwen2.5-72B","QwenViT","2025/02/02",73.9],[27,"InternVL2-26B",26.0,"InternLM2-20B","InternViT-6B","2024/07/11",73.9],[28,"GPT-4.1-20250414",null,"","","2025/04/16",73.5],[29,"Step-1.5V-mini",null,"","","2024/12/11",72.7],[30,"HunYuan-Standard-Vision",null,"","","2025/01/15",72.0],[31,"Kimi-VL-A3B-Instruct",16.4,"Moonlight-16B-A3B","MoonViT","2025/04/14",72.0],[32,"GPT-4o (0513, detail-high)",null,"","","2024/05/31",71.2],[33,"GLM-4v-Plus-20250111",null,"","","2025/01/25",71.0],[34,"Qwen-VL-Max-0809",72.0,"Qwen2-72B","QwenViT","2024/09/12",70.6],[35,"GPT-4o (0513, detail-low)",null,"","","2024/05/15",70.6],[36,"MMAlaya2",26.0,"InternLM2-20B","InternViT-6B","2024/08/27",70.0],[37,"Qwen2-VL-72B",73.4,"Qwen2-72B","QwenViT","2024/10/28",69.8],[38,"InternVL-Chat-V1.5",26.0,"InternLM2-20B","InternViT-6B","2024/04/17",69.8],[39,"TransCore-M",13.4,"PCITransGPT-13B","CLIP ViT-L/14","2024/04/16",69.8],[40,"CongRong",null,"","","2024/06/26",69.6],[41,"GPT-4o (0806, detail-high)",null,"","","2024/08/08",66.5],[42,"InternVL2-4B",4.0,"Phi-3","InternViT-300M","2024/07/11",66.3],[43,"Qwen2-VL-7B",8.0,"Qwen2-7B","QwenViT","2024/09/12",65.7],[44,"GPT-4.1-mini-20250414",null,"","","2025/04/16",64.3],[45,"Ovis2-34B",34.9,"Qwen2.5-32B","AIMv2-1B","2025/02/18",64.1],[46,"Qwen-VL-Plus-0809",null,"","","2024/09/17",64.1],[47,"LLaVA-OneVision-72B",73.0,"Qwen2-72B","SigLIP-400M","2024/09/19",63.9],[48,"GLM-4v",null,"","","2024/05/20",63.9],[49,"Qwen-VL-Max",null,"QwenLM","","2024/02/02",63.5],[50,"Mini-InternVL-Chat-2B-V1.5",2.0,"InternLM2-1.8B","InternViT-300M","2024/06/10",62.9],[51,"GLM-4v-Plus",null,"","","2024/12/11",62.5],[52,"Ovis2-16B",16.2,"Qwen2.5-14B","AIMv2 Huge","2025/02/18",62.4],[53,"Qwen2.5-VL-3B",3.75,"Qwen2.5-3B","QwenViT","2025/02/02",62.0],[54,"GPT-4o-mini (0718, detail-high)",null,"","","2024/07/20",61.4],[55,"Ola-7b",8.88,"Qwen2.5-7B","Oryx-ViT","2025/02/05",60.2],[56,"moonshot-v1-8k",null,"","","2025/03/03",60.2],[57,"abab7-preview",null,"","","2024/12/11",59.8],[58,"Ovis2-8B",8.94,"Qwen2.5-7B","AIMv2 Huge","2025/02/18",59.6],[59,"Mini-InternVL-Chat-4B-V1.5",4.0,"Phi-3","InternViT-300M","2024/06/10",59.4],[60,"Qwen2.5-VL-7B",8.29,"Qwen2.5-7B","QwenViT","2025/02/02",59.2],[61,"POINTS1.5-Qwen2.5-7B",8.3,"Qwen-2.5-7B","NaViT","2024/12/06",59.0],[62,"NVLM-D-72B",79.4,"Qwen2-72B","InternViT-6B","2024/10/19",59.0],[63,"Taiyi",null,"","","2024/12/11",58.0],[64,"GPT-4v (0409, detail-high)",null,"","","2024/05/15",57.3],[65,"grok-2-vision-1212",null,"","","2025/03/03",57.3],[66,"DeepSeek-VL2-Small",16.1,"DeepSeekMoE-16B","SigLIP-400M","2025/01/01",56.7],[67,"Claude3.5-Sonnet-20241022",null,"","","2024/11/06",56.1],[68,"RBDash-v1.5",79.0,"Qwen2-72B","CLIP ViT-L/14
InternViT-6B","2024/11/17",55.7],[69,"DeepSeek-VL2",27.5,"DeepSeekMoE-27B","SigLIP-400M","2025/01/01",55.7],[70,"MiniCPM-V-2.6",8.0,"Qwen2-7B","SigLIP-400M","2024/08/08",55.7],[71,"Phi-4-MultiModal",5.57,"Phi-4-Mini","SigLIP-400M","2025/03/13",55.5],[72,"GPT-4v (0409, detail-low)",null,"","","2024/05/15",55.5],[73,"Claude3.7-Sonnet",null,"","","2025/02/27",55.1],[74,"Qwen-VL-Plus",null,"QwenLM","","2024/01/10",55.1],[75,"LLaVA-OneVision-7B",8.0,"Qwen2-7B","SigLIP-400M","2024/09/16",54.9],[76,"XinYuan-VL-2B-Instruct",2.0,"Qwen2-1.5B","QwenViT","2024/09/27",54.7],[77,"OmChat-v2.0-13B",13.0,"Qwen2-7B","InternViT-6B","2024/08/22",54.5],[78,"Claude3.5-Sonnet",null,"","","2024/06/24",54.1],[79,"Llama-3.2-90B-Vision-Instruct",88.6,"Llama-3.1-70B","","2024/10/19",54.1],[80,"Qwen2-VL-2B",2.0,"Qwen2-1.5B","QwenViT","2024/09/12",53.7],[81,"Gemma3-27B",27.4,"Gemma3-27B","SigLIP-400M","2025/03/19",53.3],[82,"MiniCPM-o-2.6",8.67,"Qwen2.5-7B","SigLIP-400M","2025/01/21",53.3],[83,"VARCO-VISION-14B",15.2,"Qwen2.5-14B","SigLIP-400M","2025/01/02",53.1],[84,"Ovis1.6-Gemma2-27B",28.9,"Gemma2-27B","SigLIP-400M","2024/11/29",53.1],[85,"Ovis2-4B",4.62,"Qwen2.5-3B","AIMv2 Huge","2025/02/18",53.1],[86,"MUG-U-7B",7.0,"","","2025/03/19",52.7],[87,"Gemini-1.0-Pro",null,"","","2023/12/23",52.5],[88,"DeepSeek-VL-7B",7.3,"DeekSeek-7B","SAM-B
SigLIP-L","2024/03/21",52.4],[89,"Gemini-1.5-Flash",null,"","","2024/09/16",52.4],[90,"BailingMM-Pro-0120",81.0,"Bailing-80B","SigLIP-400M","2025/01/25",52.2],[91,"LLaVA-Next-Qwen-32B",33.0,"Qwen-1.5-32B","SigLIP-400M","2024/08/08",52.2],[92,"POINTS-Qwen2.5-7B",8.3,"Qwen-2.5-7B","CLIP ViT-L/14","2024/10/19",52.2],[93,"Ovis1.6-Gemma2-9B",10.2,"Gemma2-9B-It","SigLIP-400M","2024/09/19",51.8],[94,"VILA1.5-40B",40.0,"Yi-34B","InternViT-6B","2024/08/25",50.8],[95,"Yi-Vision",null,"","","2024/08/03",50.6],[96,"GPT-4v (1106, detail-high)",null,"","","2024/04/22",50.4],[97,"InternLM-XComposer2.5",8.0,"InternLM2-7B","CLIP ViT-L/14","2024/07/11",49.6],[98,"InternLM-XComposer",8.0,"InternLM-7B","EVA-G","2023/09/26",49.6],[99,"LLaVA-Next-Yi-34B",34.8,"Yi-34B","CLIP ViT-L/14","2024/03/25",49.2],[100,"Cambrian-34B",34.0,"Nous-Hermes-2-Yi-34B","CLIP ViT-L/14","2024/07/18",49.2],[101,"BailingMM-Lite-1203",21.0,"Bailing-20B","SigLIP-400M","2024/12/08",49.0],[102,"Gemma3-12B",12.2,"Gemma3-12B","SigLIP-400M","2025/03/19",49.0],[103,"POINTS-Yi-1.5-9B",9.5,"Yi-1.5-9B","CLIP ViT-L/14","2024/10/11",48.6],[104,"Aria",25.3,"Aria-MoE","SigLIP-400M","2024/12/05",48.4],[105,"Ross-Qwen2-7B",8.2,"Qwen2-7B","CLIP ViT-L/14","2025/01/17",48.4],[106,"InternLM-XComposer2",7.0,"InternLM2-7B","CLIP ViT-L/14","2024/01/26",48.2],[107,"VITA-1.5",8.3,"Qwen2-7B","InternViT-300M","2025/01/01",48.2],[108,"Monkey-Chat",9.8,"Qwen-7B","ViT-BigHuge","2024/01/16",48.0],[109,"WeMM",7.0,"InternLM2-7B","SigLIP-400M","2024/06/09",48.0],[110,"InternLM-XComposer2-4KHD",7.0,"InternLM2-7B","CLIP ViT-L/14","2024/06/09",47.1],[111,"XVERSE-V-13B",13.0,"XVERSE-13B","CLIP ViT-L/14","2024/05/10",46.9],[112,"GPT-4v (1106, detail-low)",null,"","","2023/12/23",46.5],[113,"LLaVA-InternLM2-20B (QLoRA)",20.2,"InternLM2-20B","CLIP ViT-L/14","2024/01/17",46.3],[114,"Yi-VL-34B",34.6,"Yi-34B","CLIP ViT-H/14","2024/01/25",46.1],[115,"MiniCPM-Llama3-V2.5",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/05/27",45.9],[116,"MiniCPM-V-2",2.8,"MiniCPM-2.4B","SigLIP-400M","2024/04/15",45.3],[117,"GLM-4v-9B",9.0,"GLM-4-9B","EVA-02-5B","2024/06/14",44.9],[118,"360VL-70B",70.0,"Llama-3-70B-Instruct","CLIP ViT-L/14","2024/05/25",44.9],[119,"Ovis2-2B",2.46,"Qwen2.5-1.5B","AIMv2 Large","2025/02/18",44.7],[120,"LLaVA-OneVision-7B (SI)",8.0,"Qwen2-7B","SigLIP-400M","2024/09/17",44.7],[121,"LLaVA-Next-Interleave-7B",8.0,"Qwen-1.5-7B","SigLIP-400M","2024/08/08",44.3],[122,"Bunny-Llama3-8B",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/07/18",44.1],[123,"Ovis1.5-Gemma2-9B",11.4,"Gemma2-9B-It","SigLIP-400M","2024/08/04",44.1],[124,"Aquila-VL-2B",2.2,"Qwen-2.5-1.5B","SigLIP-400M","2024/10/24",43.5],[125,"Yi-VL-6B",6.6,"Yi-6B","CLIP ViT-H/14","2024/01/25",42.9],[126,"Eagle-X5-34B-Chat",36.8,"Yi-34B","Clip-448
ConvNeXT-1024
SAM-1024
DET-1024
Pix2Struct-1024","2024/11/29",42.7],[127,"LLaVA-InternLM2-7B (QLoRA)",8.1,"InternLM2-7B","CLIP ViT-L/14","2024/01/17",42.5],[128,"LLaVA-Next-Interleave-7B-DPO",8.0,"Qwen-1.5-7B","SigLIP-400M","2024/07/29",42.4],[129,"SAIL-VL-2B",2.1,"Qwen2.5-1.5B","InternViT-300M","2024/12/25",42.2],[130,"Parrot-7B",8.0,"Qwen2-7B","CLIP ViT-L/14","2024/08/22",41.8],[131,"MiniCPM-V",3.0,"MiniCPM-2.4B","SigLIP-400M","2024/02/07",41.4],[132,"Qwen-VL-Chat",9.6,"Qwen-7B","ViT-G/16","2023/08/24",41.2],[133,"ShareCaptioner",8.0,"InternLM-7B","EVA-G","2024/01/03",40.4],[134,"InternLM-XComposer2-1.8B",2.0,"InternLM2-1.8B","CLIP ViT-L/14","2024/06/09",40.4],[135,"DeepSeek-VL2-Tiny",3.4,"DeepSeekMoE-3B","SigLIP-400M","2025/01/01",40.0],[136,"Vintern-3B-beta",3.7,"Qwen-2.5-3B","InternViT-300M","2024/10/24",39.2],[137,"Idefics3-8B-Llama3",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/08/27",38.8],[138,"CogVLM2-19B-Chat",19.0,"Llama-3-8B-Instruct","EVA2-CLIP-E","2024/05/31",38.8],[139,"Mantis-8B-Idefics2",8.0,"Mistral-7B","SigLIP-400M","2024/08/08",38.6],[140,"Pixtral-12B",13.0,"Nemo-12B","ViT-400M","2024/09/16",37.6],[141,"DeepSeek-VL-1.3B",2.0,"DeekSeek-1B","SAM-B
SigLIP-L","2024/03/21",37.6],[142,"IDEFICS2-8B",8.0,"Mistral-7B","SigLIP-400M","2024/04/26",37.6],[143,"Ovis2-1B",1.27,"Qwen2.5-0.5B","AIMv2 Large","2025/02/18",37.5],[144,"abab6.5s",null,"","","2024/12/11",37.5],[145,"LLaVA-InternLM-7B (QLoRA)",7.6,"InternLM-7B","CLIP ViT-L/14","2023/12/28",37.3],[146,"Mantis-8B-siglip-llama3",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/08/08",37.3],[147,"Monkey",9.8,"Qwen-7B","ViT-BigHuge","2024/01/11",37.1],[148,"Mantis-8B-clip-llama3",8.0,"Llama-3-8B-Instruct","CLIP ViT-L/14","2024/08/08",37.1],[149,"OmniLMM-12B",12.0,"Zephyr-7B-β","EVA-02-5B","2024/02/07",37.1],[150,"Gemma3-4B",4.3,"Gemma3-4B","SigLIP-400M","2025/03/19",36.9],[151,"Ovis1.5-Llama3-8B",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/07/29",36.7],[152,"Molmo-7B-D",8.0,"Qwen2-7B","CLIP ViT-L/14","2024/10/12",36.7],[153,"Ovis1.6-Llama3.2-3B",4.1,"Llama-3.2-3B","SigLIP-400M","2024/10/24",36.3],[154,"RekaFlash",null,"","","2024/05/07",33.7],[155,"XGen-MM-Instruct-Interleave-v1.5",4.4,"Phi-3","SigLIP-400M","2024/09/06",33.5],[156,"Janus-Pro-7B",7.42,"DeepSeek-7B","SigLIP-400M","2025/02/02",33.3],[157,"LLaVA-v1.5-13B (QLoRA)",13.4,"Vicuna-v1.5-13B","CLIP ViT-L/14","2023/12/28",32.9],[158,"XGen-MM-Instruct-DPO-v1.5",4.4,"Phi-3","SigLIP-400M","2024/09/06",32.7],[159,"LLaVA-Next-Llama3",8.0,"Llama-3-8B-Instruct","CLIP ViT-L/14","2024/07/29",32.7],[160,"GPT-4.1-nano-20250414",null,"","","2025/04/16",31.2],[161,"mPLUG-Owl2",8.2,"Llama-2-7B","CLIP ViT-L/14","2023/11/10",31.0],[162,"ShareGPT4V-7B",7.2,"Vicuna-v1.5-7B","CLIP ViT-L/14","2023/12/08",30.8],[163,"ShareGPT4V-13B",13.4,"Vicuna-v1.5-13B","CLIP ViT-L/14","2023/12/08",30.4],[164,"Llama-3.2-11B-Vision-Instruct",11.0,"Llama-3.1-8B","","2024/10/07",30.2],[165,"Falcon2-VLM-11B",11.4,"Falcon2-11B","CLIP ViT-L/14","2024/10/30",30.2],[166,"LLaVA-Next-Mistral-7B",7.6,"Mistral-7B","CLIP ViT-L/14","2024/03/25",30.0],[167,"Eagle-X5-13B",15.0,"Vicuna-v1.5-13B","Clip-448
ConvNeXT-1024
SAM-1024
DET-1024
Pix2Struct-1024","2024/09/26",30.0],[168,"Llama-3-MixSense-v1.1",8.0,"Llama-3-8B-Instruct","Florence-2-Large-FT","2024/08/21",30.0],[169,"PaliGemma-3B-mix-448",3.0,"Gemma-2B","SigLIP-400M","2024/05/17",29.6],[170,"LLaVA-Next-Vicuna-13B",13.4,"Vicuna-v1.5-13B","CLIP ViT-L/14","2024/03/25",28.8],[171,"MMAlaya",7.8,"Alaya-7B-Chat","EVA-G","2024/01/29",28.6],[172,"Eagle-X5-7B",9.0,"Vicuna-v1.5-7B","Clip-448
ConvNeXT-1024
SAM-1024
DET-1024
Pix2Struct-1024","2024/09/26",28.4],[173,"Gemini-1.5-Pro",null,"","","2024/06/10",28.4],[174,"LLaVA-v1.5-7B (QLoRA)",7.2,"Vicuna-v1.5-7B","CLIP ViT-L/14","2023/12/28",28.4],[175,"LLaVA-OneVision-0.5B",1.0,"Qwen2-0.5B","SigLIP-400M","2024/09/16",28.0],[176,"LLaVA-LLaMA-3-8B",8.0,"Llama-3-8B-Instruct","CLIP ViT-L/14","2024/05/07",27.8],[177,"granite-vision-3.2-2b",2.98,"granite-3.1-2b-instruct","SigLip","2025/06/20",27.8],[178,"Claude3-Sonnet",null,"","","2024/03/28",27.8],[179,"Slime-8B",8.0,"Llama-3-8B-Instruct","CLIP ViT-L/14","2024/09/14",27.6],[180,"Phi-3.5-Vision",4.0,"Phi-3.5","CLIP ViT-L/14","2024/08/28",27.6],[181,"Cambrian-13B",13.0,"Vicuna-v1.5-13B","CLIP ViT-L/14","2024/07/29",26.7],[182,"Claude3-Opus",null,"","","2024/03/28",26.3],[183,"LLaVA-OneVision-0.5B (SI)",1.0,"Qwen2-0.5B","SigLIP-400M","2024/09/17",25.7],[184,"AKI-4B",4.33,"Phi-3.5","SigLIP-400M","2025/03/25",25.7],[185,"Slime-7B",7.0,"Vicuna-v1.5-7B","CLIP ViT-L/14","2024/09/14",25.3],[186,"granite-vision-3.3-2b",2.98,"granite-3.1-2b-instruct","SigLIP2-400M","2025/06/20",24.9],[187,"RekaEdge",null,"","","2024/05/31",24.7],[188,"Claude3-Haiku",null,"","","2024/03/28",24.5],[189,"LLaVA-Next-Vicuna-7B",7.1,"Vicuna-v1.5-7B","CLIP ViT-L/14","2024/03/25",24.3],[190,"VILA1.5-13B",13.0,"Vicuna-v1.5-13B","SigLIP-400M","2024/08/25",24.3],[191,"VILA1.5-3B",3.0,"Sheared-LLaMA-2.7B","SigLIP-400M","2024/08/25",24.1],[192,"Phi-3-Vision",4.2,"Phi-3","CLIP ViT-L/14","2024/05/31",24.1],[193,"H2OVL-2B",2.2,"H2O-DANUBE2-1.8B","InternViT-300M","2024/10/31",23.7],[194,"Cambrian-8B",8.0,"Vicuna-v1.5-7B","CLIP ViT-L/14","2024/07/11",23.7],[195,"Llama-3-VILA1.5-8B",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/08/25",23.7],[196,"SmolVLM2",2.25,"SmolLM2-1.7M","SigLIP-400M","2025/03/13",23.1],[197,"Janus-1.3B",2.1,"DeepSeek-1B","SigLIP-400M","2024/10/24",22.2],[198,"H2OVL-800M",0.83,"H2O-DANUBE3-500M","InternViT-300M","2024/10/31",21.4],[199,"SmolVLM-Instruct",2.3,"SmolLM2-1.7B","SigLIP-400M","2025/01/27",20.8],[200,"LLaVA-v1.5-13B",13.4,"Vicuna-v1.5-13B","CLIP ViT-L/14","2023/10/05",20.8],[201,"Molmo-7B-O",8.0,"Qwen2-7B","CLIP ViT-L/14","2024/10/20",20.6],[202,"Slime-13B",13.0,"Vicuna-v1.5-13B","CLIP ViT-L/14","2024/09/14",20.0],[203,"SmolVLM-Instruct-DPO",2.3,"SmolLM2-1.7B","SigLIP-400M","2025/01/27",19.6],[204,"CogVLM-17B-Chat",17.0,"Vicuna-v1.5-7B","EVA2-CLIP-E","2024/01/03",19.0],[205,"Emu3_chat",8.49,"","","2025/01/26",19.0],[206,"Emu2_chat",37.0,"Llama-33B","EVA-02-CLIP-E-plus","2024/01/17",18.8],[207,"LLaVA-v1.5-7B",7.2,"Vicuna-v1.5-7B","CLIP ViT-L/14","2023/10/05",17.8],[208,"MolmoE-1B",7.2,"OLMoE-1B-7B-0924","CLIP ViT-L/14","2024/10/21",17.5],[209,"VisualGLM",8.0,"ChatGLM 6B","EVA-CLIP","2023/05/17",17.3],[210,"Moondream2",1.9,"SigLIP-400M","Phi-1.5","2024/10/20",15.5],[211,"SmolVLM2-500M",0.51,"SmolLM2-360M","ViT-93M","2025/03/13",13.3],[212,"LLaVA-v1-7B",7.2,"Llama-7B","CLIP ViT-L/14","2023/04/17",12.7],[213,"InstructBLIP-7B",8.0,"Vicuna-7B","EVA-G","2023/05/11",12.7],[214,"Mantis-8B-Fuyu",8.0,"Fuyu-8B","","2024/09/07",11.8],[215,"SmolVLM-Synthetic",2.3,"SmolLM2-1.7B","SigLIP-400M","2025/01/27",10.6],[216,"SmolVLM-500M",0.51,"SmolLM2-360M","ViT-93M","2025/01/27",10.6],[217,"IDEFICS-80B-Instruct",80.0,"Llama-65B","CLIP ViT-H/14","2023/07/25",10.6],[218,"Moondream1",1.9,"SigLIP-400M","Phi-1.5","2024/09/26",9.2],[219,"IDEFICS-9B-Instruct",9.0,"Llama-7B","CLIP ViT-H/14","2023/07/25",7.8],[220,"PandaGPT-13B",14.0,"Vicuna-13B","ImageBind ViT-H/14","2023/05/25",6.7],[221,"OpenFlamingo v2",9.0,"MPT 7B","CLIP ViT-L/14","2023/06/28",6.3],[222,"Qwen-VL",9.6,"Qwen-7B","ViT-G/16","2023/08/24",6.1],[223,"Chameleon-30B",30.0,"","","2024/07/29",5.9],[224,"SmolVLM-256M",0.26,"SmolLM2-135M","ViT-93M","2025/01/27",5.1],[225,"MiniGPT-4-v1-7B",8.0,"Vicuna-7B","EVA-G","2023/04/20",1.8],[226,"MiniGPT-4-v2",8.0,"Llama-2-13B","EVA-G","2023/10/27",1.4],[227,"Kosmos2",1.7,"","","2024/10/19",1.4],[228,"Chameleon-7B",7.0,"","","2024/07/29",1.4],[229,"SmolVLM2-256M",0.26,"SmolLM2-135M","ViT-93M","2025/03/13",0.0]],"metadata":null},"headers":["1","2","3"],"row_count":[1,"dynamic"],"col_count":[3,"dynamic"],"datatype":["number","html","number","html","html","str","number"],"type":"pandas","latex_delimiters":[{"left":"$$","right":"$$","display":true}],"show_label":true,"height":500,"min_width":160,"interactive":false,"visible":true,"elem_classes":[],"wrap":true,"line_breaks":true,"column_widths":[],"name":"dataframe","_selectable":false},"skip_api":false,"component_class_id":"6a51bb3357f2e94c40fb8d4fbe06aa8e","key":null,"api_info":{"properties":{"headers":{"items":{"type":"string"},"title":"Headers","type":"array"},"data":{"items":{"items":{},"type":"array"},"title":"Data","type":"array"},"metadata":{"anyOf":[{"additionalProperties":{"anyOf":[{"items":{},"type":"array"},{"type":"null"}]},"type":"object"},{"type":"null"}],"default":null,"title":"Metadata"}},"required":["headers","data"],"title":"DataframeData","type":"object"},"example_inputs":{"headers":["a","b"],"data":[["foo","bar"]]}},{"id":36,"type":"textbox","props":{"value":"CCBench","lines":1,"max_lines":20,"label":"CCBench","show_label":true,"container":true,"min_width":160,"visible":false,"autofocus":false,"autoscroll":true,"elem_classes":[],"type":"text","rtl":false,"show_copy_button":false,"name":"textbox","_selectable":false},"skip_api":false,"component_class_id":"d0491bb0fbd427bdb2a4549c4d1ac869","key":null,"api_info":{"type":"string"},"example_inputs":"Hello!!"},{"id":37,"type":"form","props":{"scale":0,"min_width":0,"name":"form"},"skip_api":true,"component_class_id":"43cda85c6ff7a5dd8f83d29496b014ee","key":null},{"id":38,"type":"form","props":{"scale":0,"min_width":0,"name":"form"},"skip_api":true,"component_class_id":"43cda85c6ff7a5dd8f83d29496b014ee","key":null},{"id":39,"type":"tabitem","props":{"label":"📊 MMBench_TEST_EN Leaderboard","visible":true,"interactive":true,"id":4,"elem_id":"MMBench_TEST_EN","name":"tab"},"skip_api":true,"component_class_id":"18f46968e2b273dc5dbda0fe78433d7e","key":null},{"id":40,"type":"markdown","props":{"value":"## MMBench TEST EN Evaluation Results \n\n- We adopt Circular Eval for benchmarks in MMBench series, you can check https://arxiv.org/pdf/2307.06281.pdf for the detailed definition of Circular Eval. ","show_label":true,"rtl":false,"latex_delimiters":[{"left":"$$","right":"$$","display":true}],"visible":true,"elem_classes":[],"sanitize_html":true,"line_breaks":false,"header_links":false,"show_copy_button":false,"name":"markdown","_selectable":false},"skip_api":false,"component_class_id":"0f35515b9a3362b42bb6721c836157a0","key":null,"api_info":{"type":"string"},"example_inputs":"# Hello!"},{"id":41,"type":"checkboxgroup","props":{"choices":[["Overall","Overall"],["CP","CP"],["FP-S","FP-S"],["FP-C","FP-C"],["AR","AR"],["LR","LR"],["RR","RR"]],"value":["Overall"],"type":"value","label":"MMBench_TEST_EN CheckBoxes","show_label":true,"container":true,"min_width":160,"interactive":true,"visible":true,"elem_classes":[],"name":"checkboxgroup","_selectable":false},"skip_api":false,"component_class_id":"0635a5d3bf87369f1c2c1c69f8a3d0cc","key":null,"api_info":{"items":{"enum":["Overall","CP","FP-S","FP-C","AR","LR","RR"],"type":"string"},"title":"Checkbox Group","type":"array"},"example_inputs":["Overall"]},{"id":42,"type":"row","props":{"variant":"default","visible":true,"equal_height":true,"show_progress":false,"name":"row"},"skip_api":true,"component_class_id":"b5cf3d15e2293fb5ccc071d7b8d69f64","key":null},{"id":43,"type":"textbox","props":{"value":"Input the Model Name (fuzzy, case insensitive)","lines":1,"max_lines":20,"label":"Model Name","show_label":true,"container":true,"min_width":160,"interactive":true,"visible":true,"autofocus":false,"autoscroll":true,"elem_classes":[],"type":"text","rtl":false,"show_copy_button":false,"name":"textbox","_selectable":false},"skip_api":false,"component_class_id":"d0491bb0fbd427bdb2a4549c4d1ac869","key":null,"api_info":{"type":"string"},"example_inputs":"Hello!!"},{"id":44,"type":"checkboxgroup","props":{"choices":[["<4B","<4B"],["4B-10B","4B-10B"],["10B-20B","10B-20B"],["20B-40B","20B-40B"],[">40B",">40B"],["Unknown","Unknown"]],"value":["<4B","4B-10B","10B-20B","20B-40B",">40B","Unknown"],"type":"value","label":"Model Size","show_label":true,"container":true,"min_width":160,"interactive":true,"visible":true,"elem_classes":[],"name":"checkboxgroup","_selectable":false},"skip_api":false,"component_class_id":"0635a5d3bf87369f1c2c1c69f8a3d0cc","key":null,"api_info":{"items":{"enum":["<4B","4B-10B","10B-20B","20B-40B",">40B","Unknown"],"type":"string"},"title":"Checkbox Group","type":"array"},"example_inputs":["<4B"]},{"id":45,"type":"checkboxgroup","props":{"choices":[["API","API"],["OpenSource","OpenSource"]],"value":["API","OpenSource"],"type":"value","label":"Model Type","show_label":true,"container":true,"min_width":160,"interactive":true,"visible":true,"elem_classes":[],"name":"checkboxgroup","_selectable":false},"skip_api":false,"component_class_id":"0635a5d3bf87369f1c2c1c69f8a3d0cc","key":null,"api_info":{"items":{"enum":["API","OpenSource"],"type":"string"},"title":"Checkbox Group","type":"array"},"example_inputs":["API"]},{"id":46,"type":"form","props":{"scale":3,"min_width":480,"name":"form"},"skip_api":true,"component_class_id":"43cda85c6ff7a5dd8f83d29496b014ee","key":null},{"id":47,"type":"dataframe","props":{"value":{"headers":["Rank","Method","Param (B)","Language Model","Vision Model","Eval Date","Overall"],"data":[[1,"GLM-4v-Plus-20250111",null,"","","2025/01/25",88.9],[2,"InternVL3-78B",78.4,"Qwen2.5-72B","InternViT-6B-v2.5","2025/04/14",88.8],[3,"InternVL2.5-78B-MPO",78.0,"Qwen-2.5-72B","InternViT-6B-v2.5","2024/12/29",88.4],[4,"Qwen2.5-VL-72B",73.4,"Qwen2.5-72B","QwenViT","2025/02/02",88.3],[5,"Step-1o",null,"","","2025/01/13",88.3],[6,"InternVL2.5-78B",78.0,"Qwen-2.5-72B","InternViT-6B-v2.5","2024/12/10",88.2],[7,"InternVL3-38B",38.4,"Qwen2.5-32B","InternViT-6B-v2.5","2025/04/14",87.7],[8,"Ovis2-34B",34.9,"Qwen2.5-32B","AIMv2-1B","2025/02/18",87.6],[9,"Ola-7b",8.88,"Qwen2.5-7B","Oryx-ViT","2025/02/05",87.4],[10,"Ovis2-16B",16.2,"Qwen2.5-14B","AIMv2 Huge","2025/02/18",87.2],[11,"BailingMM-Pro-0120",81.0,"Bailing-80B","SigLIP-400M","2025/01/25",87.1],[12,"GPT-4.1-mini-20250414",null,"","","2025/04/16",86.9],[13,"GPT-4.1-20250414",null,"","","2025/04/16",86.9],[14,"Qwen2-VL-72B",73.4,"Qwen2-72B","QwenViT","2024/10/28",86.9],[15,"Qwen-VL-Max-0809",72.0,"Qwen2-72B","QwenViT","2024/09/12",86.8],[16,"InternVL2-40B",40.0,"Nous-Hermes-2-Yi-34B","InternViT-6B","2024/07/11",86.8],[17,"Taiyi",null,"","","2024/12/11",86.7],[18,"InternVL2-Llama3-76B",76.0,"Llama-3-70B-Instruct","InternViT-6B","2024/07/19",86.5],[19,"InternVL2.5-38B-MPO",38.0,"Qwen-2.5-32B","InternViT-6B-v2.5","2024/12/28",86.4],[20,"HunYuan-Standard-Vision",null,"","","2025/01/15",86.4],[21,"LLaVA-OneVision-72B",73.0,"Qwen2-72B","SigLIP-400M","2024/09/19",85.8],[22,"InternVL3-14B",15.1,"Qwen2.5-14B","InternViT-300M-v2.5","2025/04/14",85.7],[23,"InternVL2.5-26B-MPO",26.0,"InternLM2.5-20B","InternViT-6B-v2.5","2024/12/28",85.6],[24,"Step-1.5V",null,"Step-1.5","stepencoder","2024/10/11",85.3],[25,"grok-2-vision-1212",null,"","","2025/03/03",85.3],[26,"VARCO-VISION-14B",15.2,"Qwen2.5-14B","SigLIP-400M","2025/01/02",85.1],[27,"Ovis2-8B",8.94,"Qwen2.5-7B","AIMv2 Huge","2025/02/18",84.8],[28,"Ovis1.6-Gemma2-27B",28.9,"Gemma2-27B","SigLIP-400M","2024/11/29",84.8],[29,"RBDash-v1.5",79.0,"Qwen2-72B","CLIP ViT-L/14
InternViT-6B","2024/11/17",84.6],[30,"abab7-preview",null,"","","2024/12/11",84.5],[31,"Gemini-2.0-Pro",null,"","","2025/02/27",84.3],[32,"BlueLM-V-3B",3.0,"BlueLM-3B","SigLIP-400M","2024/10/30",84.1],[33,"DeepSeek-VL2",27.5,"DeepSeekMoE-27B","SigLIP-400M","2025/01/01",84.1],[34,"BailingMM-Lite-1203",21.0,"Bailing-20B","SigLIP-400M","2024/12/08",84.0],[35,"InternVL3-9B",9.14,"InternLM3-8B","InternViT-300M-v2.5","2025/04/14",83.9],[36,"InternVL2.5-8B-MPO",8.0,"InternLM2.5-7B","InternViT-300M-v2.5","2024/12/28",83.9],[37,"MUG-U-7B",7.0,"","","2025/03/19",83.9],[38,"InternVL3-8B",7.94,"Qwen2.5-7B","InternViT-300M-v2.5","2025/04/14",83.6],[39,"Ovis2-4B",4.62,"Qwen2.5-3B","AIMv2 Huge","2025/02/18",83.6],[40,"MiniCPM-o-2.6",8.67,"Qwen2.5-7B","SigLIP-400M","2025/01/21",83.4],[41,"Ovis1.6-Gemma2-9B",10.2,"Gemma2-9B-It","SigLIP-400M","2024/09/19",83.4],[42,"GPT-4o (0513, detail-high)",null,"","","2024/05/31",83.4],[43,"InternVL2-26B",26.0,"InternLM2-20B","InternViT-6B","2024/07/11",83.4],[44,"Phi-4-MultiModal",5.57,"Phi-4-Mini","SigLIP-400M","2025/03/13",83.4],[45,"GPT-4o (0513, detail-low)",null,"","","2024/05/15",83.3],[46,"LLaVA-OneVision-7B",8.0,"Qwen2-7B","SigLIP-400M","2024/09/16",83.2],[47,"Qwen2.5-VL-7B",8.29,"Qwen2.5-7B","QwenViT","2025/02/02",83.2],[48,"DeepSeek-VL2-Small",16.1,"DeepSeekMoE-16B","SigLIP-400M","2025/01/01",82.8],[49,"POINTS1.5-Qwen2.5-7B",8.3,"Qwen-2.5-7B","NaViT","2024/12/06",82.8],[50,"Qwen2-VL-7B",8.0,"Qwen2-7B","QwenViT","2024/09/12",82.8],[51,"CongRong",null,"","","2024/06/26",82.8],[52,"Qwen-VL-Plus-0809",null,"","","2024/09/17",82.7],[53,"OmChat-v2.0-13B",13.0,"Qwen2-7B","InternViT-6B","2024/08/22",82.6],[54,"Claude3.5-Sonnet-20241022",null,"","","2024/11/06",82.6],[55,"MMAlaya2",26.0,"InternLM2-20B","InternViT-6B","2024/08/27",82.5],[56,"InternVL-Chat-V1.5",26.0,"InternLM2-20B","InternViT-6B","2024/04/17",82.3],[57,"TransCore-M",13.4,"PCITransGPT-13B","CLIP ViT-L/14","2024/04/16",82.3],[58,"Gemma3-27B",27.4,"Gemma3-27B","SigLIP-400M","2025/03/19",82.3],[59,"GPT-4o (0806, detail-high)",null,"","","2024/08/08",82.1],[60,"Kimi-VL-A3B-Instruct",16.4,"Moonlight-16B-A3B","MoonViT","2025/04/14",82.1],[61,"InternLM-XComposer2.5",8.0,"InternLM2-7B","CLIP ViT-L/14","2024/07/11",82.0],[62,"InternVL2-8B",8.0,"InternLM2.5-7B","InternViT-300M","2024/07/11",82.0],[63,"VILA1.5-40B",40.0,"Yi-34B","InternViT-6B","2024/08/25",81.7],[64,"POINTS-Yi-1.5-9B",9.5,"Yi-1.5-9B","CLIP ViT-L/14","2024/10/11",81.6],[65,"MiniCPM-V-2.6",8.0,"Qwen2-7B","SigLIP-400M","2024/08/08",81.5],[66,"GLM-4v-Plus",null,"","","2024/12/11",81.4],[67,"Claude3.7-Sonnet",null,"","","2025/02/27",81.4],[68,"POINTS-Qwen2.5-7B",8.3,"Qwen-2.5-7B","CLIP ViT-L/14","2024/10/19",81.4],[69,"GLM-4v",null,"","","2024/05/20",81.3],[70,"LLaVA-Next-Yi-34B",34.8,"Yi-34B","CLIP ViT-L/14","2024/03/25",81.1],[71,"GPT-4v (0409, detail-high)",null,"","","2024/05/15",81.0],[72,"Ovis1.5-Gemma2-9B",11.4,"Gemma2-9B-It","SigLIP-400M","2024/08/04",80.9],[73,"InternVL3-2B",2.09,"Qwen2.5-1.5B","InternViT-300M-v2.5","2025/04/14",80.8],[74,"Ovis1.5-Llama3-8B",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/07/29",80.8],[75,"GPT-4v (0409, detail-low)",null,"","","2024/05/15",80.8],[76,"InternLM-XComposer2",7.0,"InternLM2-7B","CLIP ViT-L/14","2024/01/26",80.7],[77,"LLaVA-OneVision-7B (SI)",8.0,"Qwen2-7B","SigLIP-400M","2024/09/17",80.5],[78,"Ross-Qwen2-7B",8.2,"Qwen2-7B","CLIP ViT-L/14","2025/01/17",80.5],[79,"Cambrian-34B",34.0,"Nous-Hermes-2-Yi-34B","CLIP ViT-L/14","2024/07/18",80.4],[80,"NVLM-D-72B",79.4,"Qwen2-72B","InternViT-6B","2024/10/19",80.4],[81,"Llama-3.2-90B-Vision-Instruct",88.6,"Llama-3.1-70B","","2024/10/19",80.4],[82,"InternVL2.5-4B-MPO",4.0,"Qwen-2.5-3B","InternViT-300M-v2.5","2024/12/28",80.4],[83,"InternLM-XComposer2-4KHD",7.0,"InternLM2-7B","CLIP ViT-L/14","2024/06/09",80.2],[84,"Eagle-X5-34B-Chat",36.8,"Yi-34B","Clip-448
ConvNeXT-1024
SAM-1024
DET-1024
Pix2Struct-1024","2024/11/29",80.0],[85,"Aria",25.3,"Aria-MoE","SigLIP-400M","2024/12/05",80.0],[86,"VITA-1.5",8.3,"Qwen2-7B","InternViT-300M","2025/01/01",79.8],[87,"Claude3.5-Sonnet",null,"","","2024/06/24",79.7],[88,"LLaVA-Next-Qwen-32B",33.0,"Qwen-1.5-32B","SigLIP-400M","2024/08/08",79.4],[89,"Gemini-1.5-Flash",null,"","","2024/09/16",79.4],[90,"WeMM",7.0,"InternLM2-7B","SigLIP-400M","2024/06/09",79.3],[91,"moonshot-v1-8k",null,"","","2025/03/03",79.3],[92,"InternVL2-8B-MPO",8.0,"InternLM2.5-7B","InternViT-300M","2024/11/25",79.2],[93,"Qwen2.5-VL-3B",3.75,"Qwen2.5-3B","QwenViT","2025/02/02",79.1],[94,"Aquila-VL-2B",2.2,"Qwen-2.5-1.5B","SigLIP-400M","2024/10/24",79.0],[95,"SAIL-VL-2B",2.1,"Qwen2.5-1.5B","InternViT-300M","2024/12/25",79.0],[96,"360VL-70B",70.0,"Llama-3-70B-Instruct","CLIP ViT-L/14","2024/05/25",78.8],[97,"Ovis2-2B",2.46,"Qwen2.5-1.5B","AIMv2 Large","2025/02/18",78.6],[98,"InternVL2-4B",4.0,"Phi-3","InternViT-300M","2024/07/11",78.5],[99,"Ovis1.6-Llama3.2-3B",4.1,"Llama-3.2-3B","SigLIP-400M","2024/10/24",78.5],[100,"XinYuan-VL-2B-Instruct",2.0,"Qwen2-1.5B","QwenViT","2024/09/27",78.4],[101,"InternVL2-8B-MPO-CoT",8.0,"InternLM2.5-7B","InternViT-300M","2024/11/25",78.3],[102,"Bunny-Llama3-8B",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/07/18",78.3],[103,"XGen-MM-Instruct-Interleave-v1.5",4.4,"Phi-3","SigLIP-400M","2024/09/06",78.3],[104,"Yi-Vision",null,"","","2024/08/03",78.1],[105,"granite-vision-3.2-2b",2.98,"granite-3.1-2b-instruct","SigLip","2025/06/20",78.1],[106,"XGen-MM-Instruct-DPO-v1.5",4.4,"Phi-3","SigLIP-400M","2024/09/06",78.0],[107,"Pixtral-12B",13.0,"Nemo-12B","ViT-400M","2024/09/16",77.9],[108,"Qwen-VL-Max",null,"QwenLM","","2024/02/02",77.6],[109,"GPT-4o-mini (0718, detail-high)",null,"","","2024/07/20",77.6],[110,"MiniCPM-Llama3-V2.5",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/05/27",77.6],[111,"Gemma3-12B",12.2,"Gemma3-12B","SigLIP-400M","2025/03/19",77.5],[112,"Idefics3-8B-Llama3",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/08/27",77.5],[113,"GPT-4v (1106, detail-low)",null,"","","2023/12/23",77.0],[114,"Llama-3-MixSense-v1.1",8.0,"Llama-3-8B-Instruct","Florence-2-Large-FT","2024/08/21",77.0],[115,"RekaFlash",null,"","","2024/05/07",76.8],[116,"Phi-3.5-Vision",4.0,"Phi-3.5","CLIP ViT-L/14","2024/08/28",76.0],[117,"Mantis-8B-Idefics2",8.0,"Mistral-7B","SigLIP-400M","2024/08/08",76.0],[118,"Mini-InternVL-Chat-4B-V1.5",4.0,"Phi-3","InternViT-300M","2024/06/10",75.7],[119,"IDEFICS2-8B",8.0,"Mistral-7B","SigLIP-400M","2024/04/26",75.7],[120,"XVERSE-V-13B",13.0,"XVERSE-13B","CLIP ViT-L/14","2024/05/10",75.4],[121,"LLaVA-InternLM2-20B (QLoRA)",20.2,"InternLM2-20B","CLIP ViT-L/14","2024/01/17",75.1],[122,"LLaVA-Next-Llama3",8.0,"Llama-3-8B-Instruct","CLIP ViT-L/14","2024/07/29",74.8],[123,"LLaVA-Next-Interleave-7B",8.0,"Qwen-1.5-7B","SigLIP-400M","2024/08/08",74.7],[124,"Cambrian-8B",8.0,"Vicuna-v1.5-7B","CLIP ViT-L/14","2024/07/11",74.6],[125,"Qwen2-VL-2B",2.0,"Qwen2-1.5B","QwenViT","2024/09/12",74.6],[126,"DeepSeek-VL2-Tiny",3.4,"DeepSeekMoE-3B","SigLIP-400M","2025/01/01",74.6],[127,"InternVL2.5-2B-MPO",2.0,"InternLM2.5-1.8B","InternViT-300M-v2.5","2024/12/28",74.5],[128,"InternLM-XComposer",8.0,"InternLM-7B","EVA-G","2023/09/26",74.4],[129,"VILA1.5-13B",13.0,"Vicuna-v1.5-13B","SigLIP-400M","2024/08/25",74.4],[130,"Gemini-1.5-Pro",null,"","","2024/06/10",73.9],[131,"CogVLM2-19B-Chat",19.0,"Llama-3-8B-Instruct","EVA2-CLIP-E","2024/05/31",73.9],[132,"DeepSeek-VL-7B",7.3,"DeekSeek-7B","SAM-B
SigLIP-L","2024/03/21",73.8],[133,"LLaVA-Next-Interleave-7B-DPO",8.0,"Qwen-1.5-7B","SigLIP-400M","2024/07/29",73.8],[134,"Phi-3-Vision",4.2,"Phi-3","CLIP ViT-L/14","2024/05/31",73.6],[135,"Gemini-1.0-Pro",null,"","","2023/12/23",73.6],[136,"Molmo-7B-D",8.0,"Qwen2-7B","CLIP ViT-L/14","2024/10/12",73.6],[137,"granite-vision-3.3-2b",2.98,"granite-3.1-2b-instruct","SigLIP2-400M","2025/06/20",73.5],[138,"InternVL2-2B",2.0,"InternLM2-1.8B","InternViT-300M","2024/07/11",73.4],[139,"LLaVA-InternLM2-7B (QLoRA)",8.1,"InternLM2-7B","CLIP ViT-L/14","2024/01/17",73.3],[140,"Cambrian-13B",13.0,"Vicuna-v1.5-13B","CLIP ViT-L/14","2024/07/29",73.2],[141,"InternLM-XComposer2-1.8B",2.0,"InternLM2-1.8B","CLIP ViT-L/14","2024/06/09",73.0],[142,"Slime-8B",8.0,"Llama-3-8B-Instruct","CLIP ViT-L/14","2024/09/14",72.8],[143,"Eagle-X5-13B",15.0,"Vicuna-v1.5-13B","Clip-448
ConvNeXT-1024
SAM-1024
DET-1024
Pix2Struct-1024","2024/09/26",72.6],[144,"Monkey-Chat",9.8,"Qwen-7B","ViT-BigHuge","2024/01/16",72.4],[145,"Yi-VL-34B",34.6,"Yi-34B","CLIP ViT-H/14","2024/01/25",72.4],[146,"MiniMonkey",2.2,"InternLM2-1.8B","InternViT-300M","2024/09/26",72.4],[147,"InternVL3-1B",0.94,"Qwen2.5-0.5B","InternViT-300M-v2.5","2025/04/14",72.3],[148,"Molmo-7B-O",8.0,"Qwen2-7B","CLIP ViT-L/14","2024/10/20",72.2],[149,"H2OVL-2B",2.2,"H2O-DANUBE2-1.8B","InternViT-300M","2024/10/31",72.1],[150,"Parrot-7B",8.0,"Qwen2-7B","CLIP ViT-L/14","2024/08/22",72.0],[151,"LLaVA-LLaMA-3-8B",8.0,"Llama-3-8B-Instruct","CLIP ViT-L/14","2024/05/07",71.7],[152,"OmniLMM-12B",12.0,"Zephyr-7B-β","EVA-02-5B","2024/02/07",71.7],[153,"Ovis2-1B",1.27,"Qwen2.5-0.5B","AIMv2 Large","2025/02/18",71.6],[154,"GLM-4v-9B",9.0,"GLM-4-9B","EVA-02-5B","2024/06/14",71.4],[155,"SmolVLM2",2.25,"SmolLM2-1.7M","SigLIP-400M","2025/03/13",71.4],[156,"PaliGemma-3B-mix-448",3.0,"Gemma-2B","SigLIP-400M","2024/05/17",71.0],[157,"Falcon2-VLM-11B",11.4,"Falcon2-11B","CLIP ViT-L/14","2024/10/30",70.7],[158,"Mini-InternVL-Chat-2B-V1.5",2.0,"InternLM2-1.8B","InternViT-300M","2024/06/10",70.7],[159,"Vintern-3B-beta",3.7,"Qwen-2.5-3B","InternViT-300M","2024/10/24",70.6],[160,"InternVL2.5-1B-MPO",1.0,"Qwen-2.5-0.5B","InternViT-300M-v2.5","2024/12/28",70.1],[161,"Eagle-X5-7B",9.0,"Vicuna-v1.5-7B","Clip-448
ConvNeXT-1024
SAM-1024
DET-1024
Pix2Struct-1024","2024/09/26",70.1],[162,"Moondream2",1.9,"SigLIP-400M","Phi-1.5","2024/10/20",70.0],[163,"LLaVA-Next-Vicuna-13B",13.4,"Vicuna-v1.5-13B","CLIP ViT-L/14","2024/03/25",70.0],[164,"ShareGPT4V-13B",13.4,"Vicuna-v1.5-13B","CLIP ViT-L/14","2023/12/08",69.8],[165,"LLaVA-Next-Mistral-7B",7.6,"Mistral-7B","CLIP ViT-L/14","2024/03/25",69.6],[166,"Gemma3-4B",4.3,"Gemma3-4B","SigLIP-400M","2025/03/19",69.6],[167,"LLaVA-Next-Vicuna-7B",7.1,"Vicuna-v1.5-7B","CLIP ViT-L/14","2024/03/25",69.2],[168,"LLaVA-v1.5-13B",13.4,"Vicuna-v1.5-13B","CLIP ViT-L/14","2023/10/05",69.2],[169,"MiniCPM-V-2",2.8,"MiniCPM-2.4B","SigLIP-400M","2024/04/15",69.1],[170,"Mantis-8B-siglip-llama3",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/08/08",69.0],[171,"LLaVA-InternLM-7B (QLoRA)",7.6,"InternLM-7B","CLIP ViT-L/14","2023/12/28",69.0],[172,"AKI-4B",4.33,"Phi-3.5","SigLIP-400M","2025/03/25",68.8],[173,"LLaVA-v1.5-13B (QLoRA)",13.4,"Vicuna-v1.5-13B","CLIP ViT-L/14","2023/12/28",68.8],[174,"Yi-VL-6B",6.6,"Yi-6B","CLIP ViT-H/14","2024/01/25",68.4],[175,"GPT-4.1-nano-20250414",null,"","","2025/04/16",68.2],[176,"Mantis-8B-clip-llama3",8.0,"Llama-3-8B-Instruct","CLIP ViT-L/14","2024/08/08",68.2],[177,"Llama-3.2-11B-Vision-Instruct",11.0,"Llama-3.1-8B","","2024/10/07",68.0],[178,"Claude3-Sonnet",null,"","","2024/03/28",67.8],[179,"LLaVA-v1.5-7B (QLoRA)",7.2,"Vicuna-v1.5-7B","CLIP ViT-L/14","2023/12/28",67.7],[180,"ShareGPT4V-7B",7.2,"Vicuna-v1.5-7B","CLIP ViT-L/14","2023/12/08",67.6],[181,"SmolVLM-Instruct",2.3,"SmolLM2-1.7B","SigLIP-400M","2025/01/27",67.5],[182,"Qwen-VL-Plus",null,"QwenLM","","2024/01/10",67.0],[183,"ShareCaptioner",8.0,"InternLM-7B","EVA-G","2024/01/03",66.5],[184,"LLaVA-v1.5-7B",7.2,"Vicuna-v1.5-7B","CLIP ViT-L/14","2023/10/05",66.5],[185,"RekaEdge",null,"","","2024/05/31",66.4],[186,"DeepSeek-VL-1.3B",2.0,"DeekSeek-1B","SAM-B
SigLIP-L","2024/03/21",66.4],[187,"mPLUG-Owl2",8.2,"Llama-2-7B","CLIP ViT-L/14","2023/11/10",66.0],[188,"Slime-7B",7.0,"Vicuna-v1.5-7B","CLIP ViT-L/14","2024/09/14",65.8],[189,"CogVLM-17B-Chat",17.0,"Vicuna-v1.5-7B","EVA2-CLIP-E","2024/01/03",65.8],[190,"GPT-4v (1106, detail-high)",null,"","","2024/04/22",65.4],[191,"Slime-13B",13.0,"Vicuna-v1.5-13B","CLIP ViT-L/14","2024/09/14",65.4],[192,"InternVL2-1B",1.0,"Qwen2-0.5B","InternViT-300M","2024/07/11",65.2],[193,"SmolVLM-Instruct-DPO",2.3,"SmolLM2-1.7B","SigLIP-400M","2025/01/27",65.0],[194,"MolmoE-1B",7.2,"OLMoE-1B-7B-0924","CLIP ViT-L/14","2024/10/21",64.6],[195,"VILA1.5-3B",3.0,"Sheared-LLaMA-2.7B","SigLIP-400M","2024/08/25",64.5],[196,"MiniCPM-V",3.0,"MiniCPM-2.4B","SigLIP-400M","2024/02/07",64.1],[197,"Emu3_chat",8.49,"","","2025/01/26",63.8],[198,"Emu2_chat",37.0,"Llama-33B","EVA-02-CLIP-E-plus","2024/01/17",63.6],[199,"Claude3-Opus",null,"","","2024/03/28",63.3],[200,"Janus-Pro-7B",7.42,"DeepSeek-7B","SigLIP-400M","2025/02/02",62.6],[201,"Moondream1",1.9,"SigLIP-400M","Phi-1.5","2024/09/26",62.3],[202,"Llama-3-VILA1.5-8B",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/08/25",62.1],[203,"Qwen-VL-Chat",9.6,"Qwen-7B","ViT-G/16","2023/08/24",61.8],[204,"LLaVA-OneVision-0.5B",1.0,"Qwen2-0.5B","SigLIP-400M","2024/09/16",61.6],[205,"abab6.5s",null,"","","2024/12/11",61.0],[206,"Claude3-Haiku",null,"","","2024/03/28",60.7],[207,"Monkey",9.8,"Qwen-7B","ViT-BigHuge","2024/01/11",59.6],[208,"MMAlaya",7.8,"Alaya-7B-Chat","EVA-G","2024/01/29",58.7],[209,"H2OVL-800M",0.83,"H2O-DANUBE3-500M","InternViT-300M","2024/10/31",56.3],[210,"LLaVA-OneVision-0.5B (SI)",1.0,"Qwen2-0.5B","SigLIP-400M","2024/09/17",55.8],[211,"IDEFICS-80B-Instruct",80.0,"Llama-65B","CLIP ViT-H/14","2023/07/25",54.6],[212,"SmolVLM-500M",0.51,"SmolLM2-360M","ViT-93M","2025/01/27",53.8],[213,"SmolVLM-Synthetic",2.3,"SmolLM2-1.7B","SigLIP-400M","2025/01/27",53.7],[214,"SmolVLM2-500M",0.51,"SmolLM2-360M","ViT-93M","2025/03/13",53.1],[215,"Janus-1.3B",2.1,"DeepSeek-1B","SigLIP-400M","2024/10/24",52.0],[216,"Mantis-8B-Fuyu",8.0,"Fuyu-8B","","2024/09/07",46.6],[217,"IDEFICS-9B-Instruct",9.0,"Llama-7B","CLIP ViT-H/14","2023/07/25",45.3],[218,"LLaVA-v1-7B",7.2,"Llama-7B","CLIP ViT-L/14","2023/04/17",43.8],[219,"PandaGPT-13B",14.0,"Vicuna-13B","ImageBind ViT-H/14","2023/05/25",42.5],[220,"SmolVLM-256M",0.26,"SmolLM2-135M","ViT-93M","2025/01/27",41.7],[221,"VisualGLM",8.0,"ChatGLM 6B","EVA-CLIP","2023/05/17",37.6],[222,"InstructBLIP-7B",8.0,"Vicuna-7B","EVA-G","2023/05/11",33.9],[223,"Chameleon-30B",30.0,"","","2024/07/29",32.5],[224,"Qwen-VL",9.6,"Qwen-7B","ViT-G/16","2023/08/24",32.2],[225,"MiniGPT-4-v1-7B",8.0,"Vicuna-7B","EVA-G","2023/04/20",23.0],[226,"Step-1.5V-mini",null,"","","2024/12/11",18.1],[227,"Chameleon-7B",7.0,"","","2024/07/29",15.4],[228,"SmolVLM2-256M",0.26,"SmolLM2-135M","ViT-93M","2025/03/13",11.9],[229,"MiniGPT-4-v2",8.0,"Llama-2-13B","EVA-G","2023/10/27",9.4],[230,"OpenFlamingo v2",9.0,"MPT 7B","CLIP ViT-L/14","2023/06/28",5.7],[231,"Kosmos2",1.7,"","","2024/10/19",1.1]],"metadata":null},"headers":["1","2","3"],"row_count":[1,"dynamic"],"col_count":[3,"dynamic"],"datatype":["number","html","number","html","html","str","number"],"type":"pandas","latex_delimiters":[{"left":"$$","right":"$$","display":true}],"show_label":true,"height":500,"min_width":160,"interactive":false,"visible":true,"elem_classes":[],"wrap":true,"line_breaks":true,"column_widths":[],"name":"dataframe","_selectable":false},"skip_api":false,"component_class_id":"6a51bb3357f2e94c40fb8d4fbe06aa8e","key":null,"api_info":{"properties":{"headers":{"items":{"type":"string"},"title":"Headers","type":"array"},"data":{"items":{"items":{},"type":"array"},"title":"Data","type":"array"},"metadata":{"anyOf":[{"additionalProperties":{"anyOf":[{"items":{},"type":"array"},{"type":"null"}]},"type":"object"},{"type":"null"}],"default":null,"title":"Metadata"}},"required":["headers","data"],"title":"DataframeData","type":"object"},"example_inputs":{"headers":["a","b"],"data":[["foo","bar"]]}},{"id":48,"type":"textbox","props":{"value":"MMBench_TEST_EN","lines":1,"max_lines":20,"label":"MMBench_TEST_EN","show_label":true,"container":true,"min_width":160,"visible":false,"autofocus":false,"autoscroll":true,"elem_classes":[],"type":"text","rtl":false,"show_copy_button":false,"name":"textbox","_selectable":false},"skip_api":false,"component_class_id":"d0491bb0fbd427bdb2a4549c4d1ac869","key":null,"api_info":{"type":"string"},"example_inputs":"Hello!!"},{"id":49,"type":"form","props":{"scale":0,"min_width":0,"name":"form"},"skip_api":true,"component_class_id":"43cda85c6ff7a5dd8f83d29496b014ee","key":null},{"id":50,"type":"form","props":{"scale":0,"min_width":0,"name":"form"},"skip_api":true,"component_class_id":"43cda85c6ff7a5dd8f83d29496b014ee","key":null},{"id":51,"type":"tabitem","props":{"label":"📊 MMBench_TEST_CN Leaderboard","visible":true,"interactive":true,"id":5,"elem_id":"MMBench_TEST_CN","name":"tab"},"skip_api":true,"component_class_id":"18f46968e2b273dc5dbda0fe78433d7e","key":null},{"id":52,"type":"markdown","props":{"value":"## MMBench TEST CN Evaluation Results \n\n- We adopt Circular Eval for benchmarks in MMBench series, you can check https://arxiv.org/pdf/2307.06281.pdf for the detailed definition of Circular Eval. ","show_label":true,"rtl":false,"latex_delimiters":[{"left":"$$","right":"$$","display":true}],"visible":true,"elem_classes":[],"sanitize_html":true,"line_breaks":false,"header_links":false,"show_copy_button":false,"name":"markdown","_selectable":false},"skip_api":false,"component_class_id":"0f35515b9a3362b42bb6721c836157a0","key":null,"api_info":{"type":"string"},"example_inputs":"# Hello!"},{"id":53,"type":"checkboxgroup","props":{"choices":[["Overall","Overall"],["CP","CP"],["FP-S","FP-S"],["FP-C","FP-C"],["AR","AR"],["LR","LR"],["RR","RR"]],"value":["Overall"],"type":"value","label":"MMBench_TEST_CN CheckBoxes","show_label":true,"container":true,"min_width":160,"interactive":true,"visible":true,"elem_classes":[],"name":"checkboxgroup","_selectable":false},"skip_api":false,"component_class_id":"0635a5d3bf87369f1c2c1c69f8a3d0cc","key":null,"api_info":{"items":{"enum":["Overall","CP","FP-S","FP-C","AR","LR","RR"],"type":"string"},"title":"Checkbox Group","type":"array"},"example_inputs":["Overall"]},{"id":54,"type":"row","props":{"variant":"default","visible":true,"equal_height":true,"show_progress":false,"name":"row"},"skip_api":true,"component_class_id":"b5cf3d15e2293fb5ccc071d7b8d69f64","key":null},{"id":55,"type":"textbox","props":{"value":"Input the Model Name (fuzzy, case insensitive)","lines":1,"max_lines":20,"label":"Model Name","show_label":true,"container":true,"min_width":160,"interactive":true,"visible":true,"autofocus":false,"autoscroll":true,"elem_classes":[],"type":"text","rtl":false,"show_copy_button":false,"name":"textbox","_selectable":false},"skip_api":false,"component_class_id":"d0491bb0fbd427bdb2a4549c4d1ac869","key":null,"api_info":{"type":"string"},"example_inputs":"Hello!!"},{"id":56,"type":"checkboxgroup","props":{"choices":[["<4B","<4B"],["4B-10B","4B-10B"],["10B-20B","10B-20B"],["20B-40B","20B-40B"],[">40B",">40B"],["Unknown","Unknown"]],"value":["<4B","4B-10B","10B-20B","20B-40B",">40B","Unknown"],"type":"value","label":"Model Size","show_label":true,"container":true,"min_width":160,"interactive":true,"visible":true,"elem_classes":[],"name":"checkboxgroup","_selectable":false},"skip_api":false,"component_class_id":"0635a5d3bf87369f1c2c1c69f8a3d0cc","key":null,"api_info":{"items":{"enum":["<4B","4B-10B","10B-20B","20B-40B",">40B","Unknown"],"type":"string"},"title":"Checkbox Group","type":"array"},"example_inputs":["<4B"]},{"id":57,"type":"checkboxgroup","props":{"choices":[["API","API"],["OpenSource","OpenSource"]],"value":["API","OpenSource"],"type":"value","label":"Model Type","show_label":true,"container":true,"min_width":160,"interactive":true,"visible":true,"elem_classes":[],"name":"checkboxgroup","_selectable":false},"skip_api":false,"component_class_id":"0635a5d3bf87369f1c2c1c69f8a3d0cc","key":null,"api_info":{"items":{"enum":["API","OpenSource"],"type":"string"},"title":"Checkbox Group","type":"array"},"example_inputs":["API"]},{"id":58,"type":"form","props":{"scale":3,"min_width":480,"name":"form"},"skip_api":true,"component_class_id":"43cda85c6ff7a5dd8f83d29496b014ee","key":null},{"id":59,"type":"dataframe","props":{"value":{"headers":["Rank","Method","Param (B)","Language Model","Vision Model","Eval Date","Overall"],"data":[[1,"InternVL3-78B",78.4,"Qwen2.5-72B","InternViT-6B-v2.5","2025/04/14",88.8],[2,"InternVL2.5-78B",78.0,"Qwen-2.5-72B","InternViT-6B-v2.5","2024/12/10",88.5],[3,"InternVL2.5-78B-MPO",78.0,"Qwen-2.5-72B","InternViT-6B-v2.5","2024/12/29",88.2],[4,"Qwen2.5-VL-72B",73.4,"Qwen2.5-72B","QwenViT","2025/02/02",88.2],[5,"Ovis2-34B",34.9,"Qwen2.5-32B","AIMv2-1B","2025/02/18",88.0],[6,"Step-1o",null,"","","2025/01/13",87.6],[7,"Ovis2-16B",16.2,"Qwen2.5-14B","AIMv2 Huge","2025/02/18",86.9],[8,"InternVL3-38B",38.4,"Qwen2.5-32B","InternViT-6B-v2.5","2025/04/14",86.9],[9,"GPT-4.1-20250414",null,"","","2025/04/16",86.8],[10,"Qwen2-VL-72B",73.4,"Qwen2-72B","QwenViT","2024/10/28",86.7],[11,"InternVL2-Llama3-76B",76.0,"Llama-3-70B-Instruct","InternViT-6B","2024/07/19",86.5],[12,"InternVL2.5-38B-MPO",38.0,"Qwen-2.5-32B","InternViT-6B-v2.5","2024/12/28",86.4],[13,"InternVL2-40B",40.0,"Nous-Hermes-2-Yi-34B","InternViT-6B","2024/07/11",86.4],[14,"BailingMM-Pro-0120",81.0,"Bailing-80B","SigLIP-400M","2025/01/25",85.7],[15,"GPT-4.1-mini-20250414",null,"","","2025/04/16",85.5],[16,"Taiyi",null,"","","2024/12/11",85.4],[17,"GLM-4v-Plus-20250111",null,"","","2025/01/25",85.4],[18,"InternVL2.5-26B-MPO",26.0,"InternLM2.5-20B","InternViT-6B-v2.5","2024/12/28",85.3],[19,"LLaVA-OneVision-72B",73.0,"Qwen2-72B","SigLIP-400M","2024/09/19",85.3],[20,"Ola-7b",8.88,"Qwen2.5-7B","Oryx-ViT","2025/02/05",85.1],[21,"HunYuan-Standard-Vision",null,"","","2025/01/15",85.0],[22,"Ovis2-8B",8.94,"Qwen2.5-7B","AIMv2 Huge","2025/02/18",85.0],[23,"grok-2-vision-1212",null,"","","2025/03/03",84.8],[24,"Step-1.5V",null,"Step-1.5","stepencoder","2024/10/11",84.5],[25,"InternVL3-14B",15.1,"Qwen2.5-14B","InternViT-300M-v2.5","2025/04/14",84.4],[26,"Ovis1.6-Gemma2-27B",28.9,"Gemma2-27B","SigLIP-400M","2024/11/29",84.3],[27,"InternVL3-9B",9.14,"InternLM3-8B","InternViT-300M-v2.5","2025/04/14",83.6],[28,"Claude3.5-Sonnet-20241022",null,"","","2024/11/06",83.5],[29,"BailingMM-Lite-1203",21.0,"Bailing-20B","SigLIP-400M","2024/12/08",83.4],[30,"BlueLM-V-3B",3.0,"BlueLM-3B","SigLIP-400M","2024/10/30",83.3],[31,"MUG-U-7B",7.0,"","","2025/03/19",83.2],[32,"MiniCPM-o-2.6",8.67,"Qwen2.5-7B","SigLIP-400M","2025/01/21",83.0],[33,"RBDash-v1.5",79.0,"Qwen2-72B","CLIP ViT-L/14
InternViT-6B","2024/11/17",83.0],[34,"Ovis2-4B",4.62,"Qwen2.5-3B","AIMv2 Huge","2025/02/18",82.9],[35,"Qwen2.5-VL-7B",8.29,"Qwen2.5-7B","QwenViT","2025/02/02",82.8],[36,"InternVL3-8B",7.94,"Qwen2.5-7B","InternViT-300M-v2.5","2025/04/14",82.7],[37,"LLaVA-OneVision-7B",8.0,"Qwen2-7B","SigLIP-400M","2024/09/16",82.7],[38,"DeepSeek-VL2",27.5,"DeepSeekMoE-27B","SigLIP-400M","2025/01/01",82.4],[39,"InternVL2.5-8B-MPO",8.0,"InternLM2.5-7B","InternViT-300M-v2.5","2024/12/28",82.4],[40,"abab7-preview",null,"","","2024/12/11",82.3],[41,"VARCO-VISION-14B",15.2,"Qwen2.5-14B","SigLIP-400M","2025/01/02",82.2],[42,"InternVL2-26B",26.0,"InternLM2-20B","InternViT-6B","2024/07/11",82.1],[43,"GPT-4o (0513, detail-high)",null,"","","2024/05/31",82.1],[44,"MMAlaya2",26.0,"InternLM2-20B","InternViT-6B","2024/08/27",82.1],[45,"POINTS1.5-Qwen2.5-7B",8.3,"Qwen-2.5-7B","NaViT","2024/12/06",82.1],[46,"GPT-4o (0513, detail-low)",null,"","","2024/05/15",82.1],[47,"GLM-4v-Plus",null,"","","2024/12/11",82.1],[48,"Ovis1.6-Gemma2-9B",10.2,"Gemma2-9B-It","SigLIP-400M","2024/09/19",82.0],[49,"CongRong",null,"","","2024/06/26",81.9],[50,"Kimi-VL-A3B-Instruct",16.4,"Moonlight-16B-A3B","MoonViT","2025/04/14",81.9],[51,"OmChat-v2.0-13B",13.0,"Qwen2-7B","InternViT-6B","2024/08/22",81.4],[52,"VILA1.5-40B",40.0,"Yi-34B","InternViT-6B","2024/08/25",81.2],[53,"DeepSeek-VL2-Small",16.1,"DeepSeekMoE-16B","SigLIP-400M","2025/01/01",81.0],[54,"Claude3.7-Sonnet",null,"","","2025/02/27",80.9],[55,"InternVL2-8B",8.0,"InternLM2.5-7B","InternViT-300M","2024/07/11",80.9],[56,"InternLM-XComposer2.5",8.0,"InternLM2-7B","CLIP ViT-L/14","2024/07/11",80.9],[57,"InternVL-Chat-V1.5",26.0,"InternLM2-20B","InternViT-6B","2024/04/17",80.7],[58,"Claude3.5-Sonnet",null,"","","2024/06/24",80.7],[59,"Gemma3-27B",27.4,"Gemma3-27B","SigLIP-400M","2025/03/19",80.7],[60,"TransCore-M",13.4,"PCITransGPT-13B","CLIP ViT-L/14","2024/04/16",80.7],[61,"Qwen2-VL-7B",8.0,"Qwen2-7B","QwenViT","2024/09/12",80.6],[62,"POINTS-Yi-1.5-9B",9.5,"Yi-1.5-9B","CLIP ViT-L/14","2024/10/11",80.3],[63,"GPT-4o (0806, detail-high)",null,"","","2024/08/08",80.3],[64,"GPT-4v (0409, detail-high)",null,"","","2024/05/15",80.2],[65,"NVLM-D-72B",79.4,"Qwen2-72B","InternViT-6B","2024/10/19",80.2],[66,"InternLM-XComposer2",7.0,"InternLM2-7B","CLIP ViT-L/14","2024/01/26",79.4],[67,"GLM-4v",null,"","","2024/05/20",79.4],[68,"MiniCPM-V-2.6",8.0,"Qwen2-7B","SigLIP-400M","2024/08/08",79.3],[69,"Ovis2-2B",2.46,"Qwen2.5-1.5B","AIMv2 Large","2025/02/18",79.3],[70,"Cambrian-34B",34.0,"Nous-Hermes-2-Yi-34B","CLIP ViT-L/14","2024/07/18",79.2],[71,"LLaVA-Next-Qwen-32B",33.0,"Qwen-1.5-32B","SigLIP-400M","2024/08/08",79.1],[72,"GPT-4v (0409, detail-low)",null,"","","2024/05/15",79.1],[73,"InternVL3-2B",2.09,"Qwen2.5-1.5B","InternViT-300M-v2.5","2025/04/14",79.0],[74,"POINTS-Qwen2.5-7B",8.3,"Qwen-2.5-7B","CLIP ViT-L/14","2024/10/19",79.0],[75,"LLaVA-Next-Yi-34B",34.8,"Yi-34B","CLIP ViT-L/14","2024/03/25",79.0],[76,"InternVL2.5-4B-MPO",4.0,"Qwen-2.5-3B","InternViT-300M-v2.5","2024/12/28",78.9],[77,"moonshot-v1-8k",null,"","","2025/03/03",78.9],[78,"Ovis1.5-Gemma2-9B",11.4,"Gemma2-9B-It","SigLIP-400M","2024/08/04",78.8],[79,"VITA-1.5",8.3,"Qwen2-7B","InternViT-300M","2025/01/01",78.6],[80,"Yi-Vision",null,"","","2024/08/03",78.6],[81,"Gemini-1.5-Flash",null,"","","2024/09/16",78.6],[82,"Aria",25.3,"Aria-MoE","SigLIP-400M","2024/12/05",78.3],[83,"InternLM-XComposer2-4KHD",7.0,"InternLM2-7B","CLIP ViT-L/14","2024/06/09",78.1],[84,"LLaVA-OneVision-7B (SI)",8.0,"Qwen2-7B","SigLIP-400M","2024/09/17",78.0],[85,"InternVL2-8B-MPO",8.0,"InternLM2.5-7B","InternViT-300M","2024/11/25",78.0],[86,"Llama-3.2-90B-Vision-Instruct",88.6,"Llama-3.1-70B","","2024/10/19",77.8],[87,"Phi-4-MultiModal",5.57,"Phi-4-Mini","SigLIP-400M","2025/03/13",77.7],[88,"Qwen2.5-VL-3B",3.75,"Qwen2.5-3B","QwenViT","2025/02/02",77.6],[89,"Ovis1.5-Llama3-8B",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/07/29",77.6],[90,"InternVL2-8B-MPO-CoT",8.0,"InternLM2.5-7B","InternViT-300M","2024/11/25",77.2],[91,"360VL-70B",70.0,"Llama-3-70B-Instruct","CLIP ViT-L/14","2024/05/25",77.2],[92,"Gemma3-12B",12.2,"Gemma3-12B","SigLIP-400M","2025/03/19",77.1],[93,"Ross-Qwen2-7B",8.2,"Qwen2-7B","CLIP ViT-L/14","2025/01/17",76.9],[94,"WeMM",7.0,"InternLM2-7B","SigLIP-400M","2024/06/09",76.8],[95,"Aquila-VL-2B",2.2,"Qwen-2.5-1.5B","SigLIP-400M","2024/10/24",76.3],[96,"GPT-4o-mini (0718, detail-high)",null,"","","2024/07/20",75.9],[97,"XinYuan-VL-2B-Instruct",2.0,"Qwen2-1.5B","QwenViT","2024/09/27",75.7],[98,"Qwen-VL-Max",null,"QwenLM","","2024/02/02",75.7],[99,"Molmo-7B-D",8.0,"Qwen2-7B","CLIP ViT-L/14","2024/10/12",75.2],[100,"Eagle-X5-34B-Chat",36.8,"Yi-34B","Clip-448
ConvNeXT-1024
SAM-1024
DET-1024
Pix2Struct-1024","2024/11/29",75.2],[101,"SAIL-VL-2B",2.1,"Qwen2.5-1.5B","InternViT-300M","2024/12/25",74.9],[102,"Ovis1.6-Llama3.2-3B",4.1,"Llama-3.2-3B","SigLIP-400M","2024/10/24",74.7],[103,"XVERSE-V-13B",13.0,"XVERSE-13B","CLIP ViT-L/14","2024/05/10",74.6],[104,"Idefics3-8B-Llama3",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/08/27",74.5],[105,"Bunny-Llama3-8B",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/07/18",74.4],[106,"GPT-4v (1106, detail-low)",null,"","","2023/12/23",74.4],[107,"Pixtral-12B",13.0,"Nemo-12B","ViT-400M","2024/09/16",74.4],[108,"Gemini-1.0-Pro",null,"","","2023/12/23",74.3],[109,"RekaFlash",null,"","","2024/05/07",74.1],[110,"InternVL2-4B",4.0,"Phi-3","InternViT-300M","2024/07/11",73.9],[111,"MiniCPM-Llama3-V2.5",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/05/27",73.8],[112,"Gemini-1.5-Pro",null,"","","2024/06/10",73.8],[113,"Qwen2-VL-2B",2.0,"Qwen2-1.5B","QwenViT","2024/09/12",73.8],[114,"LLaVA-Next-Interleave-7B-DPO",8.0,"Qwen-1.5-7B","SigLIP-400M","2024/07/29",73.7],[115,"LLaVA-InternLM2-20B (QLoRA)",20.2,"InternLM2-20B","CLIP ViT-L/14","2024/01/17",73.7],[116,"Llama-3-MixSense-v1.1",8.0,"Llama-3-8B-Instruct","Florence-2-Large-FT","2024/08/21",72.9],[117,"LLaVA-Next-Interleave-7B",8.0,"Qwen-1.5-7B","SigLIP-400M","2024/08/08",72.5],[118,"InternLM-XComposer",8.0,"InternLM-7B","EVA-G","2023/09/26",72.4],[119,"DeepSeek-VL2-Tiny",3.4,"DeepSeekMoE-3B","SigLIP-400M","2025/01/01",72.1],[120,"Parrot-7B",8.0,"Qwen2-7B","CLIP ViT-L/14","2024/08/22",71.7],[121,"LLaVA-InternLM2-7B (QLoRA)",8.1,"InternLM2-7B","CLIP ViT-L/14","2024/01/17",71.7],[122,"DeepSeek-VL-7B",7.3,"DeekSeek-7B","SAM-B
SigLIP-L","2024/03/21",71.4],[123,"InternVL2-2B",2.0,"InternLM2-1.8B","InternViT-300M","2024/07/11",71.2],[124,"InternVL2.5-2B-MPO",2.0,"InternLM2.5-1.8B","InternViT-300M-v2.5","2024/12/28",71.2],[125,"Yi-VL-34B",34.6,"Yi-34B","CLIP ViT-H/14","2024/01/25",70.7],[126,"Qwen-VL-Plus",null,"QwenLM","","2024/01/10",70.7],[127,"GLM-4v-9B",9.0,"GLM-4-9B","EVA-02-5B","2024/06/14",70.4],[128,"MiniMonkey",2.2,"InternLM2-1.8B","InternViT-300M","2024/09/26",70.3],[129,"LLaVA-Next-Llama3",8.0,"Llama-3-8B-Instruct","CLIP ViT-L/14","2024/07/29",70.1],[130,"Mini-InternVL-Chat-4B-V1.5",4.0,"Phi-3","InternViT-300M","2024/06/10",70.0],[131,"CogVLM2-19B-Chat",19.0,"Llama-3-8B-Instruct","EVA2-CLIP-E","2024/05/31",69.8],[132,"Gemma3-4B",4.3,"Gemma3-4B","SigLIP-400M","2025/03/19",69.7],[133,"Vintern-3B-beta",3.7,"Qwen-2.5-3B","InternViT-300M","2024/10/24",69.4],[134,"Ovis2-1B",1.27,"Qwen2.5-0.5B","AIMv2 Large","2025/02/18",68.7],[135,"XGen-MM-Instruct-DPO-v1.5",4.4,"Phi-3","SigLIP-400M","2024/09/06",68.7],[136,"Qwen-VL-Plus-0809",null,"","","2024/09/17",68.6],[137,"IDEFICS2-8B",8.0,"Mistral-7B","SigLIP-400M","2024/04/26",68.6],[138,"LLaVA-Next-Vicuna-13B",13.4,"Vicuna-v1.5-13B","CLIP ViT-L/14","2024/03/25",68.5],[139,"granite-vision-3.2-2b",2.98,"granite-3.1-2b-instruct","SigLip","2025/06/20",68.4],[140,"InternLM-XComposer2-1.8B",2.0,"InternLM2-1.8B","CLIP ViT-L/14","2024/06/09",68.4],[141,"InternVL3-1B",0.94,"Qwen2.5-0.5B","InternViT-300M-v2.5","2025/04/14",68.0],[142,"Mantis-8B-Idefics2",8.0,"Mistral-7B","SigLIP-400M","2024/08/08",67.9],[143,"Cambrian-8B",8.0,"Vicuna-v1.5-7B","CLIP ViT-L/14","2024/07/11",67.9],[144,"VILA1.5-13B",13.0,"Vicuna-v1.5-13B","SigLIP-400M","2024/08/25",67.7],[145,"Monkey-Chat",9.8,"Qwen-7B","ViT-BigHuge","2024/01/16",67.5],[146,"Eagle-X5-13B",15.0,"Vicuna-v1.5-13B","Clip-448
ConvNeXT-1024
SAM-1024
DET-1024
Pix2Struct-1024","2024/09/26",67.4],[147,"granite-vision-3.3-2b",2.98,"granite-3.1-2b-instruct","SigLIP2-400M","2025/06/20",67.3],[148,"Falcon2-VLM-11B",11.4,"Falcon2-11B","CLIP ViT-L/14","2024/10/30",67.2],[149,"XGen-MM-Instruct-Interleave-v1.5",4.4,"Phi-3","SigLIP-400M","2024/09/06",67.1],[150,"LLaVA-InternLM-7B (QLoRA)",7.6,"InternLM-7B","CLIP ViT-L/14","2023/12/28",66.7],[151,"Yi-VL-6B",6.6,"Yi-6B","CLIP ViT-H/14","2024/01/25",66.6],[152,"MiniCPM-V-2",2.8,"MiniCPM-2.4B","SigLIP-400M","2024/04/15",66.5],[153,"Phi-3.5-Vision",4.0,"Phi-3.5","CLIP ViT-L/14","2024/08/28",66.1],[154,"Slime-8B",8.0,"Llama-3-8B-Instruct","CLIP ViT-L/14","2024/09/14",66.0],[155,"Mini-InternVL-Chat-2B-V1.5",2.0,"InternLM2-1.8B","InternViT-300M","2024/06/10",66.0],[156,"Llama-3.2-11B-Vision-Instruct",11.0,"Llama-3.1-8B","","2024/10/07",65.8],[157,"InternVL2.5-1B-MPO",1.0,"Qwen-2.5-0.5B","InternViT-300M-v2.5","2024/12/28",65.7],[158,"Mantis-8B-siglip-llama3",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/08/08",65.3],[159,"ShareGPT4V-13B",13.4,"Vicuna-v1.5-13B","CLIP ViT-L/14","2023/12/08",65.1],[160,"GPT-4.1-nano-20250414",null,"","","2025/04/16",65.1],[161,"Cambrian-13B",13.0,"Vicuna-v1.5-13B","CLIP ViT-L/14","2024/07/29",65.0],[162,"Mantis-8B-clip-llama3",8.0,"Llama-3-8B-Instruct","CLIP ViT-L/14","2024/08/08",64.9],[163,"LLaVA-v1.5-13B (QLoRA)",13.4,"Vicuna-v1.5-13B","CLIP ViT-L/14","2023/12/28",64.7],[164,"Claude3-Sonnet",null,"","","2024/03/28",64.2],[165,"PaliGemma-3B-mix-448",3.0,"Gemma-2B","SigLIP-400M","2024/05/17",63.6],[166,"GPT-4v (1106, detail-high)",null,"","","2024/04/22",63.3],[167,"LLaVA-Next-Mistral-7B",7.6,"Mistral-7B","CLIP ViT-L/14","2024/03/25",63.3],[168,"LLaVA-LLaMA-3-8B",8.0,"Llama-3-8B-Instruct","CLIP ViT-L/14","2024/05/07",63.2],[169,"H2OVL-2B",2.2,"H2O-DANUBE2-1.8B","InternViT-300M","2024/10/31",62.9],[170,"DeepSeek-VL-1.3B",2.0,"DeekSeek-1B","SAM-B
SigLIP-L","2024/03/21",62.9],[171,"MiniCPM-V",3.0,"MiniCPM-2.4B","SigLIP-400M","2024/02/07",62.6],[172,"Eagle-X5-7B",9.0,"Vicuna-v1.5-7B","Clip-448
ConvNeXT-1024
SAM-1024
DET-1024
Pix2Struct-1024","2024/09/26",62.5],[173,"Phi-3-Vision",4.2,"Phi-3","CLIP ViT-L/14","2024/05/31",62.4],[174,"LLaVA-Next-Vicuna-7B",7.1,"Vicuna-v1.5-7B","CLIP ViT-L/14","2024/03/25",62.3],[175,"OmniLMM-12B",12.0,"Zephyr-7B-β","EVA-02-5B","2024/02/07",62.0],[176,"Janus-Pro-7B",7.42,"DeepSeek-7B","SigLIP-400M","2025/02/02",61.2],[177,"LLaVA-v1.5-7B (QLoRA)",7.2,"Vicuna-v1.5-7B","CLIP ViT-L/14","2023/12/28",61.0],[178,"InternVL2-1B",1.0,"Qwen2-0.5B","InternViT-300M","2024/07/11",61.0],[179,"ShareCaptioner",8.0,"InternLM-7B","EVA-G","2024/01/03",60.9],[180,"abab6.5s",null,"","","2024/12/11",60.9],[181,"ShareGPT4V-7B",7.2,"Vicuna-v1.5-7B","CLIP ViT-L/14","2023/12/08",60.7],[182,"Llama-3-VILA1.5-8B",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/08/25",60.4],[183,"mPLUG-Owl2",8.2,"Llama-2-7B","CLIP ViT-L/14","2023/11/10",60.3],[184,"RekaEdge",null,"","","2024/05/31",59.9],[185,"Molmo-7B-O",8.0,"Qwen2-7B","CLIP ViT-L/14","2024/10/20",59.4],[186,"Claude3-Opus",null,"","","2024/03/28",59.2],[187,"Slime-13B",13.0,"Vicuna-v1.5-13B","CLIP ViT-L/14","2024/09/14",58.7],[188,"MMAlaya",7.8,"Alaya-7B-Chat","EVA-G","2024/01/29",58.6],[189,"LLaVA-v1.5-13B",13.4,"Vicuna-v1.5-13B","CLIP ViT-L/14","2023/10/05",58.2],[190,"Claude3-Haiku",null,"","","2024/03/28",57.2],[191,"Slime-7B",7.0,"Vicuna-v1.5-7B","CLIP ViT-L/14","2024/09/14",56.7],[192,"Qwen-VL-Chat",9.6,"Qwen-7B","ViT-G/16","2023/08/24",56.3],[193,"VILA1.5-3B",3.0,"Sheared-LLaMA-2.7B","SigLIP-400M","2024/08/25",56.2],[194,"CogVLM-17B-Chat",17.0,"Vicuna-v1.5-7B","EVA2-CLIP-E","2024/01/03",55.9],[195,"LLaVA-OneVision-0.5B",1.0,"Qwen2-0.5B","SigLIP-400M","2024/09/16",55.5],[196,"SmolVLM2",2.25,"SmolLM2-1.7M","SigLIP-400M","2025/03/13",55.0],[197,"Monkey",9.8,"Qwen-7B","ViT-BigHuge","2024/01/11",54.7],[198,"Janus-1.3B",2.1,"DeepSeek-1B","SigLIP-400M","2024/10/24",52.2],[199,"SmolVLM-Instruct",2.3,"SmolLM2-1.7B","SigLIP-400M","2025/01/27",51.9],[200,"Qwen-VL-Max-0809",72.0,"Qwen2-72B","QwenViT","2024/09/12",50.3],[201,"LLaVA-OneVision-0.5B (SI)",1.0,"Qwen2-0.5B","SigLIP-400M","2024/09/17",50.2],[202,"Emu3_chat",8.49,"","","2025/01/26",49.8],[203,"SmolVLM-Instruct-DPO",2.3,"SmolLM2-1.7B","SigLIP-400M","2025/01/27",49.8],[204,"AKI-4B",4.33,"Phi-3.5","SigLIP-400M","2025/03/25",46.8],[205,"MolmoE-1B",7.2,"OLMoE-1B-7B-0924","CLIP ViT-L/14","2024/10/21",46.6],[206,"LLaVA-v1.5-7B",7.2,"Vicuna-v1.5-7B","CLIP ViT-L/14","2023/10/05",46.4],[207,"Emu2_chat",37.0,"Llama-33B","EVA-02-CLIP-E-plus","2024/01/17",45.9],[208,"H2OVL-800M",0.83,"H2O-DANUBE3-500M","InternViT-300M","2024/10/31",42.2],[209,"LLaVA-v1-7B",7.2,"Llama-7B","CLIP ViT-L/14","2023/04/17",38.7],[210,"IDEFICS-80B-Instruct",80.0,"Llama-65B","CLIP ViT-H/14","2023/07/25",38.1],[211,"SmolVLM-Synthetic",2.3,"SmolLM2-1.7B","SigLIP-400M","2025/01/27",36.9],[212,"VisualGLM",8.0,"ChatGLM 6B","EVA-CLIP","2023/05/17",35.5],[213,"SmolVLM-500M",0.51,"SmolLM2-360M","ViT-93M","2025/01/27",35.4],[214,"SmolVLM2-500M",0.51,"SmolLM2-360M","ViT-93M","2025/03/13",34.9],[215,"Mantis-8B-Fuyu",8.0,"Fuyu-8B","","2024/09/07",33.4],[216,"PandaGPT-13B",14.0,"Vicuna-13B","ImageBind ViT-H/14","2023/05/25",32.0],[217,"Moondream2",1.9,"SigLIP-400M","Phi-1.5","2024/10/20",28.7],[218,"IDEFICS-9B-Instruct",9.0,"Llama-7B","CLIP ViT-H/14","2023/07/25",25.2],[219,"InstructBLIP-7B",8.0,"Vicuna-7B","EVA-G","2023/05/11",23.9],[220,"Moondream1",1.9,"SigLIP-400M","Phi-1.5","2024/09/26",19.8],[221,"Chameleon-30B",30.0,"","","2024/07/29",17.5],[222,"SmolVLM-256M",0.26,"SmolLM2-135M","ViT-93M","2025/01/27",15.1],[223,"OpenFlamingo v2",9.0,"MPT 7B","CLIP ViT-L/14","2023/06/28",14.4],[224,"MiniGPT-4-v1-7B",8.0,"Vicuna-7B","EVA-G","2023/04/20",11.9],[225,"Qwen-VL",9.6,"Qwen-7B","ViT-G/16","2023/08/24",7.8],[226,"Chameleon-7B",7.0,"","","2024/07/29",7.1],[227,"MiniGPT-4-v2",8.0,"Llama-2-13B","EVA-G","2023/10/27",4.7],[228,"SmolVLM2-256M",0.26,"SmolLM2-135M","ViT-93M","2025/03/13",2.1],[229,"Kosmos2",1.7,"","","2024/10/19",0.6],[230,"Step-1.5V-mini",null,"","","2024/12/11",0.6]],"metadata":null},"headers":["1","2","3"],"row_count":[1,"dynamic"],"col_count":[3,"dynamic"],"datatype":["number","html","number","html","html","str","number"],"type":"pandas","latex_delimiters":[{"left":"$$","right":"$$","display":true}],"show_label":true,"height":500,"min_width":160,"interactive":false,"visible":true,"elem_classes":[],"wrap":true,"line_breaks":true,"column_widths":[],"name":"dataframe","_selectable":false},"skip_api":false,"component_class_id":"6a51bb3357f2e94c40fb8d4fbe06aa8e","key":null,"api_info":{"properties":{"headers":{"items":{"type":"string"},"title":"Headers","type":"array"},"data":{"items":{"items":{},"type":"array"},"title":"Data","type":"array"},"metadata":{"anyOf":[{"additionalProperties":{"anyOf":[{"items":{},"type":"array"},{"type":"null"}]},"type":"object"},{"type":"null"}],"default":null,"title":"Metadata"}},"required":["headers","data"],"title":"DataframeData","type":"object"},"example_inputs":{"headers":["a","b"],"data":[["foo","bar"]]}},{"id":60,"type":"textbox","props":{"value":"MMBench_TEST_CN","lines":1,"max_lines":20,"label":"MMBench_TEST_CN","show_label":true,"container":true,"min_width":160,"visible":false,"autofocus":false,"autoscroll":true,"elem_classes":[],"type":"text","rtl":false,"show_copy_button":false,"name":"textbox","_selectable":false},"skip_api":false,"component_class_id":"d0491bb0fbd427bdb2a4549c4d1ac869","key":null,"api_info":{"type":"string"},"example_inputs":"Hello!!"},{"id":61,"type":"form","props":{"scale":0,"min_width":0,"name":"form"},"skip_api":true,"component_class_id":"43cda85c6ff7a5dd8f83d29496b014ee","key":null},{"id":62,"type":"form","props":{"scale":0,"min_width":0,"name":"form"},"skip_api":true,"component_class_id":"43cda85c6ff7a5dd8f83d29496b014ee","key":null},{"id":63,"type":"tabitem","props":{"label":"📊 MMBench_TEST_EN_V11 Leaderboard","visible":true,"interactive":true,"id":6,"elem_id":"MMBench_TEST_EN_V11","name":"tab"},"skip_api":true,"component_class_id":"18f46968e2b273dc5dbda0fe78433d7e","key":null},{"id":64,"type":"checkboxgroup","props":{"choices":[["Overall","Overall"],["AR","AR"],["CP","CP"],["FP-C","FP-C"],["FP-S","FP-S"],["LR","LR"],["RR","RR"],["Action Recognition","Action Recognition"],["Attribute Comparison","Attribute Comparison"],["Attribute Recognition","Attribute Recognition"],["Celebrity Recognition","Celebrity Recognition"],["Function Reasoning","Function Reasoning"],["Future Prediction","Future Prediction"],["Identity Reasoning","Identity Reasoning"],["Image Emotion","Image Emotion"],["Image Quality","Image Quality"],["Image Scene","Image Scene"],["Image Style","Image Style"],["Image Topic","Image Topic"],["Nature Relation","Nature Relation"],["Object Localization","Object Localization"],["Ocr","Ocr"],["Physical Property Reasoning","Physical Property Reasoning"],["Physical Relation","Physical Relation"],["Social Relation","Social Relation"],["Spatial Relationship","Spatial Relationship"],["Structuralized Imagetext Understanding","Structuralized Imagetext Understanding"]],"value":["Overall"],"type":"value","label":"MMBench_TEST_EN_V11 CheckBoxes","show_label":true,"container":true,"min_width":160,"interactive":true,"visible":true,"elem_classes":[],"name":"checkboxgroup","_selectable":false},"skip_api":false,"component_class_id":"0635a5d3bf87369f1c2c1c69f8a3d0cc","key":null,"api_info":{"items":{"enum":["Overall","AR","CP","FP-C","FP-S","LR","RR","Action Recognition","Attribute Comparison","Attribute Recognition","Celebrity Recognition","Function Reasoning","Future Prediction","Identity Reasoning","Image Emotion","Image Quality","Image Scene","Image Style","Image Topic","Nature Relation","Object Localization","Ocr","Physical Property Reasoning","Physical Relation","Social Relation","Spatial Relationship","Structuralized Imagetext Understanding"],"type":"string"},"title":"Checkbox Group","type":"array"},"example_inputs":["Overall"]},{"id":65,"type":"row","props":{"variant":"default","visible":true,"equal_height":true,"show_progress":false,"name":"row"},"skip_api":true,"component_class_id":"b5cf3d15e2293fb5ccc071d7b8d69f64","key":null},{"id":66,"type":"textbox","props":{"value":"Input the Model Name (fuzzy, case insensitive)","lines":1,"max_lines":20,"label":"Model Name","show_label":true,"container":true,"min_width":160,"interactive":true,"visible":true,"autofocus":false,"autoscroll":true,"elem_classes":[],"type":"text","rtl":false,"show_copy_button":false,"name":"textbox","_selectable":false},"skip_api":false,"component_class_id":"d0491bb0fbd427bdb2a4549c4d1ac869","key":null,"api_info":{"type":"string"},"example_inputs":"Hello!!"},{"id":67,"type":"checkboxgroup","props":{"choices":[["<4B","<4B"],["4B-10B","4B-10B"],["10B-20B","10B-20B"],["20B-40B","20B-40B"],[">40B",">40B"],["Unknown","Unknown"]],"value":["<4B","4B-10B","10B-20B","20B-40B",">40B","Unknown"],"type":"value","label":"Model Size","show_label":true,"container":true,"min_width":160,"interactive":true,"visible":true,"elem_classes":[],"name":"checkboxgroup","_selectable":false},"skip_api":false,"component_class_id":"0635a5d3bf87369f1c2c1c69f8a3d0cc","key":null,"api_info":{"items":{"enum":["<4B","4B-10B","10B-20B","20B-40B",">40B","Unknown"],"type":"string"},"title":"Checkbox Group","type":"array"},"example_inputs":["<4B"]},{"id":68,"type":"checkboxgroup","props":{"choices":[["API","API"],["OpenSource","OpenSource"]],"value":["API","OpenSource"],"type":"value","label":"Model Type","show_label":true,"container":true,"min_width":160,"interactive":true,"visible":true,"elem_classes":[],"name":"checkboxgroup","_selectable":false},"skip_api":false,"component_class_id":"0635a5d3bf87369f1c2c1c69f8a3d0cc","key":null,"api_info":{"items":{"enum":["API","OpenSource"],"type":"string"},"title":"Checkbox Group","type":"array"},"example_inputs":["API"]},{"id":69,"type":"form","props":{"scale":3,"min_width":480,"name":"form"},"skip_api":true,"component_class_id":"43cda85c6ff7a5dd8f83d29496b014ee","key":null},{"id":70,"type":"dataframe","props":{"value":{"headers":["Rank","Method","Param (B)","Language Model","Vision Model","Eval Date","Overall"],"data":[[1,"Gemini-2.5-Pro",null,"","","2025/04/07",88.5],[2,"JT-VL-Chat-V3.0",null,"","","2025/08/04",88.5],[3,"SenseNova-V6-Pro",null,"","","2025/05/05",88.4],[4,"Qwen2.5-VL-72B",73.4,"Qwen2.5-72B","QwenViT","2025/02/02",88.3],[5,"CongRong-v2.0",null,"","","2025/05/20",87.9],[6,"InternVL2.5-78B-MPO",78.0,"Qwen-2.5-72B","InternViT-6B-v2.5","2024/12/29",87.9],[7,"GLM-4v-Plus-20250111",null,"","","2025/01/25",87.8],[8,"BailingMM-Pro-0120",81.0,"Bailing-80B","SigLIP-400M","2025/01/25",87.7],[9,"Step-1o",null,"","","2025/01/13",87.6],[10,"SenseNova-V6-5-Pro",null,"","","2025/09/03",87.6],[11,"InternVL3-78B",78.4,"Qwen2.5-72B","InternViT-6B-v2.5","2025/04/14",87.5],[12,"InternVL2.5-78B",78.0,"Qwen-2.5-72B","InternViT-6B-v2.5","2024/12/10",87.3],[13,"InternVL3-38B",38.4,"Qwen2.5-32B","InternViT-6B-v2.5","2025/04/14",87.0],[14,"GPT-4.1-20250414",null,"","","2025/04/16",86.9],[15,"GPT-5-20250807",null,"","","2025/08/14",86.8],[16,"ChatGPT-4o-latest",null,"","","2025/04/07",86.8],[17,"Ovis2-34B",34.9,"Qwen2.5-32B","AIMv2-1B","2025/02/18",86.6],[18,"BlueLM-2.6-3B",3.0,"","","2025/09/17",86.4],[19,"GPT-5-mini-20250807",null,"","","2025/08/14",86.2],[20,"Qwen2-VL-72B",73.4,"Qwen2-72B","QwenViT","2024/10/28",86.1],[21,"SenseNova",null,"","","2024/12/12",86.1],[22,"Qwen-VL-Max-0809",72.0,"Qwen2-72B","QwenViT","2024/09/12",86.0],[23,"Ovis2-16B",16.2,"Qwen2.5-14B","AIMv2 Huge","2025/02/18",85.8],[24,"Ola-7b",8.88,"Qwen2.5-7B","Oryx-ViT","2025/02/05",85.5],[25,"InternVL2-Llama3-76B",76.0,"Llama-3-70B-Instruct","InternViT-6B","2024/07/19",85.5],[26,"InternVL2.5-38B-MPO",38.0,"Qwen-2.5-32B","InternViT-6B-v2.5","2024/12/28",85.4],[27,"InternVL2.5-38B",38.0,"Qwen-2.5-32B","InternViT-6B-v2.5","2024/12/10",85.3],[28,"InternVL2-40B",40.0,"Nous-Hermes-2-Yi-34B","InternViT-6B","2024/07/11",85.1],[29,"LLaVA-OneVision-72B",73.0,"Qwen2-72B","SigLIP-400M","2024/09/19",85.0],[30,"GPT-4o (1120, detail-high)",null,"","","2024/12/02",84.8],[31,"Taiyi",null,"","","2024/12/11",84.7],[32,"Qwen2.5-VL-32B",33.5,"Qwen2.5-32B","QwenViT","2025/07/02",84.7],[33,"VARCO-VISION-2.0-14B",15.2,"Qwen3-14B","SigLIP-400M","2025/08/04",84.4],[34,"Gemini-1.5-Pro-002",null,"","","2024/12/02",84.4],[35,"InternVL2.5-26B",26.0,"InternLM2.5-20B","InternViT-6B-v2.5","2024/12/10",84.4],[36,"InternVL2.5-26B-MPO",26.0,"InternLM2.5-20B","InternViT-6B-v2.5","2024/12/28",84.3],[37,"SAIL-VL-1.6-8B",8.33,"Qwen2.5-7B","AIMv2 Huge","2025/04/24",84.3],[38,"BailingMM-Lite-1203",21.0,"Bailing-20B","SigLIP-400M","2024/12/08",83.9],[39,"HunYuan-Standard-Vision",null,"","","2025/01/15",83.9],[40,"InternVL3-14B",15.1,"Qwen2.5-14B","InternViT-300M-v2.5","2025/04/14",83.9],[41,"Ovis2-8B",8.94,"Qwen2.5-7B","AIMv2 Huge","2025/02/18",83.8],[42,"R-4B",4.82,"Qwen3-4B","SigLip-400M","2025/08/11",83.7],[43,"GPT-4.5",null,"","","2025/03/26",83.5],[44,"abab7-preview",null,"","","2024/12/11",83.4],[45,"grok-2-vision-1212",null,"","","2025/03/03",83.3],[46,"LLaVA-OneVision-72B (SI)",73.0,"Qwen2-72B","SigLIP-400M","2024/09/19",83.3],[47,"GPT-4.1-mini-20250414",null,"","","2025/04/16",83.2],[48,"InternVL2.5-8B",8.0,"InternLM2.5-7B","InternViT-300M-v2.5","2024/12/10",83.2],[49,"GPT-4o (0513, detail-low)",null,"","","2024/05/15",83.1],[50,"BlueLM-V-3B",3.0,"BlueLM-3B","SigLIP-400M","2024/10/30",83.1],[51,"GPT-4o (0513, detail-high)",null,"","","2024/05/31",83.0],[52,"Ovis1.6-Gemma2-27B",28.9,"Gemma2-27B","SigLIP-400M","2024/11/29",82.8],[53,"SAIL-VL-1.5-8B",7.95,"Qwen2.5-7B","InternViT-300B","2025/04/23",82.5],[54,"WeThink-Qwen2.5VL-7B",8.29,"Qwen2.5-7B","QwenViT","2025/05/26",82.5],[55,"Gemini-2.0-Pro",null,"","","2025/02/27",82.4],[56,"InternVL2.5-8B-MPO",8.0,"InternLM2.5-7B","InternViT-300M-v2.5","2024/12/28",82.4],[57,"Qwen2.5-VL-7B",8.29,"Qwen2.5-7B","QwenViT","2025/02/02",82.4],[58,"InternVL3-8B",7.94,"Qwen2.5-7B","InternViT-300M-v2.5","2025/04/14",82.3],[59,"DeepSeek-VL2",27.5,"DeepSeekMoE-27B","SigLIP-400M","2025/01/01",82.3],[60,"VARCO-VISION-14B",15.2,"Qwen2.5-14B","SigLIP-400M","2025/01/02",82.3],[61,"RBDash-v1.5",79.0,"Qwen2-72B","CLIP ViT-L/14
InternViT-6B","2024/11/17",82.3],[62,"valley2_dpo",8.88,"Qwen2.5-7B","SigLIP-400M","2025/05/30",82.1],[63,"bailingMM-mini",17.0,"bailing-mini","bailingMM-encoder-1B
InternViT-6B","2024/10/24",82.1],[64,"InternVL3-9B",9.14,"InternLM3-8B","InternViT-300M-v2.5","2025/04/14",81.9],[65,"MUG-U-7B",7.0,"","","2025/03/19",81.9],[66,"Qwen2-VL-7B",8.0,"Qwen2-7B","QwenViT","2024/09/12",81.8],[67,"GPT-4o (0806, detail-high)",null,"","","2024/08/08",81.8],[68,"Ovis2-4B",4.62,"Qwen2.5-3B","AIMv2 Huge","2025/02/18",81.8],[69,"TeleMM",null,"","","2024/12/31",81.6],[70,"Gemini-1.5-Flash-002",null,"","","2024/12/02",81.6],[71,"InternVL2-26B",26.0,"InternLM2-20B","InternViT-6B","2024/07/11",81.5],[72,"MiMo-VL-7B",8.31,"Mimo-7B","Qwen2.5-ViT","2025/07/02",81.5],[73,"Ovis1.6-Gemma2-9B",10.2,"Gemma2-9B-It","SigLIP-400M","2024/09/19",81.5],[74,"Valley-Eagle",8.9,"Qwen2.5-7B","Qwen-ViT
SigLIP-400M","2024/12/29",81.4],[75,"MiniCPM-o-2.6",8.67,"Qwen2.5-7B","SigLIP-400M","2025/01/21",81.3],[76,"POINTS1.5-Qwen2.5-7B",8.3,"Qwen-2.5-7B","NaViT","2024/12/06",81.2],[77,"Ristretto-3B",3.84,"Qwen2.5-3B","SigLIP-400M","2025/04/01",81.2],[78,"valley2",8.88,"Qwen2.5-7B","SigLIP-400M","2025/05/30",81.2],[79,"Qwen-VL-Plus-0809",null,"","","2024/09/17",81.1],[80,"LLaVA-OneVision-7B",8.0,"Qwen2-7B","SigLIP-400M","2024/09/16",80.9],[81,"Claude3.5-Sonnet-20241022",null,"","","2024/11/06",80.9],[82,"Kimi-VL-A3B-Instruct",16.4,"Moonlight-16B-A3B","MoonViT","2025/04/14",80.9],[83,"CongRong",null,"","","2024/06/26",80.9],[84,"DeepSeek-VL2-Small",16.1,"DeepSeekMoE-16B","SigLIP-400M","2025/01/01",80.7],[85,"MMAlaya2",26.0,"InternLM2-20B","InternViT-6B","2024/08/27",80.6],[86,"Kimi-VL-A3B-Thinking-2506",16.4,"Moonlight-16B-A3B","MoonViT","2025/07/02",80.4],[87,"Step-1.5V",null,"Step-1.5","stepencoder","2024/10/11",80.4],[88,"InternVL-Chat-V1.5",26.0,"InternLM2-20B","InternViT-6B","2024/04/17",80.3],[89,"InternLM-XComposer2.5",8.0,"InternLM2-7B","CLIP ViT-L/14","2024/07/11",80.1],[90,"GPT-4v (0409, detail-high)",null,"","","2024/05/15",80.0],[91,"VILA1.5-40B",40.0,"Yi-34B","InternViT-6B","2024/08/25",79.9],[92,"Step-1.5V-mini",null,"","","2024/12/11",79.8],[93,"Claude3.7-Sonnet",null,"","","2025/02/27",79.8],[94,"GLM-4v-Plus",null,"","","2024/12/11",79.7],[95,"OmChat-v2.0-13B",13.0,"Qwen2-7B","InternViT-6B","2024/08/22",79.6],[96,"Gemma3-27B",27.4,"Gemma3-27B","SigLIP-400M","2025/03/19",79.6],[97,"Llama-3.2-90B-Vision-Instruct",88.6,"Llama-3.1-70B","","2024/10/19",79.5],[98,"InternVL2-8B",8.0,"InternLM2.5-7B","InternViT-300M","2024/07/11",79.5],[99,"Phi-4-MultiModal",5.57,"Phi-4-Mini","SigLIP-400M","2025/03/13",79.5],[100,"Molmo-72B",73.3,"Qwen2-72B","CLIP ViT-L/14","2024/10/28",79.4],[101,"SAIL-VL-1.5-2B",2.47,"Qwen2.5-1.5B","AIMv2 Huge","2025/04/23",79.4],[102,"GPT-4v (0409, detail-low)",null,"","","2024/05/15",79.3],[103,"GLM-4v",null,"","","2024/05/20",79.2],[104,"InternVL3-2B",2.09,"Qwen2.5-1.5B","InternViT-300M-v2.5","2025/04/14",79.0],[105,"MiniCPM-V-2.6",8.0,"Qwen2-7B","SigLIP-400M","2024/08/08",79.0],[106,"POINTS-Yi-1.5-9B",9.5,"Yi-1.5-9B","CLIP ViT-L/14","2024/10/11",79.0],[107,"NVLM-D-72B",79.4,"Qwen2-72B","InternViT-6B","2024/10/19",79.0],[108,"POINTS-Qwen2.5-7B",8.3,"Qwen-2.5-7B","CLIP ViT-L/14","2024/10/19",79.0],[109,"GPT-5-nano-20250807",null,"","","2025/08/14",78.9],[110,"InternVL2.5-4B",4.0,"Qwen-2.5-3B","InternViT-300M-v2.5","2024/12/10",78.8],[111,"InternVL2.5-4B-MPO",4.0,"Qwen-2.5-3B","InternViT-300M-v2.5","2024/12/28",78.6],[112,"QTuneVL1.5-2B",2.09,"Qwen2.5-1.5B","InternViT-300M-v2.5","2025/08/11",78.6],[113,"LLaVA-Next-Yi-34B",34.8,"Yi-34B","CLIP ViT-L/14","2024/03/25",78.5],[114,"Ovis1.5-Gemma2-9B",11.4,"Gemma2-9B-It","SigLIP-400M","2024/08/04",78.4],[115,"Ovis-U1-3B",3.64,"Qwen3-1.7B","aimv2-large-path14-448","2025/07/20",78.3],[116,"Cambrian-34B",34.0,"Nous-Hermes-2-Yi-34B","CLIP ViT-L/14","2024/07/18",78.3],[117,"Aria",25.3,"Aria-MoE","SigLIP-400M","2024/12/05",78.2],[118,"Ovis1.5-Llama3-8B",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/07/29",78.1],[119,"InternLM-XComposer2",7.0,"InternLM2-7B","CLIP ViT-L/14","2024/01/26",78.1],[120,"WeMM",7.0,"InternLM2-7B","SigLIP-400M","2024/06/09",77.8],[121,"Eagle-X5-34B-Chat",36.8,"Yi-34B","Clip-448
ConvNeXT-1024
SAM-1024
DET-1024
Pix2Struct-1024","2024/11/29",77.8],[122,"Claude3.5-Sonnet",null,"","","2024/06/24",77.7],[123,"LLaVA-OneVision-7B (SI)",8.0,"Qwen2-7B","SigLIP-400M","2024/09/17",77.7],[124,"VITA-1.5",8.3,"Qwen2-7B","InternViT-300M","2025/01/01",77.5],[125,"QTuneVL1.5-3B",3.75,"Qwen2.5-3B","QwenViT","2025/08/11",77.5],[126,"Flash-VL-2B-Dynamic-ISS",2.53,"Qwen-2.5-1.5B-Instruct","SigLIP2-400M-512","2025/05/30",77.1],[127,"Ovis2-2B",2.46,"Qwen2.5-1.5B","AIMv2 Large","2025/02/18",77.1],[128,"GPT-4o-mini (0718, detail-high)",null,"","","2024/07/20",77.1],[129,"Gemini-1.5-Flash",null,"","","2024/09/16",77.1],[130,"Ross-Qwen2-7B",8.2,"Qwen2-7B","CLIP ViT-L/14","2025/01/17",77.1],[131,"InternLM-XComposer2-4KHD",7.0,"InternLM2-7B","CLIP ViT-L/14","2024/06/09",77.0],[132,"Qwen2.5-VL-3B",3.75,"Qwen2.5-3B","QwenViT","2025/02/02",77.0],[133,"moonshot-v1-8k",null,"","","2025/03/03",76.8],[134,"Long-VITA-16K",14.0,"Qwen2.5-14B","InternViT-300M","2025/06/13",76.8],[135,"Yi-Vision",null,"","","2024/08/03",76.6],[136,"LLaVA-Next-Qwen-32B",33.0,"Qwen-1.5-32B","SigLIP-400M","2024/08/08",76.5],[137,"InternVL2-8B-MPO",8.0,"InternLM2.5-7B","InternViT-300M","2024/11/25",76.5],[138,"Aquila-VL-2B",2.2,"Qwen-2.5-1.5B","SigLIP-400M","2024/10/24",76.3],[139,"Ovis1.6-Llama3.2-3B",4.1,"Llama-3.2-3B","SigLIP-400M","2024/10/24",76.2],[140,"XinYuan-VL-2B-Instruct",2.0,"Qwen2-1.5B","QwenViT","2024/09/27",76.2],[141,"360VL-70B",70.0,"Llama-3-70B-Instruct","CLIP ViT-L/14","2024/05/25",76.0],[142,"granite-vision-3.2-2b",2.98,"granite-3.1-2b-instruct","SigLip","2025/06/20",75.8],[143,"InternVL2-4B",4.0,"Phi-3","InternViT-300M","2024/07/11",75.8],[144,"InternVL2-8B-MPO-CoT",8.0,"InternLM2.5-7B","InternViT-300M","2024/11/25",75.6],[145,"SAIL-VL-2B",2.1,"Qwen2.5-1.5B","InternViT-300M","2024/12/25",75.5],[146,"Qwen-VL-Max",null,"QwenLM","","2024/02/02",75.4],[147,"GPT-4v (1106, detail-low)",null,"","","2023/12/23",75.3],[148,"XGen-MM-Instruct-Interleave-v1.5",4.4,"Phi-3","SigLIP-400M","2024/09/06",75.3],[149,"Pixtral-12B",13.0,"Nemo-12B","ViT-400M","2024/09/16",75.3],[150,"XGen-MM-Instruct-DPO-v1.5",4.4,"Phi-3","SigLIP-400M","2024/09/06",75.2],[151,"Idefics3-8B-Llama3",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/08/27",75.0],[152,"Gemma3-12B",12.2,"Gemma3-12B","SigLIP-400M","2025/03/19",74.9],[153,"VARCO-VISION-2.0-1.7B",2.12,"Qwen3-1.7B","SigLIP-400M","2025/08/04",74.9],[154,"Gemini-1.5-Pro",null,"","","2024/06/10",74.6],[155,"RekaFlash",null,"","","2024/05/07",74.5],[156,"LLaVA-CoT",11.0,"","","2025/01/05",74.4],[157,"Bunny-Llama3-8B",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/07/18",74.1],[158,"granite-vision-3.1-2b-preview",2.98,"granite-3.1-2b-instruct","SigLip","2025/06/20",74.1],[159,"MiniCPM-Llama3-V2.5",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/05/27",74.0],[160,"Llama-3-MixSense-v1.1",8.0,"Llama-3-8B-Instruct","Florence-2-Large-FT","2024/08/21",73.7],[161,"BlueLM-2.5-3B",2.9,"BlueLM-base-3B","Siglip2-So400M","2025/07/16",73.7],[162,"Mantis-8B-Idefics2",8.0,"Mistral-7B","SigLIP-400M","2024/08/08",73.6],[163,"Qwen2-VL-2B",2.0,"Qwen2-1.5B","QwenViT","2024/09/12",73.2],[164,"LLaVA-Next-Interleave-7B",8.0,"Qwen-1.5-7B","SigLIP-400M","2024/08/08",72.8],[165,"IDEFICS2-8B",8.0,"Mistral-7B","SigLIP-400M","2024/04/26",72.7],[166,"CogVLM2-19B-Chat",19.0,"Llama-3-8B-Instruct","EVA2-CLIP-E","2024/05/31",72.7],[167,"Mini-InternVL-Chat-4B-V1.5",4.0,"Phi-3","InternViT-300M","2024/06/10",72.6],[168,"QTuneVL1-2B",2.21,"InternLM2.5-1.8B","InternViT-300M-v2.5","2025/05/05",72.6],[169,"Kimi-VL-A3B-Thinking",16.4,"Moonlight-16B-A3B","MoonViT","2025/04/23",72.5],[170,"InternVL2.5-2B",2.0,"InternLM2.5-1.8B","InternViT-300M-v2.5","2024/12/10",72.4],[171,"LLaVA-InternLM2-20B (QLoRA)",20.2,"InternLM2-20B","CLIP ViT-L/14","2024/01/17",72.3],[172,"Phi-3.5-Vision",4.0,"Phi-3.5","CLIP ViT-L/14","2024/08/28",72.1],[173,"LLaVA-Next-Llama3",8.0,"Llama-3-8B-Instruct","CLIP ViT-L/14","2024/07/29",72.1],[174,"XVERSE-V-13B",13.0,"XVERSE-13B","CLIP ViT-L/14","2024/05/10",72.1],[175,"InternVL2.5-2B-MPO",2.0,"InternLM2.5-1.8B","InternViT-300M-v2.5","2024/12/28",71.9],[176,"LLaVA-InternLM2-7B (QLoRA)",8.1,"InternLM2-7B","CLIP ViT-L/14","2024/01/17",71.9],[177,"VILA1.5-13B",13.0,"Vicuna-v1.5-13B","SigLIP-400M","2024/08/25",71.8],[178,"DeepSeek-VL-7B",7.3,"DeekSeek-7B","SAM-B
SigLIP-L","2024/03/21",71.7],[179,"LLaVA-Next-Interleave-7B-DPO",8.0,"Qwen-1.5-7B","SigLIP-400M","2024/07/29",71.7],[180,"DeepSeek-VL2-Tiny",3.4,"DeepSeekMoE-3B","SigLIP-400M","2025/01/01",71.7],[181,"Cambrian-8B",8.0,"Vicuna-v1.5-7B","CLIP ViT-L/14","2024/07/11",71.6],[182,"Cambrian-13B",13.0,"Vicuna-v1.5-13B","CLIP ViT-L/14","2024/07/29",71.4],[183,"granite-vision-3.3-2b",2.98,"granite-3.1-2b-instruct","SigLIP2-400M","2025/06/20",71.3],[184,"VITA",47.0,"Mixtral-8x7B","InternViT-300M","2025/01/20",70.8],[185,"Phi-3-Vision",4.2,"Phi-3","CLIP ViT-L/14","2024/05/31",70.5],[186,"InternLM-XComposer2-1.8B",2.0,"InternLM2-1.8B","CLIP ViT-L/14","2024/06/09",70.4],[187,"Gemini-2.0-Flash",null,"","","2025/01/02",70.4],[188,"Molmo-7B-D",8.0,"Qwen2-7B","CLIP ViT-L/14","2024/10/12",70.3],[189,"Gemini-1.0-Pro",null,"","","2023/12/23",70.2],[190,"InternVL2-2B",2.0,"InternLM2-1.8B","InternViT-300M","2024/07/11",70.2],[191,"Ovis2-1B",1.27,"Qwen2.5-0.5B","AIMv2 Large","2025/02/18",70.1],[192,"Eagle-X5-13B",15.0,"Vicuna-v1.5-13B","Clip-448
ConvNeXT-1024
SAM-1024
DET-1024
Pix2Struct-1024","2024/09/26",70.0],[193,"InternVL3-1B",0.94,"Qwen2.5-0.5B","InternViT-300M-v2.5","2025/04/14",69.9],[194,"Monkey-Chat",9.8,"Qwen-7B","ViT-BigHuge","2024/01/16",69.6],[195,"MiniMonkey",2.2,"InternLM2-1.8B","InternViT-300M","2024/09/26",69.6],[196,"OmniLMM-12B",12.0,"Zephyr-7B-β","EVA-02-5B","2024/02/07",69.2],[197,"Molmo-7B-O",8.0,"Qwen2-7B","CLIP ViT-L/14","2024/10/20",69.1],[198,"SmolVLM2",2.25,"SmolLM2-1.7M","SigLIP-400M","2025/03/13",69.1],[199,"Slime-8B",8.0,"Llama-3-8B-Instruct","CLIP ViT-L/14","2024/09/14",69.0],[200,"Parrot-7B",8.0,"Qwen2-7B","CLIP ViT-L/14","2024/08/22",68.8],[201,"Yi-VL-34B",34.6,"Yi-34B","CLIP ViT-H/14","2024/01/25",68.7],[202,"H2OVL-2B",2.2,"H2O-DANUBE2-1.8B","InternViT-300M","2024/10/31",68.7],[203,"Falcon2-VLM-11B",11.4,"Falcon2-11B","CLIP ViT-L/14","2024/10/30",68.7],[204,"GLM-4v-9B",9.0,"GLM-4-9B","EVA-02-5B","2024/06/14",68.7],[205,"LLaVA-LLaMA-3-8B",8.0,"Llama-3-8B-Instruct","CLIP ViT-L/14","2024/05/07",68.5],[206,"PaliGemma-3B-mix-448",3.0,"Gemma-2B","SigLIP-400M","2024/05/17",68.4],[207,"InternVL2.5-1B",1.0,"Qwen-2.5-0.5B","InternViT-300M-v2.5","2024/12/10",68.2],[208,"TransCore-M",13.4,"PCITransGPT-13B","CLIP ViT-L/14","2024/04/16",67.7],[209,"Moondream2",1.9,"SigLIP-400M","Phi-1.5","2024/10/20",67.7],[210,"Mini-InternVL-Chat-2B-V1.5",2.0,"InternLM2-1.8B","InternViT-300M","2024/06/10",67.5],[211,"Llama-3.2-11B-Vision-Instruct",11.0,"Llama-3.1-8B","","2024/10/07",67.5],[212,"ShareGPT4V-13B",13.4,"Vicuna-v1.5-13B","CLIP ViT-L/14","2023/12/08",67.5],[213,"Eagle-X5-7B",9.0,"Vicuna-v1.5-7B","Clip-448
ConvNeXT-1024
SAM-1024
DET-1024
Pix2Struct-1024","2024/09/26",67.4],[214,"LLaVA-Next-Vicuna-13B",13.4,"Vicuna-v1.5-13B","CLIP ViT-L/14","2024/03/25",67.3],[215,"InternVL2.5-1B-MPO",1.0,"Qwen-2.5-0.5B","InternViT-300M-v2.5","2024/12/28",67.2],[216,"Vintern-3B-beta",3.7,"Qwen-2.5-3B","InternViT-300M","2024/10/24",67.0],[217,"LLaVA-v1.5-13B (QLoRA)",13.4,"Vicuna-v1.5-13B","CLIP ViT-L/14","2023/12/28",67.0],[218,"MiniCPM-V-2",2.8,"MiniCPM-2.4B","SigLIP-400M","2024/04/15",67.0],[219,"LLaVA-Next-Vicuna-7B",7.1,"Vicuna-v1.5-7B","CLIP ViT-L/14","2024/03/25",66.5],[220,"LLaVA-Next-Mistral-7B",7.6,"Mistral-7B","CLIP ViT-L/14","2024/03/25",66.5],[221,"Mantis-8B-siglip-llama3",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/08/08",66.1],[222,"Gemma3-4B",4.3,"Gemma3-4B","SigLIP-400M","2025/03/19",66.1],[223,"LLaVA-InternLM-7B (QLoRA)",7.6,"InternLM-7B","CLIP ViT-L/14","2023/12/28",66.0],[224,"AKI-4B",4.33,"Phi-3.5","SigLIP-400M","2025/03/25",65.9],[225,"LLaVA-v1.5-13B",13.4,"Vicuna-v1.5-13B","CLIP ViT-L/14","2023/10/05",65.8],[226,"DeepSeek-VL-1.3B",2.0,"DeekSeek-1B","SAM-B
SigLIP-L","2024/03/21",65.6],[227,"GPT-4v (1106, detail-high)",null,"","","2024/04/22",65.4],[228,"HawkVL-2B",2.44,"Qwen2.5-1.5B","QwenViT","2025/06/16",65.3],[229,"Yi-VL-6B",6.6,"Yi-6B","CLIP ViT-H/14","2024/01/25",65.2],[230,"LLaVA-v1.5-7B (QLoRA)",7.2,"Vicuna-v1.5-7B","CLIP ViT-L/14","2023/12/28",64.7],[231,"ShareGPT4V-7B",7.2,"Vicuna-v1.5-7B","CLIP ViT-L/14","2023/12/08",64.6],[232,"GPT-4.1-nano-20250414",null,"","","2025/04/16",64.4],[233,"SmolVLM-Instruct",2.3,"SmolLM2-1.7B","SigLIP-400M","2025/01/27",64.4],[234,"Qwen-VL-Plus",null,"QwenLM","","2024/01/10",64.3],[235,"Claude3-Sonnet",null,"","","2024/03/28",64.2],[236,"ShareCaptioner",8.0,"InternLM-7B","EVA-G","2024/01/03",63.9],[237,"Mantis-8B-clip-llama3",8.0,"Llama-3-8B-Instruct","CLIP ViT-L/14","2024/08/08",63.8],[238,"CogVLM-17B-Chat",17.0,"Vicuna-v1.5-7B","EVA2-CLIP-E","2024/01/03",63.6],[239,"RekaEdge",null,"","","2024/05/31",63.6],[240,"mPLUG-Owl2",8.2,"Llama-2-7B","CLIP ViT-L/14","2023/11/10",63.5],[241,"VILA1.5-3B",3.0,"Sheared-LLaMA-2.7B","SigLIP-400M","2024/08/25",63.1],[242,"Slime-7B",7.0,"Vicuna-v1.5-7B","CLIP ViT-L/14","2024/09/14",63.1],[243,"Slime-13B",13.0,"Vicuna-v1.5-13B","CLIP ViT-L/14","2024/09/14",62.9],[244,"SmolVLM-Instruct-DPO",2.3,"SmolLM2-1.7B","SigLIP-400M","2025/01/27",62.6],[245,"LLaVA-v1.5-7B",7.2,"Vicuna-v1.5-7B","CLIP ViT-L/14","2023/10/05",62.3],[246,"InternVL2-1B",1.0,"Qwen2-0.5B","InternViT-300M","2024/07/11",61.6],[247,"MiniCPM-V",3.0,"MiniCPM-2.4B","SigLIP-400M","2024/02/07",61.4],[248,"Emu2_chat",37.0,"Llama-33B","EVA-02-CLIP-E-plus","2024/01/17",61.3],[249,"Qwen-VL-Chat",9.6,"Qwen-7B","ViT-G/16","2023/08/24",60.8],[250,"MolmoE-1B",7.2,"OLMoE-1B-7B-0924","CLIP ViT-L/14","2024/10/21",60.5],[251,"Claude3-Opus",null,"","","2024/03/28",60.1],[252,"Janus-Pro-7B",7.42,"DeepSeek-7B","SigLIP-400M","2025/02/02",60.0],[253,"Moondream1",1.9,"SigLIP-400M","Phi-1.5","2024/09/26",59.6],[254,"LLaVA-OneVision-0.5B",1.0,"Qwen2-0.5B","SigLIP-400M","2024/09/16",59.6],[255,"Emu3_chat",8.49,"","","2025/01/26",59.3],[256,"Claude3-Haiku",null,"","","2024/03/28",58.0],[257,"abab6.5s",null,"","","2024/12/11",57.9],[258,"Llama-3-VILA1.5-8B",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/08/25",57.9],[259,"Monkey",9.8,"Qwen-7B","ViT-BigHuge","2024/01/11",57.4],[260,"MMAlaya",7.8,"Alaya-7B-Chat","EVA-G","2024/01/29",55.7],[261,"Vintern-1B-v2",3.7,"Qwen2-0.5B","InternViT-300M","2024/11/16",54.6],[262,"H2OVL-800M",0.83,"H2O-DANUBE3-500M","InternViT-300M","2024/10/31",53.9],[263,"LLaVA-OneVision-0.5B (SI)",1.0,"Qwen2-0.5B","SigLIP-400M","2024/09/17",53.0],[264,"SmolVLM-Synthetic",2.3,"SmolLM2-1.7B","SigLIP-400M","2025/01/27",51.0],[265,"Janus-1.3B",2.1,"DeepSeek-1B","SigLIP-400M","2024/10/24",50.2],[266,"SmolVLM-500M",0.51,"SmolLM2-360M","ViT-93M","2025/01/27",50.0],[267,"SmolVLM2-500M",0.51,"SmolLM2-360M","ViT-93M","2025/03/13",49.8],[268,"Mantis-8B-Fuyu",8.0,"Fuyu-8B","","2024/09/07",44.1],[269,"Qwen-VL",9.6,"Qwen-7B","ViT-G/16","2023/08/24",41.6],[270,"LLaVA-v1-7B",7.2,"Llama-7B","CLIP ViT-L/14","2023/04/17",41.6],[271,"PandaGPT-13B",14.0,"Vicuna-13B","ImageBind ViT-H/14","2023/05/25",39.7],[272,"SmolVLM-256M",0.26,"SmolLM2-135M","ViT-93M","2025/01/27",39.4],[273,"InstructBLIP-7B",8.0,"Vicuna-7B","EVA-G","2023/05/11",38.4],[274,"Chameleon-30B",30.0,"","","2024/07/29",37.6],[275,"VisualGLM",8.0,"ChatGLM 6B","EVA-CLIP","2023/05/17",36.7],[276,"IDEFICS-9B-Instruct",9.0,"Llama-7B","CLIP ViT-H/14","2023/07/25",35.2],[277,"MiniGPT-4-v1-7B",8.0,"Vicuna-7B","EVA-G","2023/04/20",30.9],[278,"Chameleon-7B",7.0,"","","2024/07/29",19.9],[279,"IDEFICS-80B-Instruct",80.0,"Llama-65B","CLIP ViT-H/14","2023/07/25",11.3],[280,"SmolVLM2-256M",0.26,"SmolLM2-135M","ViT-93M","2025/03/13",11.0],[281,"InternLM-XComposer",8.0,"InternLM-7B","EVA-G","2023/09/26",6.4],[282,"MiniGPT-4-v2",8.0,"Llama-2-13B","EVA-G","2023/10/27",5.0],[283,"OpenFlamingo v2",9.0,"MPT 7B","CLIP ViT-L/14","2023/06/28",2.4],[284,"Kosmos2",1.7,"","","2024/10/19",1.2]],"metadata":null},"headers":["1","2","3"],"row_count":[1,"dynamic"],"col_count":[3,"dynamic"],"datatype":["number","html","number","html","html","str","number"],"type":"pandas","latex_delimiters":[{"left":"$$","right":"$$","display":true}],"show_label":true,"height":500,"min_width":160,"interactive":false,"visible":true,"elem_classes":[],"wrap":true,"line_breaks":true,"column_widths":[],"name":"dataframe","_selectable":false},"skip_api":false,"component_class_id":"6a51bb3357f2e94c40fb8d4fbe06aa8e","key":null,"api_info":{"properties":{"headers":{"items":{"type":"string"},"title":"Headers","type":"array"},"data":{"items":{"items":{},"type":"array"},"title":"Data","type":"array"},"metadata":{"anyOf":[{"additionalProperties":{"anyOf":[{"items":{},"type":"array"},{"type":"null"}]},"type":"object"},{"type":"null"}],"default":null,"title":"Metadata"}},"required":["headers","data"],"title":"DataframeData","type":"object"},"example_inputs":{"headers":["a","b"],"data":[["foo","bar"]]}},{"id":71,"type":"textbox","props":{"value":"MMBench_TEST_EN_V11","lines":1,"max_lines":20,"label":"MMBench_TEST_EN_V11","show_label":true,"container":true,"min_width":160,"visible":false,"autofocus":false,"autoscroll":true,"elem_classes":[],"type":"text","rtl":false,"show_copy_button":false,"name":"textbox","_selectable":false},"skip_api":false,"component_class_id":"d0491bb0fbd427bdb2a4549c4d1ac869","key":null,"api_info":{"type":"string"},"example_inputs":"Hello!!"},{"id":72,"type":"form","props":{"scale":0,"min_width":0,"name":"form"},"skip_api":true,"component_class_id":"43cda85c6ff7a5dd8f83d29496b014ee","key":null},{"id":73,"type":"form","props":{"scale":0,"min_width":0,"name":"form"},"skip_api":true,"component_class_id":"43cda85c6ff7a5dd8f83d29496b014ee","key":null},{"id":74,"type":"tabitem","props":{"label":"📊 MMBench_TEST_CN_V11 Leaderboard","visible":true,"interactive":true,"id":7,"elem_id":"MMBench_TEST_CN_V11","name":"tab"},"skip_api":true,"component_class_id":"18f46968e2b273dc5dbda0fe78433d7e","key":null},{"id":75,"type":"checkboxgroup","props":{"choices":[["Overall","Overall"],["AR","AR"],["CP","CP"],["FP-C","FP-C"],["FP-S","FP-S"],["LR","LR"],["RR","RR"],["Action Recognition","Action Recognition"],["Attribute Comparison","Attribute Comparison"],["Attribute Recognition","Attribute Recognition"],["Celebrity Recognition","Celebrity Recognition"],["Function Reasoning","Function Reasoning"],["Future Prediction","Future Prediction"],["Identity Reasoning","Identity Reasoning"],["Image Emotion","Image Emotion"],["Image Quality","Image Quality"],["Image Scene","Image Scene"],["Image Style","Image Style"],["Image Topic","Image Topic"],["Nature Relation","Nature Relation"],["Object Localization","Object Localization"],["Ocr","Ocr"],["Physical Property Reasoning","Physical Property Reasoning"],["Physical Relation","Physical Relation"],["Social Relation","Social Relation"],["Spatial Relationship","Spatial Relationship"],["Structuralized Imagetext Understanding","Structuralized Imagetext Understanding"]],"value":["Overall"],"type":"value","label":"MMBench_TEST_CN_V11 CheckBoxes","show_label":true,"container":true,"min_width":160,"interactive":true,"visible":true,"elem_classes":[],"name":"checkboxgroup","_selectable":false},"skip_api":false,"component_class_id":"0635a5d3bf87369f1c2c1c69f8a3d0cc","key":null,"api_info":{"items":{"enum":["Overall","AR","CP","FP-C","FP-S","LR","RR","Action Recognition","Attribute Comparison","Attribute Recognition","Celebrity Recognition","Function Reasoning","Future Prediction","Identity Reasoning","Image Emotion","Image Quality","Image Scene","Image Style","Image Topic","Nature Relation","Object Localization","Ocr","Physical Property Reasoning","Physical Relation","Social Relation","Spatial Relationship","Structuralized Imagetext Understanding"],"type":"string"},"title":"Checkbox Group","type":"array"},"example_inputs":["Overall"]},{"id":76,"type":"row","props":{"variant":"default","visible":true,"equal_height":true,"show_progress":false,"name":"row"},"skip_api":true,"component_class_id":"b5cf3d15e2293fb5ccc071d7b8d69f64","key":null},{"id":77,"type":"textbox","props":{"value":"Input the Model Name (fuzzy, case insensitive)","lines":1,"max_lines":20,"label":"Model Name","show_label":true,"container":true,"min_width":160,"interactive":true,"visible":true,"autofocus":false,"autoscroll":true,"elem_classes":[],"type":"text","rtl":false,"show_copy_button":false,"name":"textbox","_selectable":false},"skip_api":false,"component_class_id":"d0491bb0fbd427bdb2a4549c4d1ac869","key":null,"api_info":{"type":"string"},"example_inputs":"Hello!!"},{"id":78,"type":"checkboxgroup","props":{"choices":[["<4B","<4B"],["4B-10B","4B-10B"],["10B-20B","10B-20B"],["20B-40B","20B-40B"],[">40B",">40B"],["Unknown","Unknown"]],"value":["<4B","4B-10B","10B-20B","20B-40B",">40B","Unknown"],"type":"value","label":"Model Size","show_label":true,"container":true,"min_width":160,"interactive":true,"visible":true,"elem_classes":[],"name":"checkboxgroup","_selectable":false},"skip_api":false,"component_class_id":"0635a5d3bf87369f1c2c1c69f8a3d0cc","key":null,"api_info":{"items":{"enum":["<4B","4B-10B","10B-20B","20B-40B",">40B","Unknown"],"type":"string"},"title":"Checkbox Group","type":"array"},"example_inputs":["<4B"]},{"id":79,"type":"checkboxgroup","props":{"choices":[["API","API"],["OpenSource","OpenSource"]],"value":["API","OpenSource"],"type":"value","label":"Model Type","show_label":true,"container":true,"min_width":160,"interactive":true,"visible":true,"elem_classes":[],"name":"checkboxgroup","_selectable":false},"skip_api":false,"component_class_id":"0635a5d3bf87369f1c2c1c69f8a3d0cc","key":null,"api_info":{"items":{"enum":["API","OpenSource"],"type":"string"},"title":"Checkbox Group","type":"array"},"example_inputs":["API"]},{"id":80,"type":"form","props":{"scale":3,"min_width":480,"name":"form"},"skip_api":true,"component_class_id":"43cda85c6ff7a5dd8f83d29496b014ee","key":null},{"id":81,"type":"dataframe","props":{"value":{"headers":["Rank","Method","Param (B)","Language Model","Vision Model","Eval Date","Overall"],"data":[[1,"CongRong-v2.0",null,"","","2025/05/20",88.3],[2,"Gemini-2.5-Pro",null,"","","2025/04/07",88.1],[3,"InternVL3-78B",78.4,"Qwen2.5-72B","InternViT-6B-v2.5","2025/04/14",87.9],[4,"InternVL2.5-78B",78.0,"Qwen-2.5-72B","InternViT-6B-v2.5","2024/12/10",87.8],[5,"SenseNova-V6-Pro",null,"","","2025/05/05",87.6],[6,"InternVL2.5-78B-MPO",78.0,"Qwen-2.5-72B","InternViT-6B-v2.5","2024/12/29",87.5],[7,"Qwen2.5-VL-72B",73.4,"Qwen2.5-72B","QwenViT","2025/02/02",87.4],[8,"Step-1o",null,"","","2025/01/13",87.0],[9,"SenseNova-V6-5-Pro",null,"","","2025/09/03",87.0],[10,"JT-VL-Chat-V3.0",null,"","","2025/08/04",86.6],[11,"InternVL3-38B",38.4,"Qwen2.5-32B","InternViT-6B-v2.5","2025/04/14",86.6],[12,"Ovis2-34B",34.9,"Qwen2.5-32B","AIMv2-1B","2025/02/18",86.5],[13,"BailingMM-Pro-0120",81.0,"Bailing-80B","SigLIP-400M","2025/01/25",86.5],[14,"GPT-5-20250807",null,"","","2025/08/14",86.4],[15,"BlueLM-2.6-3B",3.0,"","","2025/09/17",86.4],[16,"GPT-4.1-20250414",null,"","","2025/04/16",86.2],[17,"GPT-5-mini-20250807",null,"","","2025/08/14",86.1],[18,"Qwen2-VL-72B",73.4,"Qwen2-72B","QwenViT","2024/10/28",85.8],[19,"Qwen-VL-Max-0809",72.0,"Qwen2-72B","QwenViT","2024/09/12",85.7],[20,"InternVL2.5-38B",38.0,"Qwen-2.5-32B","InternViT-6B-v2.5","2024/12/10",85.6],[21,"InternVL2-Llama3-76B",76.0,"Llama-3-70B-Instruct","InternViT-6B","2024/07/19",85.5],[22,"Ovis2-16B",16.2,"Qwen2.5-14B","AIMv2 Huge","2025/02/18",85.5],[23,"InternVL2.5-38B-MPO",38.0,"Qwen-2.5-32B","InternViT-6B-v2.5","2024/12/28",85.4],[24,"SenseNova",null,"","","2024/12/12",85.2],[25,"ChatGPT-4o-latest",null,"","","2025/04/07",85.2],[26,"Taiyi",null,"","","2024/12/11",85.0],[27,"InternVL2-40B",40.0,"Nous-Hermes-2-Yi-34B","InternViT-6B","2024/07/11",84.9],[28,"InternVL2.5-26B",26.0,"InternLM2.5-20B","InternViT-6B-v2.5","2024/12/10",84.7],[29,"GLM-4v-Plus-20250111",null,"","","2025/01/25",84.1],[30,"InternVL2.5-26B-MPO",26.0,"InternLM2.5-20B","InternViT-6B-v2.5","2024/12/28",84.1],[31,"GPT-4o (1120, detail-high)",null,"","","2024/12/02",83.9],[32,"LLaVA-OneVision-72B",73.0,"Qwen2-72B","SigLIP-400M","2024/09/19",83.9],[33,"SAIL-VL-1.6-8B",8.33,"Qwen2.5-7B","AIMv2 Huge","2025/04/24",83.7],[34,"Gemini-2.0-Pro",null,"","","2025/02/27",83.5],[35,"Step-1.5V",null,"Step-1.5","stepencoder","2024/10/11",83.5],[36,"Ovis2-8B",8.94,"Qwen2.5-7B","AIMv2 Huge","2025/02/18",83.4],[37,"InternVL3-14B",15.1,"Qwen2.5-14B","InternViT-300M-v2.5","2025/04/14",83.3],[38,"GPT-4.5",null,"","","2025/03/26",83.3],[39,"HunYuan-Standard-Vision",null,"","","2025/01/15",83.3],[40,"Qwen2.5-VL-32B",33.5,"Qwen2.5-32B","QwenViT","2025/07/02",83.2],[41,"Ola-7b",8.88,"Qwen2.5-7B","Oryx-ViT","2025/02/05",83.2],[42,"VARCO-VISION-2.0-14B",15.2,"Qwen3-14B","SigLIP-400M","2025/08/04",83.0],[43,"BailingMM-Lite-1203",21.0,"Bailing-20B","SigLIP-400M","2024/12/08",82.9],[44,"GPT-4o (0513, detail-low)",null,"","","2024/05/15",82.5],[45,"Claude3.5-Sonnet-20241022",null,"","","2024/11/06",82.5],[46,"grok-2-vision-1212",null,"","","2025/03/03",82.5],[47,"InternVL3-9B",9.14,"InternLM3-8B","InternViT-300M-v2.5","2025/04/14",82.4],[48,"BlueLM-V-3B",3.0,"BlueLM-3B","SigLIP-400M","2024/10/30",82.3],[49,"bailingMM-mini",17.0,"bailing-mini","bailingMM-encoder-1B
InternViT-6B","2024/10/24",82.2],[50,"Qwen2.5-VL-7B",8.29,"Qwen2.5-7B","QwenViT","2025/02/02",82.1],[51,"LLaVA-OneVision-72B (SI)",73.0,"Qwen2-72B","SigLIP-400M","2024/09/19",81.9],[52,"InternVL3-8B",7.94,"Qwen2.5-7B","InternViT-300M-v2.5","2025/04/14",81.9],[53,"R-4B",4.82,"Qwen3-4B","SigLip-400M","2025/08/11",81.8],[54,"InternVL2.5-8B",8.0,"InternLM2.5-7B","InternViT-300M-v2.5","2024/12/10",81.7],[55,"SAIL-VL-1.5-8B",7.95,"Qwen2.5-7B","InternViT-300B","2025/04/23",81.7],[56,"MUG-U-7B",7.0,"","","2025/03/19",81.6],[57,"valley2_dpo",8.88,"Qwen2.5-7B","SigLIP-400M","2025/05/30",81.6],[58,"GPT-4o (0513, detail-high)",null,"","","2024/05/31",81.5],[59,"Ovis1.6-Gemma2-27B",28.9,"Gemma2-27B","SigLIP-400M","2024/11/29",81.5],[60,"InternVL2.5-8B-MPO",8.0,"InternLM2.5-7B","InternViT-300M-v2.5","2024/12/28",81.5],[61,"WeThink-Qwen2.5VL-7B",8.29,"Qwen2.5-7B","QwenViT","2025/05/26",81.1],[62,"Gemini-1.5-Pro-002",null,"","","2024/12/02",81.1],[63,"Gemini-1.5-Flash-002",null,"","","2024/12/02",81.0],[64,"GLM-4v-Plus",null,"","","2024/12/11",81.0],[65,"Ovis2-4B",4.62,"Qwen2.5-3B","AIMv2 Huge","2025/02/18",81.0],[66,"LLaVA-OneVision-7B",8.0,"Qwen2-7B","SigLIP-400M","2024/09/16",80.9],[67,"InternVL2-26B",26.0,"InternLM2-20B","InternViT-6B","2024/07/11",80.9],[68,"valley2",8.88,"Qwen2.5-7B","SigLIP-400M","2025/05/30",80.7],[69,"abab7-preview",null,"","","2024/12/11",80.6],[70,"Kimi-VL-A3B-Instruct",16.4,"Moonlight-16B-A3B","MoonViT","2025/04/14",80.6],[71,"CongRong",null,"","","2024/06/26",80.4],[72,"RBDash-v1.5",79.0,"Qwen2-72B","CLIP ViT-L/14
InternViT-6B","2024/11/17",80.3],[73,"Qwen2-VL-7B",8.0,"Qwen2-7B","QwenViT","2024/09/12",80.3],[74,"POINTS1.5-Qwen2.5-7B",8.3,"Qwen-2.5-7B","NaViT","2024/12/06",80.2],[75,"VARCO-VISION-14B",15.2,"Qwen2.5-14B","SigLIP-400M","2025/01/02",80.1],[76,"DeepSeek-VL2",27.5,"DeepSeekMoE-27B","SigLIP-400M","2025/01/01",80.1],[77,"MiniCPM-o-2.6",8.67,"Qwen2.5-7B","SigLIP-400M","2025/01/21",79.9],[78,"Valley-Eagle",8.9,"Qwen2.5-7B","Qwen-ViT
SigLIP-400M","2024/12/29",79.9],[79,"MiMo-VL-7B",8.31,"Mimo-7B","Qwen2.5-ViT","2025/07/02",79.8],[80,"Kimi-VL-A3B-Thinking-2506",16.4,"Moonlight-16B-A3B","MoonViT","2025/07/02",79.8],[81,"MMAlaya2",26.0,"InternLM2-20B","InternViT-6B","2024/08/27",79.7],[82,"GPT-5-nano-20250807",null,"","","2025/08/14",79.6],[83,"Molmo-72B",73.3,"Qwen2-72B","CLIP ViT-L/14","2024/10/28",79.6],[84,"Step-1.5V-mini",null,"","","2024/12/11",79.6],[85,"Claude3.7-Sonnet",null,"","","2025/02/27",79.5],[86,"Ovis1.6-Gemma2-9B",10.2,"Gemma2-9B-It","SigLIP-400M","2024/09/19",79.5],[87,"GPT-4v (0409, detail-high)",null,"","","2024/05/15",79.5],[88,"OmChat-v2.0-13B",13.0,"Qwen2-7B","InternViT-6B","2024/08/22",79.5],[89,"VILA1.5-40B",40.0,"Yi-34B","InternViT-6B","2024/08/25",79.4],[90,"Claude3.5-Sonnet",null,"","","2024/06/24",79.3],[91,"InternVL2-8B",8.0,"InternLM2.5-7B","InternViT-300M","2024/07/11",79.3],[92,"GPT-4o (0806, detail-high)",null,"","","2024/08/08",79.2],[93,"DeepSeek-VL2-Small",16.1,"DeepSeekMoE-16B","SigLIP-400M","2025/01/01",79.1],[94,"InternVL-Chat-V1.5",26.0,"InternLM2-20B","InternViT-6B","2024/04/17",79.1],[95,"Ristretto-3B",3.84,"Qwen2.5-3B","SigLIP-400M","2025/04/01",79.1],[96,"InternLM-XComposer2.5",8.0,"InternLM2-7B","CLIP ViT-L/14","2024/07/11",78.8],[97,"GPT-4.1-mini-20250414",null,"","","2025/04/16",78.6],[98,"TeleMM",null,"","","2024/12/31",78.3],[99,"GPT-4v (0409, detail-low)",null,"","","2024/05/15",78.2],[100,"Gemma3-27B",27.4,"Gemma3-27B","SigLIP-400M","2025/03/19",78.2],[101,"GLM-4v",null,"","","2024/05/20",78.0],[102,"NVLM-D-72B",79.4,"Qwen2-72B","InternViT-6B","2024/10/19",78.0],[103,"POINTS-Yi-1.5-9B",9.5,"Yi-1.5-9B","CLIP ViT-L/14","2024/10/11",77.8],[104,"Ovis-U1-3B",3.64,"Qwen3-1.7B","aimv2-large-path14-448","2025/07/20",77.6],[105,"InternVL2.5-4B",4.0,"Qwen-2.5-3B","InternViT-300M-v2.5","2024/12/10",77.6],[106,"SAIL-VL-1.5-2B",2.47,"Qwen2.5-1.5B","AIMv2 Huge","2025/04/23",77.5],[107,"Cambrian-34B",34.0,"Nous-Hermes-2-Yi-34B","CLIP ViT-L/14","2024/07/18",77.3],[108,"QTuneVL1.5-3B",3.75,"Qwen2.5-3B","QwenViT","2025/08/11",77.1],[109,"LLaVA-Next-Yi-34B",34.8,"Yi-34B","CLIP ViT-L/14","2024/03/25",77.1],[110,"InternLM-XComposer2",7.0,"InternLM2-7B","CLIP ViT-L/14","2024/01/26",77.1],[111,"LLaVA-Next-Qwen-32B",33.0,"Qwen-1.5-32B","SigLIP-400M","2024/08/08",77.1],[112,"InternVL3-2B",2.09,"Qwen2.5-1.5B","InternViT-300M-v2.5","2025/04/14",77.0],[113,"MiniCPM-V-2.6",8.0,"Qwen2-7B","SigLIP-400M","2024/08/08",76.9],[114,"QTuneVL1.5-2B",2.09,"Qwen2.5-1.5B","InternViT-300M-v2.5","2025/08/11",76.9],[115,"POINTS-Qwen2.5-7B",8.3,"Qwen-2.5-7B","CLIP ViT-L/14","2024/10/19",76.9],[116,"InternVL2.5-4B-MPO",4.0,"Qwen-2.5-3B","InternViT-300M-v2.5","2024/12/28",76.9],[117,"Ovis2-2B",2.46,"Qwen2.5-1.5B","AIMv2 Large","2025/02/18",76.8],[118,"Gemini-1.5-Flash",null,"","","2024/09/16",76.7],[119,"Aria",25.3,"Aria-MoE","SigLIP-400M","2024/12/05",76.6],[120,"Qwen2.5-VL-3B",3.75,"Qwen2.5-3B","QwenViT","2025/02/02",76.5],[121,"InternVL2-8B-MPO",8.0,"InternLM2.5-7B","InternViT-300M","2024/11/25",76.4],[122,"Ovis1.5-Gemma2-9B",11.4,"Gemma2-9B-It","SigLIP-400M","2024/08/04",76.2],[123,"moonshot-v1-8k",null,"","","2025/03/03",76.2],[124,"InternLM-XComposer2-4KHD",7.0,"InternLM2-7B","CLIP ViT-L/14","2024/06/09",76.1],[125,"Yi-Vision",null,"","","2024/08/03",76.1],[126,"VITA-1.5",8.3,"Qwen2-7B","InternViT-300M","2025/01/01",76.1],[127,"Long-VITA-16K",14.0,"Qwen2.5-14B","InternViT-300M","2025/06/13",75.9],[128,"LLaVA-OneVision-7B (SI)",8.0,"Qwen2-7B","SigLIP-400M","2024/09/17",75.8],[129,"InternVL2-8B-MPO-CoT",8.0,"InternLM2.5-7B","InternViT-300M","2024/11/25",75.8],[130,"BlueLM-2.5-3B",2.9,"BlueLM-base-3B","Siglip2-So400M","2025/07/16",75.5],[131,"Llama-3.2-90B-Vision-Instruct",88.6,"Llama-3.1-70B","","2024/10/19",75.2],[132,"Ovis1.5-Llama3-8B",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/07/29",75.1],[133,"GPT-4o-mini (0718, detail-high)",null,"","","2024/07/20",75.0],[134,"Phi-4-MultiModal",5.57,"Phi-4-Mini","SigLIP-400M","2025/03/13",74.9],[135,"Flash-VL-2B-Dynamic-ISS",2.53,"Qwen-2.5-1.5B-Instruct","SigLIP2-400M-512","2025/05/30",74.4],[136,"Gemma3-12B",12.2,"Gemma3-12B","SigLIP-400M","2025/03/19",74.3],[137,"XinYuan-VL-2B-Instruct",2.0,"Qwen2-1.5B","QwenViT","2024/09/27",74.2],[138,"Aquila-VL-2B",2.2,"Qwen-2.5-1.5B","SigLIP-400M","2024/10/24",74.1],[139,"360VL-70B",70.0,"Llama-3-70B-Instruct","CLIP ViT-L/14","2024/05/25",73.9],[140,"Ross-Qwen2-7B",8.2,"Qwen2-7B","CLIP ViT-L/14","2025/01/17",73.8],[141,"Eagle-X5-34B-Chat",36.8,"Yi-34B","Clip-448
ConvNeXT-1024
SAM-1024
DET-1024
Pix2Struct-1024","2024/11/29",73.7],[142,"Qwen-VL-Max",null,"QwenLM","","2024/02/02",73.7],[143,"WeMM",7.0,"InternLM2-7B","SigLIP-400M","2024/06/09",73.6],[144,"Gemini-1.5-Pro",null,"","","2024/06/10",73.2],[145,"GPT-4v (1106, detail-low)",null,"","","2023/12/23",72.2],[146,"Ovis1.6-Llama3.2-3B",4.1,"Llama-3.2-3B","SigLIP-400M","2024/10/24",71.9],[147,"Idefics3-8B-Llama3",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/08/27",71.9],[148,"SAIL-VL-2B",2.1,"Qwen2.5-1.5B","InternViT-300M","2024/12/25",71.8],[149,"Bunny-Llama3-8B",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/07/18",71.7],[150,"Molmo-7B-D",8.0,"Qwen2-7B","CLIP ViT-L/14","2024/10/12",71.6],[151,"Gemini-2.0-Flash",null,"","","2025/01/02",71.6],[152,"InternVL2-4B",4.0,"Phi-3","InternViT-300M","2024/07/11",71.4],[153,"LLaVA-CoT",11.0,"","","2025/01/05",71.4],[154,"RekaFlash",null,"","","2024/05/07",71.4],[155,"Qwen2-VL-2B",2.0,"Qwen2-1.5B","QwenViT","2024/09/12",71.2],[156,"LLaVA-Next-Interleave-7B-DPO",8.0,"Qwen-1.5-7B","SigLIP-400M","2024/07/29",70.9],[157,"VARCO-VISION-2.0-1.7B",2.12,"Qwen3-1.7B","SigLIP-400M","2025/08/04",70.8],[158,"LLaVA-InternLM2-20B (QLoRA)",20.2,"InternLM2-20B","CLIP ViT-L/14","2024/01/17",70.5],[159,"Llama-3-MixSense-v1.1",8.0,"Llama-3-8B-Instruct","Florence-2-Large-FT","2024/08/21",70.1],[160,"DeepSeek-VL2-Tiny",3.4,"DeepSeekMoE-3B","SigLIP-400M","2025/01/01",70.1],[161,"MiniCPM-Llama3-V2.5",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/05/27",70.1],[162,"Pixtral-12B",13.0,"Nemo-12B","ViT-400M","2024/09/16",70.1],[163,"LLaVA-InternLM2-7B (QLoRA)",8.1,"InternLM2-7B","CLIP ViT-L/14","2024/01/17",70.0],[164,"DeepSeek-VL-7B",7.3,"DeekSeek-7B","SAM-B
SigLIP-L","2024/03/21",69.7],[165,"QTuneVL1-2B",2.21,"InternLM2.5-1.8B","InternViT-300M-v2.5","2025/05/05",69.6],[166,"InternVL2.5-2B-MPO",2.0,"InternLM2.5-1.8B","InternViT-300M-v2.5","2024/12/28",69.5],[167,"LLaVA-Next-Interleave-7B",8.0,"Qwen-1.5-7B","SigLIP-400M","2024/08/08",69.4],[168,"InternVL2.5-2B",2.0,"InternLM2.5-1.8B","InternViT-300M-v2.5","2024/12/10",69.4],[169,"Gemini-1.0-Pro",null,"","","2023/12/23",69.2],[170,"Parrot-7B",8.0,"Qwen2-7B","CLIP ViT-L/14","2024/08/22",69.2],[171,"InternVL2-2B",2.0,"InternLM2-1.8B","InternViT-300M","2024/07/11",68.9],[172,"VITA",47.0,"Mixtral-8x7B","InternViT-300M","2025/01/20",68.7],[173,"Qwen-VL-Plus-0809",null,"","","2024/09/17",68.7],[174,"CogVLM2-19B-Chat",19.0,"Llama-3-8B-Instruct","EVA2-CLIP-E","2024/05/31",68.6],[175,"MiniMonkey",2.2,"InternLM2-1.8B","InternViT-300M","2024/09/26",68.3],[176,"Qwen-VL-Plus",null,"QwenLM","","2024/01/10",68.2],[177,"TransCore-M",13.4,"PCITransGPT-13B","CLIP ViT-L/14","2024/04/16",67.9],[178,"LLaVA-Next-Llama3",8.0,"Llama-3-8B-Instruct","CLIP ViT-L/14","2024/07/29",67.5],[179,"GLM-4v-9B",9.0,"GLM-4-9B","EVA-02-5B","2024/06/14",67.1],[180,"Yi-VL-34B",34.6,"Yi-34B","CLIP ViT-H/14","2024/01/25",66.8],[181,"Gemma3-4B",4.3,"Gemma3-4B","SigLIP-400M","2025/03/19",66.8],[182,"InternLM-XComposer2-1.8B",2.0,"InternLM2-1.8B","CLIP ViT-L/14","2024/06/09",66.8],[183,"Mini-InternVL-Chat-4B-V1.5",4.0,"Phi-3","InternViT-300M","2024/06/10",66.8],[184,"Ovis2-1B",1.27,"Qwen2.5-0.5B","AIMv2 Large","2025/02/18",66.6],[185,"InternVL3-1B",0.94,"Qwen2.5-0.5B","InternViT-300M-v2.5","2025/04/14",66.4],[186,"Vintern-3B-beta",3.7,"Qwen-2.5-3B","InternViT-300M","2024/10/24",66.2],[187,"Mantis-8B-Idefics2",8.0,"Mistral-7B","SigLIP-400M","2024/08/08",65.8],[188,"granite-vision-3.2-2b",2.98,"granite-3.1-2b-instruct","SigLip","2025/06/20",65.7],[189,"LLaVA-Next-Vicuna-13B",13.4,"Vicuna-v1.5-13B","CLIP ViT-L/14","2024/03/25",65.7],[190,"Falcon2-VLM-11B",11.4,"Falcon2-11B","CLIP ViT-L/14","2024/10/30",65.6],[191,"GPT-4v (1106, detail-high)",null,"","","2024/04/22",65.5],[192,"XGen-MM-Instruct-DPO-v1.5",4.4,"Phi-3","SigLIP-400M","2024/09/06",65.5],[193,"VILA1.5-13B",13.0,"Vicuna-v1.5-13B","SigLIP-400M","2024/08/25",65.2],[194,"Eagle-X5-13B",15.0,"Vicuna-v1.5-13B","Clip-448
ConvNeXT-1024
SAM-1024
DET-1024
Pix2Struct-1024","2024/09/26",65.2],[195,"IDEFICS2-8B",8.0,"Mistral-7B","SigLIP-400M","2024/04/26",65.1],[196,"Monkey-Chat",9.8,"Qwen-7B","ViT-BigHuge","2024/01/16",65.1],[197,"granite-vision-3.3-2b",2.98,"granite-3.1-2b-instruct","SigLIP2-400M","2025/06/20",65.0],[198,"Cambrian-8B",8.0,"Vicuna-v1.5-7B","CLIP ViT-L/14","2024/07/11",64.9],[199,"InternVL2.5-1B",1.0,"Qwen-2.5-0.5B","InternViT-300M-v2.5","2024/12/10",64.8],[200,"MiniCPM-V-2",2.8,"MiniCPM-2.4B","SigLIP-400M","2024/04/15",64.5],[201,"granite-vision-3.1-2b-preview",2.98,"granite-3.1-2b-instruct","SigLip","2025/06/20",64.4],[202,"InternVL2.5-1B-MPO",1.0,"Qwen-2.5-0.5B","InternViT-300M-v2.5","2024/12/28",64.3],[203,"Llama-3.2-11B-Vision-Instruct",11.0,"Llama-3.1-8B","","2024/10/07",64.2],[204,"XGen-MM-Instruct-Interleave-v1.5",4.4,"Phi-3","SigLIP-400M","2024/09/06",64.2],[205,"Kimi-VL-A3B-Thinking",16.4,"Moonlight-16B-A3B","MoonViT","2025/04/23",64.1],[206,"LLaVA-InternLM-7B (QLoRA)",7.6,"InternLM-7B","CLIP ViT-L/14","2023/12/28",64.1],[207,"HawkVL-2B",2.44,"Qwen2.5-1.5B","QwenViT","2025/06/16",63.8],[208,"Slime-8B",8.0,"Llama-3-8B-Instruct","CLIP ViT-L/14","2024/09/14",63.7],[209,"Cambrian-13B",13.0,"Vicuna-v1.5-13B","CLIP ViT-L/14","2024/07/29",63.6],[210,"Claude3-Sonnet",null,"","","2024/03/28",63.5],[211,"Yi-VL-6B",6.6,"Yi-6B","CLIP ViT-H/14","2024/01/25",63.1],[212,"Mantis-8B-siglip-llama3",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/08/08",63.1],[213,"Mini-InternVL-Chat-2B-V1.5",2.0,"InternLM2-1.8B","InternViT-300M","2024/06/10",63.0],[214,"ShareGPT4V-13B",13.4,"Vicuna-v1.5-13B","CLIP ViT-L/14","2023/12/08",63.0],[215,"Phi-3.5-Vision",4.0,"Phi-3.5","CLIP ViT-L/14","2024/08/28",62.8],[216,"PaliGemma-3B-mix-448",3.0,"Gemma-2B","SigLIP-400M","2024/05/17",62.8],[217,"LLaVA-v1.5-13B (QLoRA)",13.4,"Vicuna-v1.5-13B","CLIP ViT-L/14","2023/12/28",62.5],[218,"DeepSeek-VL-1.3B",2.0,"DeekSeek-1B","SAM-B
SigLIP-L","2024/03/21",61.9],[219,"Mantis-8B-clip-llama3",8.0,"Llama-3-8B-Instruct","CLIP ViT-L/14","2024/08/08",61.5],[220,"H2OVL-2B",2.2,"H2O-DANUBE2-1.8B","InternViT-300M","2024/10/31",61.0],[221,"XVERSE-V-13B",13.0,"XVERSE-13B","CLIP ViT-L/14","2024/05/10",60.5],[222,"Eagle-X5-7B",9.0,"Vicuna-v1.5-7B","Clip-448
ConvNeXT-1024
SAM-1024
DET-1024
Pix2Struct-1024","2024/09/26",60.5],[223,"GPT-4.1-nano-20250414",null,"","","2025/04/16",60.4],[224,"LLaVA-LLaMA-3-8B",8.0,"Llama-3-8B-Instruct","CLIP ViT-L/14","2024/05/07",60.2],[225,"LLaVA-Next-Mistral-7B",7.6,"Mistral-7B","CLIP ViT-L/14","2024/03/25",59.8],[226,"Phi-3-Vision",4.2,"Phi-3","CLIP ViT-L/14","2024/05/31",59.8],[227,"MiniCPM-V",3.0,"MiniCPM-2.4B","SigLIP-400M","2024/02/07",59.6],[228,"LLaVA-v1.5-7B (QLoRA)",7.2,"Vicuna-v1.5-7B","CLIP ViT-L/14","2023/12/28",59.5],[229,"LLaVA-Next-Vicuna-7B",7.1,"Vicuna-v1.5-7B","CLIP ViT-L/14","2024/03/25",59.4],[230,"OmniLMM-12B",12.0,"Zephyr-7B-β","EVA-02-5B","2024/02/07",59.4],[231,"ShareGPT4V-7B",7.2,"Vicuna-v1.5-7B","CLIP ViT-L/14","2023/12/08",58.6],[232,"Janus-Pro-7B",7.42,"DeepSeek-7B","SigLIP-400M","2025/02/02",58.3],[233,"Claude3-Opus",null,"","","2024/03/28",58.1],[234,"mPLUG-Owl2",8.2,"Llama-2-7B","CLIP ViT-L/14","2023/11/10",58.0],[235,"Llama-3-VILA1.5-8B",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/08/25",57.9],[236,"ShareCaptioner",8.0,"InternLM-7B","EVA-G","2024/01/03",57.8],[237,"InternVL2-1B",1.0,"Qwen2-0.5B","InternViT-300M","2024/07/11",57.7],[238,"Qwen-VL-Chat",9.6,"Qwen-7B","ViT-G/16","2023/08/24",57.5],[239,"abab6.5s",null,"","","2024/12/11",57.5],[240,"Molmo-7B-O",8.0,"Qwen2-7B","CLIP ViT-L/14","2024/10/20",56.8],[241,"Slime-13B",13.0,"Vicuna-v1.5-13B","CLIP ViT-L/14","2024/09/14",56.8],[242,"MMAlaya",7.8,"Alaya-7B-Chat","EVA-G","2024/01/29",56.6],[243,"RekaEdge",null,"","","2024/05/31",56.6],[244,"Claude3-Haiku",null,"","","2024/03/28",56.2],[245,"LLaVA-v1.5-13B",13.4,"Vicuna-v1.5-13B","CLIP ViT-L/14","2023/10/05",55.5],[246,"VILA1.5-3B",3.0,"Sheared-LLaMA-2.7B","SigLIP-400M","2024/08/25",54.5],[247,"Slime-7B",7.0,"Vicuna-v1.5-7B","CLIP ViT-L/14","2024/09/14",54.3],[248,"CogVLM-17B-Chat",17.0,"Vicuna-v1.5-7B","EVA2-CLIP-E","2024/01/03",54.0],[249,"LLaVA-OneVision-0.5B",1.0,"Qwen2-0.5B","SigLIP-400M","2024/09/16",53.9],[250,"SmolVLM2",2.25,"SmolLM2-1.7M","SigLIP-400M","2025/03/13",53.2],[251,"Monkey",9.8,"Qwen-7B","ViT-BigHuge","2024/01/11",52.5],[252,"Vintern-1B-v2",3.7,"Qwen2-0.5B","InternViT-300M","2024/11/16",52.2],[253,"Janus-1.3B",2.1,"DeepSeek-1B","SigLIP-400M","2024/10/24",50.4],[254,"SmolVLM-Instruct",2.3,"SmolLM2-1.7B","SigLIP-400M","2025/01/27",50.3],[255,"SmolVLM-Instruct-DPO",2.3,"SmolLM2-1.7B","SigLIP-400M","2025/01/27",48.1],[256,"LLaVA-OneVision-0.5B (SI)",1.0,"Qwen2-0.5B","SigLIP-400M","2024/09/17",47.6],[257,"Emu3_chat",8.49,"","","2025/01/26",46.1],[258,"InternLM-XComposer",8.0,"InternLM-7B","EVA-G","2023/09/26",45.5],[259,"AKI-4B",4.33,"Phi-3.5","SigLIP-400M","2025/03/25",45.3],[260,"IDEFICS-80B-Instruct",80.0,"Llama-65B","CLIP ViT-H/14","2023/07/25",44.4],[261,"Emu2_chat",37.0,"Llama-33B","EVA-02-CLIP-E-plus","2024/01/17",44.3],[262,"MolmoE-1B",7.2,"OLMoE-1B-7B-0924","CLIP ViT-L/14","2024/10/21",44.2],[263,"LLaVA-v1.5-7B",7.2,"Vicuna-v1.5-7B","CLIP ViT-L/14","2023/10/05",43.9],[264,"H2OVL-800M",0.83,"H2O-DANUBE3-500M","InternViT-300M","2024/10/31",41.5],[265,"LLaVA-v1-7B",7.2,"Llama-7B","CLIP ViT-L/14","2023/04/17",35.8],[266,"SmolVLM-Synthetic",2.3,"SmolLM2-1.7B","SigLIP-400M","2025/01/27",35.3],[267,"VisualGLM",8.0,"ChatGLM 6B","EVA-CLIP","2023/05/17",34.6],[268,"SmolVLM-500M",0.51,"SmolLM2-360M","ViT-93M","2025/01/27",33.7],[269,"SmolVLM2-500M",0.51,"SmolLM2-360M","ViT-93M","2025/03/13",33.4],[270,"Mantis-8B-Fuyu",8.0,"Fuyu-8B","","2024/09/07",31.8],[271,"PandaGPT-13B",14.0,"Vicuna-13B","ImageBind ViT-H/14","2023/05/25",29.2],[272,"Moondream2",1.9,"SigLIP-400M","Phi-1.5","2024/10/20",28.5],[273,"Chameleon-30B",30.0,"","","2024/07/29",27.8],[274,"Qwen-VL",9.6,"Qwen-7B","ViT-G/16","2023/08/24",24.2],[275,"Chameleon-7B",7.0,"","","2024/07/29",19.6],[276,"IDEFICS-9B-Instruct",9.0,"Llama-7B","CLIP ViT-H/14","2023/07/25",19.5],[277,"Moondream1",1.9,"SigLIP-400M","Phi-1.5","2024/09/26",18.6],[278,"InstructBLIP-7B",8.0,"Vicuna-7B","EVA-G","2023/05/11",18.4],[279,"SmolVLM-256M",0.26,"SmolLM2-135M","ViT-93M","2025/01/27",14.5],[280,"OpenFlamingo v2",9.0,"MPT 7B","CLIP ViT-L/14","2023/06/28",13.3],[281,"MiniGPT-4-v1-7B",8.0,"Vicuna-7B","EVA-G","2023/04/20",10.7],[282,"SmolVLM2-256M",0.26,"SmolLM2-135M","ViT-93M","2025/03/13",1.9],[283,"MiniGPT-4-v2",8.0,"Llama-2-13B","EVA-G","2023/10/27",1.4],[284,"Kosmos2",1.7,"","","2024/10/19",0.9]],"metadata":null},"headers":["1","2","3"],"row_count":[1,"dynamic"],"col_count":[3,"dynamic"],"datatype":["number","html","number","html","html","str","number"],"type":"pandas","latex_delimiters":[{"left":"$$","right":"$$","display":true}],"show_label":true,"height":500,"min_width":160,"interactive":false,"visible":true,"elem_classes":[],"wrap":true,"line_breaks":true,"column_widths":[],"name":"dataframe","_selectable":false},"skip_api":false,"component_class_id":"6a51bb3357f2e94c40fb8d4fbe06aa8e","key":null,"api_info":{"properties":{"headers":{"items":{"type":"string"},"title":"Headers","type":"array"},"data":{"items":{"items":{},"type":"array"},"title":"Data","type":"array"},"metadata":{"anyOf":[{"additionalProperties":{"anyOf":[{"items":{},"type":"array"},{"type":"null"}]},"type":"object"},{"type":"null"}],"default":null,"title":"Metadata"}},"required":["headers","data"],"title":"DataframeData","type":"object"},"example_inputs":{"headers":["a","b"],"data":[["foo","bar"]]}},{"id":82,"type":"textbox","props":{"value":"MMBench_TEST_CN_V11","lines":1,"max_lines":20,"label":"MMBench_TEST_CN_V11","show_label":true,"container":true,"min_width":160,"visible":false,"autofocus":false,"autoscroll":true,"elem_classes":[],"type":"text","rtl":false,"show_copy_button":false,"name":"textbox","_selectable":false},"skip_api":false,"component_class_id":"d0491bb0fbd427bdb2a4549c4d1ac869","key":null,"api_info":{"type":"string"},"example_inputs":"Hello!!"},{"id":83,"type":"form","props":{"scale":0,"min_width":0,"name":"form"},"skip_api":true,"component_class_id":"43cda85c6ff7a5dd8f83d29496b014ee","key":null},{"id":84,"type":"form","props":{"scale":0,"min_width":0,"name":"form"},"skip_api":true,"component_class_id":"43cda85c6ff7a5dd8f83d29496b014ee","key":null},{"id":85,"type":"tabitem","props":{"label":"📊 MME Leaderboard","visible":true,"interactive":true,"id":8,"elem_id":"MME","name":"tab"},"skip_api":true,"component_class_id":"18f46968e2b273dc5dbda0fe78433d7e","key":null},{"id":86,"type":"checkboxgroup","props":{"choices":[["Overall","Overall"],["Perception","Perception"],["Cognition","Cognition"],["OCR","OCR"],["Artwork","Artwork"],["Celebrity","Celebrity"],["Code Reasoning","Code Reasoning"],["Color","Color"],["Commonsense Reasoning","Commonsense Reasoning"],["Count","Count"],["Existence","Existence"],["Landmark","Landmark"],["Numerical Calculation","Numerical Calculation"],["Position","Position"],["Posters","Posters"],["Scene","Scene"],["Text Translation","Text Translation"]],"value":["Overall","Perception","Cognition"],"type":"value","label":"MME CheckBoxes","show_label":true,"container":true,"min_width":160,"interactive":true,"visible":true,"elem_classes":[],"name":"checkboxgroup","_selectable":false},"skip_api":false,"component_class_id":"0635a5d3bf87369f1c2c1c69f8a3d0cc","key":null,"api_info":{"items":{"enum":["Overall","Perception","Cognition","OCR","Artwork","Celebrity","Code Reasoning","Color","Commonsense Reasoning","Count","Existence","Landmark","Numerical Calculation","Position","Posters","Scene","Text Translation"],"type":"string"},"title":"Checkbox Group","type":"array"},"example_inputs":["Overall"]},{"id":87,"type":"row","props":{"variant":"default","visible":true,"equal_height":true,"show_progress":false,"name":"row"},"skip_api":true,"component_class_id":"b5cf3d15e2293fb5ccc071d7b8d69f64","key":null},{"id":88,"type":"textbox","props":{"value":"Input the Model Name (fuzzy, case insensitive)","lines":1,"max_lines":20,"label":"Model Name","show_label":true,"container":true,"min_width":160,"interactive":true,"visible":true,"autofocus":false,"autoscroll":true,"elem_classes":[],"type":"text","rtl":false,"show_copy_button":false,"name":"textbox","_selectable":false},"skip_api":false,"component_class_id":"d0491bb0fbd427bdb2a4549c4d1ac869","key":null,"api_info":{"type":"string"},"example_inputs":"Hello!!"},{"id":89,"type":"checkboxgroup","props":{"choices":[["<4B","<4B"],["4B-10B","4B-10B"],["10B-20B","10B-20B"],["20B-40B","20B-40B"],[">40B",">40B"],["Unknown","Unknown"]],"value":["<4B","4B-10B","10B-20B","20B-40B",">40B","Unknown"],"type":"value","label":"Model Size","show_label":true,"container":true,"min_width":160,"interactive":true,"visible":true,"elem_classes":[],"name":"checkboxgroup","_selectable":false},"skip_api":false,"component_class_id":"0635a5d3bf87369f1c2c1c69f8a3d0cc","key":null,"api_info":{"items":{"enum":["<4B","4B-10B","10B-20B","20B-40B",">40B","Unknown"],"type":"string"},"title":"Checkbox Group","type":"array"},"example_inputs":["<4B"]},{"id":90,"type":"checkboxgroup","props":{"choices":[["API","API"],["OpenSource","OpenSource"]],"value":["API","OpenSource"],"type":"value","label":"Model Type","show_label":true,"container":true,"min_width":160,"interactive":true,"visible":true,"elem_classes":[],"name":"checkboxgroup","_selectable":false},"skip_api":false,"component_class_id":"0635a5d3bf87369f1c2c1c69f8a3d0cc","key":null,"api_info":{"items":{"enum":["API","OpenSource"],"type":"string"},"title":"Checkbox Group","type":"array"},"example_inputs":["API"]},{"id":91,"type":"form","props":{"scale":3,"min_width":480,"name":"form"},"skip_api":true,"component_class_id":"43cda85c6ff7a5dd8f83d29496b014ee","key":null},{"id":92,"type":"dataframe","props":{"value":{"headers":["Rank","Method","Param (B)","Language Model","Vision Model","Eval Date","Overall","Perception","Cognition"],"data":[[1,"InternVL3-78B",78.4,"Qwen2.5-72B","InternViT-6B-v2.5","2025/04/14",2538.6,1785.3,753.2],[2,"Qwen2-VL-72B",73.4,"Qwen2-72B","QwenViT","2024/10/28",2504.2,1770.6,733.6],[3,"InternVL3-38B",38.4,"Qwen2.5-32B","InternViT-6B-v2.5","2025/04/14",2500.7,1773.6,727.1],[4,"Qwen-VL-Max-0809",72.0,"Qwen2-72B","QwenViT","2024/09/12",2492.5,1768.6,723.9],[5,"InternVL2.5-78B-MPO",78.0,"Qwen-2.5-72B","InternViT-6B-v2.5","2024/12/29",2479.1,1758.0,721.1],[6,"InternVL2.5-78B",78.0,"Qwen-2.5-72B","InternViT-6B-v2.5","2024/12/10",2467.6,1748.3,719.3],[7,"InternVL3-14B",15.1,"Qwen2.5-14B","InternViT-300M-v2.5","2025/04/14",2462.3,1741.6,720.7],[8,"InternVL2.5-38B-MPO",38.0,"Qwen-2.5-32B","InternViT-6B-v2.5","2024/12/28",2446.4,1726.0,720.4],[9,"Qwen2.5-VL-72B",73.4,"Qwen2.5-72B","QwenViT","2025/02/02",2435.0,1699.3,735.7],[10,"Gemini-2.0-Pro",null,"","","2025/02/27",2428.7,1721.5,707.1],[11,"InternVL3-8B",7.94,"Qwen2.5-7B","InternViT-300M-v2.5","2025/04/14",2422.0,1748.4,673.6],[12,"GLM-4v-Plus-20250111",null,"","","2025/01/25",2418.7,1721.9,696.8],[13,"Step-1o",null,"","","2025/01/13",2411.3,1748.1,663.2],[14,"Ovis2-34B",34.9,"Qwen2.5-32B","AIMv2-1B","2025/02/18",2406.2,1663.4,742.9],[15,"InternVL2-Llama3-76B",76.0,"Llama-3-70B-Instruct","InternViT-6B","2024/07/19",2397.6,1739.0,658.6],[16,"NVLM-D-72B",79.4,"Qwen2-72B","InternViT-6B","2024/10/19",2394.5,1738.8,655.7],[17,"Gemini-2.0-Flash",null,"","","2025/01/02",2386.1,1678.6,707.5],[18,"Ovis2-16B",16.2,"Qwen2.5-14B","AIMv2 Huge","2025/02/18",2371.3,1675.2,696.1],[19,"InternVL3-9B",9.14,"InternLM3-8B","InternViT-300M-v2.5","2025/04/14",2368.0,1723.0,645.0],[20,"TeleMM",null,"","","2024/12/31",2359.6,1671.0,688.6],[21,"Taiyi",null,"","","2024/12/11",2355.9,1717.7,638.2],[22,"InternVL2.5-26B-MPO",26.0,"InternLM2.5-20B","InternViT-6B-v2.5","2024/12/28",2344.3,1703.3,641.1],[23,"MUG-U-7B",7.0,"","","2025/03/19",2342.9,1680.0,662.9],[24,"GPT-4.1-20250414",null,"","","2025/04/16",2337.6,1663.6,673.9],[25,"Ovis1.6-Gemma2-27B",28.9,"Gemma2-27B","SigLIP-400M","2024/11/29",2336.1,1672.5,663.6],[26,"BailingMM-Pro-0120",81.0,"Bailing-80B","SigLIP-400M","2025/01/25",2335.3,1639.6,695.7],[27,"GPT-4o (0513, detail-low)",null,"","","2024/05/15",2328.7,1609.4,719.3],[28,"VITA-1.5",8.3,"Qwen2-7B","InternViT-300M","2025/01/01",2328.1,1722.7,605.4],[29,"InternVL2.5-8B-MPO",8.0,"InternLM2.5-7B","InternViT-300M-v2.5","2024/12/28",2326.7,1686.7,640.0],[30,"Ovis2-8B",8.94,"Qwen2.5-7B","AIMv2 Huge","2025/02/18",2326.6,1628.1,698.6],[31,"LLaVA-OneVision-72B (SI)",73.0,"Qwen2-72B","SigLIP-400M","2024/09/19",2319.4,1735.5,583.9],[32,"Qwen2.5-VL-7B",8.29,"Qwen2.5-7B","QwenViT","2025/02/02",2312.1,1698.1,613.9],[33,"GPT-4o (0513, detail-high)",null,"","","2024/05/31",2310.3,1614.2,696.1],[34,"Qwen-VL-Plus-0809",null,"","","2024/09/17",2300.2,1666.2,633.9],[35,"InternVL2-8B-MPO-CoT",8.0,"InternLM2.5-7B","InternViT-300M","2024/11/25",2297.4,1657.4,640.0],[36,"InternVL2-40B",40.0,"Nous-Hermes-2-Yi-34B","InternViT-6B","2024/07/11",2293.1,1721.0,572.1],[37,"RBDash-v1.5",79.0,"Qwen2-72B","CLIP ViT-L/14
InternViT-6B","2024/11/17",2292.6,1730.8,561.8],[38,"GPT-4o (0806, detail-high)",null,"","","2024/08/08",2291.0,1594.6,696.4],[39,"InternVL2.5-4B-MPO",4.0,"Qwen-2.5-3B","InternViT-300M-v2.5","2024/12/28",2289.8,1670.2,619.6],[40,"Qwen-VL-Max",null,"QwenLM","","2024/02/02",2281.7,1705.6,576.1],[41,"CongRong",null,"","","2024/06/26",2278.3,1756.5,521.8],[42,"Qwen2-VL-7B",8.0,"Qwen2-7B","QwenViT","2024/09/12",2276.3,1639.2,637.1],[43,"MiniCPM-V-2.6",8.0,"Qwen2-7B","SigLIP-400M","2024/08/08",2268.7,1670.9,597.9],[44,"abab7-preview",null,"","","2024/12/11",2264.9,1659.5,605.4],[45,"InternVL2-26B",26.0,"InternLM2-20B","InternViT-6B","2024/07/11",2259.8,1732.6,527.1],[46,"LLaVA-OneVision-72B",73.0,"Qwen2-72B","SigLIP-400M","2024/09/19",2257.4,1682.4,575.0],[47,"MiniCPM-o-2.6",8.67,"Qwen2.5-7B","SigLIP-400M","2025/01/21",2255.4,1655.4,600.0],[48,"HunYuan-Standard-Vision",null,"","","2025/01/15",2250.4,1584.3,666.1],[49,"InternVL2-8B-MPO",8.0,"InternLM2.5-7B","InternViT-300M","2024/11/25",2239.0,1652.3,586.8],[50,"InternLM-XComposer2.5",8.0,"InternLM2-7B","CLIP ViT-L/14","2024/07/11",2233.1,1640.6,592.5],[51,"DeepSeek-VL2",27.5,"DeepSeekMoE-27B","SigLIP-400M","2025/01/01",2230.2,1632.7,597.5],[52,"Qwen-VL-Plus",null,"QwenLM","","2024/01/10",2229.8,1692.3,537.5],[53,"POINTS1.5-Qwen2.5-7B",8.3,"Qwen-2.5-7B","NaViT","2024/12/06",2226.3,1597.7,628.6],[54,"InternLM-XComposer2",7.0,"InternLM2-7B","CLIP ViT-L/14","2024/01/26",2220.4,1696.9,523.6],[55,"InternVL2-8B",8.0,"InternLM2.5-7B","InternViT-300M","2024/07/11",2215.1,1639.7,575.4],[56,"VILA1.5-40B",40.0,"Yi-34B","InternViT-6B","2024/08/25",2209.1,1694.1,515.0],[57,"Ovis1.6-Gemma2-9B",10.2,"Gemma2-9B-It","SigLIP-400M","2024/09/19",2206.1,1639.3,566.8],[58,"Yi-Vision",null,"","","2024/08/03",2203.7,1581.6,622.1],[59,"Qwen2.5-VL-3B",3.75,"Qwen2.5-3B","QwenViT","2025/02/02",2199.9,1592.4,607.5],[60,"Aria",25.3,"Aria-MoE","SigLIP-400M","2024/12/05",2195.1,1654.8,540.4],[61,"GLM-4v-Plus",null,"","","2024/12/11",2194.9,1552.4,642.5],[62,"InternVL-Chat-V1.5",26.0,"InternLM2-20B","InternViT-6B","2024/04/17",2189.6,1694.9,494.6],[63,"Step-1.5V",null,"Step-1.5","stepencoder","2024/10/11",2186.6,1604.9,581.8],[64,"InternVL3-2B",2.09,"Qwen2.5-1.5B","InternViT-300M-v2.5","2025/04/14",2186.4,1627.5,558.9],[65,"POINTS-Qwen2.5-7B",8.3,"Qwen-2.5-7B","CLIP ViT-L/14","2024/10/19",2184.1,1665.2,518.9],[66,"VARCO-VISION-14B",15.2,"Qwen2.5-14B","SigLIP-400M","2025/01/02",2183.3,1666.9,516.4],[67,"MMAlaya2",26.0,"InternLM2-20B","InternViT-6B","2024/08/27",2179.9,1658.8,521.1],[68,"Kimi-VL-A3B-Instruct",16.4,"Moonlight-16B-A3B","MoonViT","2025/04/14",2175.3,1638.6,536.8],[69,"BailingMM-Lite-1203",21.0,"Bailing-20B","SigLIP-400M","2024/12/08",2166.1,1590.4,575.7],[70,"GLM-4v",null,"","","2024/05/20",2163.7,1590.5,573.2],[71,"Ovis2-4B",4.62,"Qwen2.5-3B","AIMv2 Huge","2025/02/18",2161.6,1564.8,596.8],[72,"grok-2-vision-1212",null,"","","2025/03/03",2154.7,1660.8,493.9],[73,"moonshot-v1-8k",null,"","","2025/03/03",2151.6,1525.9,625.7],[74,"WeMM",7.0,"InternLM2-7B","SigLIP-400M","2024/06/09",2150.1,1686.8,463.2],[75,"Gemini-1.0-Pro",null,"","","2023/12/23",2148.9,1608.9,540.0],[76,"Gemma3-27B",27.4,"Gemma3-27B","SigLIP-400M","2025/03/19",2148.5,1558.5,590.0],[77,"LLaVA-OneVision-7B (SI)",8.0,"Qwen2-7B","SigLIP-400M","2024/09/17",2146.3,1642.4,503.9],[78,"DeepSeek-VL2-Small",16.1,"DeepSeekMoE-16B","SigLIP-400M","2025/01/01",2137.6,1644.3,493.2],[79,"InternLM-XComposer2-4KHD",7.0,"InternLM2-7B","CLIP ViT-L/14","2024/06/09",2130.4,1581.5,548.9],[80,"OmChat-v2.0-13B",13.0,"Qwen2-7B","InternViT-6B","2024/08/22",2130.1,1686.2,443.9],[81,"Ovis1.5-Gemma2-9B",11.4,"Gemma2-9B-It","SigLIP-400M","2024/08/04",2125.2,1651.6,473.6],[82,"InternVL2.5-2B-MPO",2.0,"InternLM2.5-1.8B","InternViT-300M-v2.5","2024/12/28",2117.9,1606.5,511.4],[83,"GPT-4.1-mini-20250414",null,"","","2025/04/16",2110.9,1495.2,615.7],[84,"Gemini-1.5-Pro",null,"","","2024/06/10",2110.6,1562.4,548.2],[85,"Claude3.5-Sonnet-20241022",null,"","","2024/11/06",2110.0,1510.3,599.6],[86,"bailingMM-mini",17.0,"bailing-mini","bailingMM-encoder-1B
InternViT-6B","2024/10/24",2079.8,1513.7,566.1],[87,"Mini-InternVL-Chat-4B-V1.5",4.0,"Phi-3","InternViT-300M","2024/06/10",2079.2,1583.9,495.4],[88,"Gemini-1.5-Flash",null,"","","2024/09/16",2077.9,1589.3,488.6],[89,"GPT-4v (0409, detail-high)",null,"","","2024/05/15",2070.2,1560.5,509.6],[90,"InternVL2-4B",4.0,"Phi-3","InternViT-300M","2024/07/11",2064.6,1532.8,531.8],[91,"Gemma3-12B",12.2,"Gemma3-12B","SigLIP-400M","2025/03/19",2053.5,1533.5,520.0],[92,"Yi-VL-34B",34.6,"Yi-34B","CLIP ViT-H/14","2024/01/25",2050.2,1608.4,441.8],[93,"Cambrian-34B",34.0,"Nous-Hermes-2-Yi-34B","CLIP ViT-L/14","2024/07/18",2049.9,1625.2,424.6],[94,"GPT-4v (0409, detail-low)",null,"","","2024/05/15",2037.8,1551.1,486.8],[95,"Step-1.5V-mini",null,"","","2024/12/11",2037.5,1525.3,512.1],[96,"POINTS-Yi-1.5-9B",9.5,"Yi-1.5-9B","CLIP ViT-L/14","2024/10/11",2028.4,1519.1,509.3],[97,"MiniCPM-Llama3-V2.5",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/05/27",2024.6,1620.0,404.6],[98,"GLM-4v-9B",9.0,"GLM-4-9B","EVA-02-5B","2024/06/14",2018.8,1561.3,457.5],[99,"360VL-70B",70.0,"Llama-3-70B-Instruct","CLIP ViT-L/14","2024/05/25",2009.7,1646.2,363.6],[100,"LLaVA-Next-Yi-34B",34.8,"Yi-34B","CLIP ViT-L/14","2024/03/25",2006.5,1614.3,392.1],[101,"Ovis2-2B",2.46,"Qwen2.5-1.5B","AIMv2 Large","2025/02/18",2005.0,1430.7,574.3],[102,"GPT-4o-mini (0718, detail-high)",null,"","","2024/07/20",2003.4,1440.1,563.2],[103,"LLaVA-OneVision-7B",8.0,"Qwen2-7B","SigLIP-400M","2024/09/16",1993.6,1577.8,415.7],[104,"Molmo-72B",73.3,"Qwen2-72B","CLIP ViT-L/14","2024/10/28",1992.0,1548.7,443.2],[105,"Bunny-Llama3-8B",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/07/18",1987.7,1636.6,351.1],[106,"SAIL-VL-2B",2.1,"Qwen2.5-1.5B","InternViT-300M","2024/12/25",1984.0,1468.3,515.7],[107,"InternVL2.5-1B-MPO",1.0,"Qwen-2.5-0.5B","InternViT-300M-v2.5","2024/12/28",1969.6,1495.3,474.3],[108,"Phi-4-MultiModal",5.57,"Phi-4-Mini","SigLIP-400M","2025/03/13",1961.7,1475.3,486.4],[109,"LLaVA-Next-Qwen-32B",33.0,"Qwen-1.5-32B","SigLIP-400M","2024/08/08",1951.7,1624.5,327.1],[110,"Ovis1.6-Llama3.2-3B",4.1,"Llama-3.2-3B","SigLIP-400M","2024/10/24",1951.4,1546.0,405.4],[111,"Ovis1.5-Llama3-8B",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/07/29",1948.5,1566.4,382.1],[112,"BlueLM-V-3B",3.0,"BlueLM-3B","SigLIP-400M","2024/10/30",1947.0,1452.7,494.3],[113,"Idefics3-8B-Llama3",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/08/27",1937.4,1584.9,352.5],[114,"OmniLMM-12B",12.0,"Zephyr-7B-β","EVA-02-5B","2024/02/07",1935.8,1617.2,318.6],[115,"Pixtral-12B",13.0,"Nemo-12B","ViT-400M","2024/09/16",1921.7,1545.3,376.4],[116,"Claude3.5-Sonnet",null,"","","2024/06/24",1920.0,1380.7,539.3],[117,"Yi-VL-6B",6.6,"Yi-6B","CLIP ViT-H/14","2024/01/25",1915.1,1545.8,369.3],[118,"ShareGPT4V-7B",7.2,"Vicuna-v1.5-7B","CLIP ViT-L/14","2023/12/08",1914.9,1561.4,353.6],[119,"InternVL3-1B",0.94,"Qwen2.5-0.5B","InternViT-300M-v2.5","2025/04/14",1912.4,1497.7,414.6],[120,"XVERSE-V-13B",13.0,"XVERSE-13B","CLIP ViT-L/14","2024/05/10",1909.9,1543.1,366.8],[121,"LLaVA-Next-Llama3",8.0,"Llama-3-8B-Instruct","CLIP ViT-L/14","2024/07/29",1908.0,1551.5,356.4],[122,"Mini-InternVL-Chat-2B-V1.5",2.0,"InternLM2-1.8B","InternViT-300M","2024/06/10",1906.1,1482.5,423.6],[123,"DeepSeek-VL2-Tiny",3.4,"DeepSeekMoE-3B","SigLIP-400M","2025/01/01",1905.5,1548.3,357.1],[124,"MiniMonkey",2.2,"InternLM2-1.8B","InternViT-300M","2024/09/26",1899.6,1470.3,429.3],[125,"Qwen2-VL-2B",2.0,"Qwen2-1.5B","QwenViT","2024/09/12",1899.1,1485.1,413.9],[126,"InternLM-XComposer2-1.8B",2.0,"InternLM2-1.8B","CLIP ViT-L/14","2024/06/09",1895.9,1495.9,400.0],[127,"Slime-8B",8.0,"Llama-3-8B-Instruct","CLIP ViT-L/14","2024/09/14",1895.7,1567.9,327.9],[128,"Monkey-Chat",9.8,"Qwen-7B","ViT-BigHuge","2024/01/16",1887.4,1505.6,381.8],[129,"TransCore-M",13.4,"PCITransGPT-13B","CLIP ViT-L/14","2024/04/16",1885.0,1585.7,299.3],[130,"Cambrian-13B",13.0,"Vicuna-v1.5-13B","CLIP ViT-L/14","2024/07/29",1876.8,1520.8,356.1],[131,"InternLM-XComposer",8.0,"InternLM-7B","EVA-G","2023/09/26",1874.2,1497.4,376.8],[132,"Falcon2-VLM-11B",11.4,"Falcon2-11B","CLIP ViT-L/14","2024/10/30",1873.0,1565.1,307.9],[133,"CogVLM2-19B-Chat",19.0,"Llama-3-8B-Instruct","EVA2-CLIP-E","2024/05/31",1869.5,1495.6,373.9],[134,"LLaVA-InternLM2-20B (QLoRA)",20.2,"InternLM2-20B","CLIP ViT-L/14","2024/01/17",1867.1,1512.1,355.0],[135,"Eagle-X5-7B",9.0,"Vicuna-v1.5-7B","Clip-448
ConvNeXT-1024
SAM-1024
DET-1024
Pix2Struct-1024","2024/09/26",1866.0,1502.8,363.2],[136,"InternVL2-2B",2.0,"InternLM2-1.8B","InternViT-300M","2024/07/11",1864.3,1441.4,422.9],[137,"RekaFlash",null,"","","2024/05/07",1861.1,1433.6,427.5],[138,"Qwen-VL-Chat",9.6,"Qwen-7B","ViT-G/16","2023/08/24",1860.0,1467.8,392.1],[139,"Ross-Qwen2-7B",8.2,"Qwen2-7B","CLIP ViT-L/14","2025/01/17",1853.5,1470.3,383.2],[140,"Molmo-7B-D",8.0,"Qwen2-7B","CLIP ViT-L/14","2024/10/12",1853.2,1461.8,391.4],[141,"ShareGPT4V-13B",13.4,"Vicuna-v1.5-13B","CLIP ViT-L/14","2023/12/08",1853.1,1568.8,284.3],[142,"granite-vision-3.2-2b",2.98,"granite-3.1-2b-instruct","SigLip","2025/06/20",1851.0,1496.4,354.6],[143,"Eagle-X5-13B",15.0,"Vicuna-v1.5-13B","Clip-448
ConvNeXT-1024
SAM-1024
DET-1024
Pix2Struct-1024","2024/09/26",1847.8,1528.9,318.9],[144,"IDEFICS2-8B",8.0,"Mistral-7B","SigLIP-400M","2024/04/26",1847.6,1492.9,354.6],[145,"Claude3.7-Sonnet",null,"","","2025/02/27",1839.3,1189.7,649.6],[146,"XinYuan-VL-2B-Instruct",2.0,"Qwen2-1.5B","QwenViT","2024/09/27",1838.8,1425.2,413.6],[147,"Phi-3.5-Vision",4.0,"Phi-3.5","CLIP ViT-L/14","2024/08/28",1838.1,1457.0,381.1],[148,"LLaVA-LLaMA-3-8B",8.0,"Llama-3-8B-Instruct","CLIP ViT-L/14","2024/05/07",1825.5,1476.6,348.9],[149,"LLaVA-Next-Mistral-7B",7.6,"Mistral-7B","CLIP ViT-L/14","2024/03/25",1821.2,1512.3,308.9],[150,"Llama-3.2-11B-Vision-Instruct",11.0,"Llama-3.1-8B","","2024/10/07",1820.5,1380.9,439.6],[151,"Parrot-7B",8.0,"Qwen2-7B","CLIP ViT-L/14","2024/08/22",1818.1,1505.2,312.9],[152,"granite-vision-3.3-2b",2.98,"granite-3.1-2b-instruct","SigLIP2-400M","2025/06/20",1813.8,1494.9,318.9],[153,"InternVL2-1B",1.0,"Qwen2-0.5B","InternViT-300M","2024/07/11",1808.9,1377.1,431.8],[154,"XGen-MM-Instruct-Interleave-v1.5",4.4,"Phi-3","SigLIP-400M","2024/09/06",1808.7,1477.7,331.1],[155,"LLaVA-v1.5-7B",7.2,"Vicuna-v1.5-7B","CLIP ViT-L/14","2023/10/05",1808.4,1506.2,302.1],[156,"MiniCPM-V-2",2.8,"MiniCPM-2.4B","SigLIP-400M","2024/04/15",1808.2,1411.4,396.8],[157,"Mantis-8B-Idefics2",8.0,"Mistral-7B","SigLIP-400M","2024/08/08",1805.9,1480.1,325.7],[158,"Cambrian-8B",8.0,"Vicuna-v1.5-7B","CLIP ViT-L/14","2024/07/11",1802.9,1466.5,336.4],[159,"Aquila-VL-2B",2.2,"Qwen-2.5-1.5B","SigLIP-400M","2024/10/24",1801.1,1373.3,427.9],[160,"AKI-4B",4.33,"Phi-3.5","SigLIP-400M","2025/03/25",1795.6,1452.7,342.9],[161,"Slime-13B",13.0,"Vicuna-v1.5-13B","CLIP ViT-L/14","2024/09/14",1794.3,1492.2,302.1],[162,"SmolVLM2",2.25,"SmolLM2-1.7M","SigLIP-400M","2025/03/13",1792.5,1467.2,325.4],[163,"Janus-Pro-7B",7.42,"DeepSeek-7B","SigLIP-400M","2025/02/02",1791.7,1516.7,275.0],[164,"XGen-MM-Instruct-DPO-v1.5",4.4,"Phi-3","SigLIP-400M","2024/09/06",1790.5,1487.6,302.9],[165,"GPT-4v (1106, detail-high)",null,"","","2024/04/22",1790.3,1320.3,470.0],[166,"Slime-7B",7.0,"Vicuna-v1.5-7B","CLIP ViT-L/14","2024/09/14",1789.7,1471.2,318.6],[167,"GPT-4.1-nano-20250414",null,"","","2025/04/16",1789.6,1339.6,450.0],[168,"Eagle-X5-34B-Chat",36.8,"Yi-34B","Clip-448
ConvNeXT-1024
SAM-1024
DET-1024
Pix2Struct-1024","2024/11/29",1788.0,1451.3,336.8],[169,"mPLUG-Owl2",8.2,"Llama-2-7B","CLIP ViT-L/14","2023/11/10",1786.4,1436.0,350.4],[170,"Vintern-3B-beta",3.7,"Qwen-2.5-3B","InternViT-300M","2024/10/24",1782.6,1339.7,442.9],[171,"LLaVA-v1.5-13B",13.4,"Vicuna-v1.5-13B","CLIP ViT-L/14","2023/10/05",1780.8,1502.6,278.2],[172,"GPT-4v (1106, detail-low)",null,"","","2023/12/23",1771.5,1334.0,437.5],[173,"LLaVA-Next-Vicuna-7B",7.1,"Vicuna-v1.5-7B","CLIP ViT-L/14","2024/03/25",1769.1,1475.6,293.6],[174,"H2OVL-2B",2.2,"H2O-DANUBE2-1.8B","InternViT-300M","2024/10/31",1767.5,1418.2,349.3],[175,"Mantis-8B-clip-llama3",8.0,"Llama-3-8B-Instruct","CLIP ViT-L/14","2024/08/08",1766.0,1416.7,349.3],[176,"LLaVA-v1.5-13B (QLoRA)",13.4,"Vicuna-v1.5-13B","CLIP ViT-L/14","2023/12/28",1766.0,1475.3,290.7],[177,"DeepSeek-VL-7B",7.3,"DeekSeek-7B","SAM-B
SigLIP-L","2024/03/21",1765.4,1467.6,297.9],[178,"Llama-3-MixSense-v1.1",8.0,"Llama-3-8B-Instruct","Florence-2-Large-FT","2024/08/21",1761.0,1448.5,312.5],[179,"Monkey",9.8,"Qwen-7B","ViT-BigHuge","2024/01/11",1759.9,1471.7,288.2],[180,"LLaVA-Next-Interleave-7B",8.0,"Qwen-1.5-7B","SigLIP-400M","2024/08/08",1749.5,1463.8,285.7],[181,"LLaVA-Next-Vicuna-13B",13.4,"Vicuna-v1.5-13B","CLIP ViT-L/14","2024/03/25",1745.6,1448.4,297.1],[182,"Gemma3-4B",4.3,"Gemma3-4B","SigLIP-400M","2025/03/19",1744.1,1353.4,390.7],[183,"Llama-3.2-90B-Vision-Instruct",88.6,"Llama-3.1-70B","","2024/10/19",1741.0,1326.0,415.0],[184,"CogVLM-17B-Chat",17.0,"Vicuna-v1.5-7B","EVA2-CLIP-E","2024/01/03",1736.6,1437.7,298.9],[185,"Ovis2-1B",1.27,"Qwen2.5-0.5B","AIMv2 Large","2025/02/18",1719.5,1418.8,300.7],[186,"VILA1.5-13B",13.0,"Vicuna-v1.5-13B","SigLIP-400M","2024/08/25",1718.2,1429.3,288.9],[187,"LLaVA-v1.5-7B (QLoRA)",7.2,"Vicuna-v1.5-7B","CLIP ViT-L/14","2023/12/28",1716.6,1434.5,282.1],[188,"Molmo-7B-O",8.0,"Qwen2-7B","CLIP ViT-L/14","2024/10/20",1714.7,1410.4,304.3],[189,"LLaVA-InternLM2-7B (QLoRA)",8.1,"InternLM2-7B","CLIP ViT-L/14","2024/01/17",1699.5,1404.5,295.0],[190,"Llama-3-VILA1.5-8B",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/08/25",1698.5,1438.8,259.6],[191,"PaliGemma-3B-mix-448",3.0,"Gemma-2B","SigLIP-400M","2024/05/17",1686.1,1394.7,291.4],[192,"Emu2_chat",37.0,"Llama-33B","EVA-02-CLIP-E-plus","2024/01/17",1678.0,1345.1,332.9],[193,"abab6.5s",null,"","","2024/12/11",1675.7,1140.7,535.0],[194,"Mantis-8B-siglip-llama3",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/08/08",1674.6,1381.4,293.2],[195,"LLaVA-Next-Interleave-7B-DPO",8.0,"Qwen-1.5-7B","SigLIP-400M","2024/07/29",1664.4,1392.7,271.8],[196,"MiniCPM-V",3.0,"MiniCPM-2.4B","SigLIP-400M","2024/02/07",1650.2,1378.8,271.4],[197,"VILA1.5-3B",3.0,"Sheared-LLaMA-2.7B","SigLIP-400M","2024/08/25",1647.5,1379.3,268.2],[198,"ShareCaptioner",8.0,"InternLM-7B","EVA-G","2024/01/03",1642.5,1294.6,347.9],[199,"RekaEdge",null,"","","2024/05/31",1641.6,1357.3,284.3],[200,"SmolVLM-Instruct",2.3,"SmolLM2-1.7B","SigLIP-400M","2025/01/27",1641.0,1347.1,293.9],[201,"LLaVA-InternLM-7B (QLoRA)",7.6,"InternLM-7B","CLIP ViT-L/14","2023/12/28",1637.1,1392.8,244.3],[202,"Claude3-Sonnet",null,"","","2024/03/28",1625.9,1251.3,374.6],[203,"Emu3_chat",8.49,"","","2025/01/26",1610.5,1334.1,276.4],[204,"SmolVLM-Instruct-DPO",2.3,"SmolLM2-1.7B","SigLIP-400M","2025/01/27",1604.3,1334.0,270.4],[205,"Claude3-Opus",null,"","","2024/03/28",1586.8,1289.3,297.5],[206,"Janus-1.3B",2.1,"DeepSeek-1B","SigLIP-400M","2024/10/24",1578.5,1339.9,238.6],[207,"DeepSeek-VL-1.3B",2.0,"DeekSeek-1B","SAM-B
SigLIP-L","2024/03/21",1531.6,1306.6,225.0],[208,"Moondream2",1.9,"SigLIP-400M","Phi-1.5","2024/10/20",1528.3,1258.3,270.0],[209,"IDEFICS-80B-Instruct",80.0,"Llama-65B","CLIP ViT-H/14","2023/07/25",1518.2,1284.6,233.6],[210,"Phi-3-Vision",4.2,"Phi-3","CLIP ViT-L/14","2024/05/31",1508.0,1205.1,302.9],[211,"Moondream1",1.9,"SigLIP-400M","Phi-1.5","2024/09/26",1506.3,1244.1,262.1],[212,"MolmoE-1B",7.2,"OLMoE-1B-7B-0924","CLIP ViT-L/14","2024/10/21",1471.1,1201.1,270.0],[213,"H2OVL-800M",0.83,"H2O-DANUBE3-500M","InternViT-300M","2024/10/31",1468.9,1141.8,327.1],[214,"SmolVLM-Synthetic",2.3,"SmolLM2-1.7B","SigLIP-400M","2025/01/27",1459.4,1224.7,234.6],[215,"Claude3-Haiku",null,"","","2024/03/28",1453.2,1182.5,270.7],[216,"LLaVA-OneVision-0.5B",1.0,"Qwen2-0.5B","SigLIP-400M","2024/09/16",1448.5,1211.0,237.5],[217,"SmolVLM2-500M",0.51,"SmolLM2-360M","ViT-93M","2025/03/13",1448.3,1211.2,237.1],[218,"SmolVLM-500M",0.51,"SmolLM2-360M","ViT-93M","2025/01/27",1394.8,1157.6,237.1],[219,"LLaVA-OneVision-0.5B (SI)",1.0,"Qwen2-0.5B","SigLIP-400M","2024/09/17",1392.9,1169.6,223.2],[220,"InstructBLIP-7B",8.0,"Vicuna-7B","EVA-G","2023/05/11",1391.4,1137.1,254.3],[221,"MMAlaya",7.8,"Alaya-7B-Chat","EVA-G","2024/01/29",1356.0,1131.4,224.6],[222,"Mantis-8B-Fuyu",8.0,"Fuyu-8B","","2024/09/07",1321.6,1057.7,263.9],[223,"SmolVLM-256M",0.26,"SmolLM2-135M","ViT-93M","2025/01/27",1261.1,1037.8,223.2],[224,"SmolVLM2-256M",0.26,"SmolLM2-135M","ViT-93M","2025/03/13",1236.5,992.9,243.6],[225,"IDEFICS-9B-Instruct",9.0,"Llama-7B","CLIP ViT-H/14","2023/07/25",1177.3,942.0,235.4],[226,"LLaVA-v1-7B",7.2,"Llama-7B","CLIP ViT-L/14","2023/04/17",1075.5,832.0,243.6],[227,"PandaGPT-13B",14.0,"Vicuna-13B","ImageBind ViT-H/14","2023/05/25",1072.2,826.1,246.1],[228,"MiniGPT-4-v1-7B",8.0,"Vicuna-7B","EVA-G","2023/04/20",1047.4,770.6,276.8],[229,"MiniGPT-4-v2",8.0,"Llama-2-13B","EVA-G","2023/10/27",968.4,708.4,260.0],[230,"VisualGLM",8.0,"ChatGLM 6B","EVA-CLIP","2023/05/17",738.1,628.5,109.6],[231,"Kosmos2",1.7,"","","2024/10/19",721.1,519.7,201.4],[232,"OpenFlamingo v2",9.0,"MPT 7B","CLIP ViT-L/14","2023/06/28",607.2,535.0,72.1],[233,"Chameleon-30B",30.0,"","","2024/07/29",604.5,575.3,29.3],[234,"Qwen-VL",9.6,"Qwen-7B","ViT-G/16","2023/08/24",482.7,334.1,148.6],[235,"Chameleon-7B",7.0,"","","2024/07/29",202.7,153.1,49.6]],"metadata":null},"headers":["1","2","3"],"row_count":[1,"dynamic"],"col_count":[3,"dynamic"],"datatype":["number","html","number","html","html","str","number","number","number"],"type":"pandas","latex_delimiters":[{"left":"$$","right":"$$","display":true}],"show_label":true,"height":500,"min_width":160,"interactive":false,"visible":true,"elem_classes":[],"wrap":true,"line_breaks":true,"column_widths":[],"name":"dataframe","_selectable":false},"skip_api":false,"component_class_id":"6a51bb3357f2e94c40fb8d4fbe06aa8e","key":null,"api_info":{"properties":{"headers":{"items":{"type":"string"},"title":"Headers","type":"array"},"data":{"items":{"items":{},"type":"array"},"title":"Data","type":"array"},"metadata":{"anyOf":[{"additionalProperties":{"anyOf":[{"items":{},"type":"array"},{"type":"null"}]},"type":"object"},{"type":"null"}],"default":null,"title":"Metadata"}},"required":["headers","data"],"title":"DataframeData","type":"object"},"example_inputs":{"headers":["a","b"],"data":[["foo","bar"]]}},{"id":93,"type":"textbox","props":{"value":"MME","lines":1,"max_lines":20,"label":"MME","show_label":true,"container":true,"min_width":160,"visible":false,"autofocus":false,"autoscroll":true,"elem_classes":[],"type":"text","rtl":false,"show_copy_button":false,"name":"textbox","_selectable":false},"skip_api":false,"component_class_id":"d0491bb0fbd427bdb2a4549c4d1ac869","key":null,"api_info":{"type":"string"},"example_inputs":"Hello!!"},{"id":94,"type":"form","props":{"scale":0,"min_width":0,"name":"form"},"skip_api":true,"component_class_id":"43cda85c6ff7a5dd8f83d29496b014ee","key":null},{"id":95,"type":"form","props":{"scale":0,"min_width":0,"name":"form"},"skip_api":true,"component_class_id":"43cda85c6ff7a5dd8f83d29496b014ee","key":null},{"id":96,"type":"tabitem","props":{"label":"📊 MMVet Leaderboard","visible":true,"interactive":true,"id":9,"elem_id":"MMVet","name":"tab"},"skip_api":true,"component_class_id":"18f46968e2b273dc5dbda0fe78433d7e","key":null},{"id":97,"type":"markdown","props":{"value":"## MMVet Evaluation Results\n\n- In MMVet Evaluation, we use GPT-4-Turbo (gpt-4-1106-preview) as the judge LLM to assign scores to the VLM outputs. We only perform the evaluation once due to the limited variance among results of multiple evaluation pass originally reported. \n- No specific prompt template adopted for **ALL VLMs**.\n- We also provide performance on the [**Official Leaderboard**](https://paperswithcode.com/sota/visual-question-answering-on-mm-vet) for models that are applicable. Those results are obtained with GPT-4-0314 evaluator (which has been deperacted for new users). ","show_label":true,"rtl":false,"latex_delimiters":[{"left":"$$","right":"$$","display":true}],"visible":true,"elem_classes":[],"sanitize_html":true,"line_breaks":false,"header_links":false,"show_copy_button":false,"name":"markdown","_selectable":false},"skip_api":false,"component_class_id":"0f35515b9a3362b42bb6721c836157a0","key":null,"api_info":{"type":"string"},"example_inputs":"# Hello!"},{"id":98,"type":"checkboxgroup","props":{"choices":[["Overall","Overall"],["Overall (official)","Overall (official)"],["Rec","Rec"],["Ocr","Ocr"],["Know","Know"],["Gen","Gen"],["Spat","Spat"],["Math","Math"]],"value":["Overall","Overall (official)"],"type":"value","label":"MMVet CheckBoxes","show_label":true,"container":true,"min_width":160,"interactive":true,"visible":true,"elem_classes":[],"name":"checkboxgroup","_selectable":false},"skip_api":false,"component_class_id":"0635a5d3bf87369f1c2c1c69f8a3d0cc","key":null,"api_info":{"items":{"enum":["Overall","Overall (official)","Rec","Ocr","Know","Gen","Spat","Math"],"type":"string"},"title":"Checkbox Group","type":"array"},"example_inputs":["Overall"]},{"id":99,"type":"row","props":{"variant":"default","visible":true,"equal_height":true,"show_progress":false,"name":"row"},"skip_api":true,"component_class_id":"b5cf3d15e2293fb5ccc071d7b8d69f64","key":null},{"id":100,"type":"textbox","props":{"value":"Input the Model Name (fuzzy, case insensitive)","lines":1,"max_lines":20,"label":"Model Name","show_label":true,"container":true,"min_width":160,"interactive":true,"visible":true,"autofocus":false,"autoscroll":true,"elem_classes":[],"type":"text","rtl":false,"show_copy_button":false,"name":"textbox","_selectable":false},"skip_api":false,"component_class_id":"d0491bb0fbd427bdb2a4549c4d1ac869","key":null,"api_info":{"type":"string"},"example_inputs":"Hello!!"},{"id":101,"type":"checkboxgroup","props":{"choices":[["<4B","<4B"],["4B-10B","4B-10B"],["10B-20B","10B-20B"],["20B-40B","20B-40B"],[">40B",">40B"],["Unknown","Unknown"]],"value":["<4B","4B-10B","10B-20B","20B-40B",">40B","Unknown"],"type":"value","label":"Model Size","show_label":true,"container":true,"min_width":160,"interactive":true,"visible":true,"elem_classes":[],"name":"checkboxgroup","_selectable":false},"skip_api":false,"component_class_id":"0635a5d3bf87369f1c2c1c69f8a3d0cc","key":null,"api_info":{"items":{"enum":["<4B","4B-10B","10B-20B","20B-40B",">40B","Unknown"],"type":"string"},"title":"Checkbox Group","type":"array"},"example_inputs":["<4B"]},{"id":102,"type":"checkboxgroup","props":{"choices":[["API","API"],["OpenSource","OpenSource"]],"value":["API","OpenSource"],"type":"value","label":"Model Type","show_label":true,"container":true,"min_width":160,"interactive":true,"visible":true,"elem_classes":[],"name":"checkboxgroup","_selectable":false},"skip_api":false,"component_class_id":"0635a5d3bf87369f1c2c1c69f8a3d0cc","key":null,"api_info":{"items":{"enum":["API","OpenSource"],"type":"string"},"title":"Checkbox Group","type":"array"},"example_inputs":["API"]},{"id":103,"type":"form","props":{"scale":3,"min_width":480,"name":"form"},"skip_api":true,"component_class_id":"43cda85c6ff7a5dd8f83d29496b014ee","key":null},{"id":104,"type":"dataframe","props":{"value":{"headers":["Rank","Method","Param (B)","Language Model","Vision Model","Eval Date","Overall","Overall (official)"],"data":[[1,"SenseNova-V6-5-Pro",null,"","","2025/09/03",89.4,"N/A"],[2,"SenseNova-V6-Pro",null,"","","2025/05/05",88.2,"N/A"],[3,"CongRong-v2.0",null,"","","2025/05/20",83.9,"N/A"],[4,"Gemini-2.5-Pro",null,"","","2025/04/07",83.3,"N/A"],[5,"InternVL3-8B",7.94,"Qwen2.5-7B","InternViT-300M-v2.5","2025/04/14",82.8,"N/A"],[6,"Step-1o",null,"","","2025/01/13",82.8,"N/A"],[7,"InternVL3-38B",38.4,"Qwen2.5-32B","InternViT-6B-v2.5","2025/04/14",81.1,"N/A"],[8,"InternVL3-78B",78.4,"Qwen2.5-72B","InternViT-6B-v2.5","2025/04/14",80.7,"N/A"],[9,"InternVL3-14B",15.1,"Qwen2.5-14B","InternViT-300M-v2.5","2025/04/14",80.5,"N/A"],[10,"JT-VL-Chat-V3.0",null,"","","2025/08/04",80.3,"N/A"],[11,"HunYuan-Standard-Vision",null,"","","2025/01/15",79.9,"N/A"],[12,"GPT-4.1-20250414",null,"","","2025/04/16",78.8,"N/A"],[13,"Ola-7b",8.88,"Qwen2.5-7B","Oryx-ViT","2025/02/05",78.6,"N/A"],[14,"BlueLM-2.6-3B",3.0,"","","2025/09/17",78.5,"N/A"],[15,"InternVL3-9B",9.14,"InternLM3-8B","InternViT-300M-v2.5","2025/04/14",78.4,"N/A"],[16,"SenseNova",null,"","","2024/12/12",78.2,"N/A"],[17,"GPT-5-20250807",null,"","","2025/08/14",77.6,"N/A"],[18,"BailingMM-Pro-0120",81.0,"Bailing-80B","SigLIP-400M","2025/01/25",77.6,"N/A"],[19,"Ovis2-34B",34.9,"Qwen2.5-32B","AIMv2-1B","2025/02/18",77.1,"N/A"],[20,"Kimi-VL-A3B-Thinking-2506",16.4,"Moonlight-16B-A3B","MoonViT","2025/07/02",77.0,"N/A"],[21,"ChatGPT-4o-latest",null,"","","2025/04/07",76.9,"N/A"],[22,"Qwen2.5-VL-72B",73.4,"Qwen2.5-72B","QwenViT","2025/02/02",76.9,"N/A"],[23,"R-4B",4.82,"Qwen3-4B","SigLip-400M","2025/08/11",76.2,"N/A"],[24,"GLM-4v-Plus-20250111",null,"","","2025/01/25",75.7,"N/A"],[25,"TeleMM",null,"","","2024/12/31",75.7,"N/A"],[26,"GPT-4.5",null,"","","2025/03/26",75.3,"N/A"],[27,"GPT-4o (0806, detail-high)",null,"","","2024/08/08",75.1,"N/A"],[28,"Gemini-1.5-Pro-002",null,"","","2024/12/02",74.6,"N/A"],[29,"GPT-5-mini-20250807",null,"","","2025/08/14",74.6,"N/A"],[30,"GPT-4o (1120, detail-high)",null,"","","2024/12/02",74.5,"N/A"],[31,"GPT-4.1-mini-20250414",null,"","","2025/04/16",74.3,"N/A"],[32,"Qwen2-VL-72B",73.4,"Qwen2-72B","QwenViT","2024/10/28",73.9,"N/A"],[33,"Gemini-2.0-Flash",null,"","","2025/01/02",73.6,"N/A"],[34,"InternVL2.5-78B-MPO",78.0,"Qwen-2.5-72B","InternViT-6B-v2.5","2024/12/29",73.5,"N/A"],[35,"SAIL-VL-1.6-8B",8.33,"Qwen2.5-7B","AIMv2 Huge","2025/04/24",73.3,"N/A"],[36,"WeThink-Qwen2.5VL-7B",8.29,"Qwen2.5-7B","QwenViT","2025/05/26",73.2,"N/A"],[37,"Qwen2.5-VL-32B",33.5,"Qwen2.5-32B","QwenViT","2025/07/02",72.9,"N/A"],[38,"InternVL2.5-38B-MPO",38.0,"Qwen-2.5-32B","InternViT-6B-v2.5","2024/12/28",72.6,"N/A"],[39,"Qwen-VL-Max-0809",72.0,"Qwen2-72B","QwenViT","2024/09/12",72.3,"N/A"],[40,"MiMo-VL-7B",8.31,"Mimo-7B","Qwen2.5-ViT","2025/07/02",72.2,"N/A"],[41,"Step-1.5V",null,"Step-1.5","stepencoder","2024/10/11",71.3,"N/A"],[42,"Gemma3-27B",27.4,"Gemma3-27B","SigLIP-400M","2025/03/19",71.0,"N/A"],[43,"Gemini-2.0-Pro",null,"","","2025/02/27",70.4,"N/A"],[44,"Claude3.5-Sonnet-20241022",null,"","","2024/11/06",70.1,"N/A"],[45,"Claude3.7-Sonnet",null,"","","2025/02/27",70.0,"N/A"],[46,"Qwen2.5-VL-7B",8.29,"Qwen2.5-7B","QwenViT","2025/02/02",69.7,"N/A"],[47,"Gemini-1.5-Flash-002",null,"","","2024/12/02",69.7,"N/A"],[48,"GPT-4o (0513, detail-high)",null,"","","2024/05/31",69.1,"N/A"],[49,"GLM-4v-Plus",null,"","","2024/12/11",69.1,"N/A"],[50,"SAIL-VL-1.5-8B",7.95,"Qwen2.5-7B","InternViT-300B","2025/04/23",69.0,"N/A"],[51,"VARCO-VISION-2.0-14B",15.2,"Qwen3-14B","SigLIP-400M","2025/08/04",68.9,"N/A"],[52,"Ovis2-16B",16.2,"Qwen2.5-14B","AIMv2 Huge","2025/02/18",68.4,"N/A"],[53,"InternVL2.5-26B-MPO",26.0,"InternLM2.5-20B","InternViT-6B-v2.5","2024/12/28",68.1,"N/A"],[54,"InternVL2.5-8B-MPO",8.0,"InternLM2.5-7B","InternViT-300M-v2.5","2024/12/28",68.1,"N/A"],[55,"Ovis1.6-Gemma2-27B",28.9,"Gemma2-27B","SigLIP-400M","2024/11/29",68.0,"N/A"],[56,"Taiyi",null,"","","2024/12/11",67.9,"N/A"],[57,"GPT-4v (0409, detail-high)",null,"","","2024/05/15",67.5,"N/A"],[58,"GPT-5-nano-20250807",null,"","","2025/08/14",67.4,"N/A"],[59,"Kimi-VL-A3B-Thinking",16.4,"Moonlight-16B-A3B","MoonViT","2025/04/23",67.4,"N/A"],[60,"MiniCPM-o-2.6",8.67,"Qwen2.5-7B","SigLIP-400M","2025/01/21",67.2,"N/A"],[61,"InternVL2.5-38B",38.0,"Qwen-2.5-32B","InternViT-6B-v2.5","2024/12/10",67.2,"N/A"],[62,"InternVL3-2B",2.09,"Qwen2.5-1.5B","InternViT-300M-v2.5","2025/04/14",67.0,"N/A"],[63,"GPT-4o-mini (0718, detail-high)",null,"","","2024/07/20",66.9,"N/A"],[64,"GPT-4o (0513, detail-low)",null,"","","2024/05/15",66.5,"N/A"],[65,"Step-1.5V-mini",null,"","","2024/12/11",66.5,"N/A"],[66,"Kimi-VL-A3B-Instruct",16.4,"Moonlight-16B-A3B","MoonViT","2025/04/14",66.1,"N/A"],[67,"InternVL2.5-4B-MPO",4.0,"Qwen-2.5-3B","InternViT-300M-v2.5","2024/12/28",66.0,"N/A"],[68,"Claude3.5-Sonnet",null,"","","2024/06/24",66.0,"N/A"],[69,"Ovis-U1-3B",3.64,"Qwen3-1.7B","aimv2-large-path14-448","2025/07/20",66.0,"N/A"],[70,"QTuneVL1.5-2B",2.09,"Qwen2.5-1.5B","InternViT-300M-v2.5","2025/08/11",65.9,"N/A"],[71,"Ovis2-4B",4.62,"Qwen2.5-3B","AIMv2 Huge","2025/02/18",65.5,"N/A"],[72,"InternVL2.5-26B",26.0,"InternLM2.5-20B","InternViT-6B-v2.5","2024/12/10",65.4,"N/A"],[73,"grok-2-vision-1212",null,"","","2025/03/03",65.2,"N/A"],[74,"Ovis2-8B",8.94,"Qwen2.5-7B","AIMv2 Huge","2025/02/18",65.1,"N/A"],[75,"Ovis1.6-Gemma2-9B",10.2,"Gemma2-9B-It","SigLIP-400M","2024/09/19",65.0,"N/A"],[76,"Gemma3-12B",12.2,"Gemma3-12B","SigLIP-400M","2025/03/19",64.9,"N/A"],[77,"BailingMM-Lite-1203",21.0,"Bailing-20B","SigLIP-400M","2024/12/08",64.9,"N/A"],[78,"InternVL2-Llama3-76B",76.0,"Llama-3-70B-Instruct","InternViT-6B","2024/07/19",64.4,"N/A"],[79,"InternVL2.5-2B-MPO",2.0,"InternLM2.5-1.8B","InternViT-300M-v2.5","2024/12/28",64.2,"N/A"],[80,"Llama-3.2-90B-Vision-Instruct",88.6,"Llama-3.1-70B","","2024/10/19",64.1,"N/A"],[81,"Gemini-1.5-Pro",null,"","","2024/06/10",64.0,"N/A"],[82,"abab7-preview",null,"","","2024/12/11",63.7,"N/A"],[83,"GPT-4v (0409, detail-low)",null,"","","2024/05/15",63.6,"N/A"],[84,"Gemini-1.5-Flash",null,"","","2024/09/16",63.2,"N/A"],[85,"MUG-U-7B",7.0,"","","2025/03/19",63.0,"N/A"],[86,"QTuneVL1-2B",2.21,"InternLM2.5-1.8B","InternViT-300M-v2.5","2025/05/05",63.0,"N/A"],[87,"InternVL2.5-8B",8.0,"InternLM2.5-7B","InternViT-300M-v2.5","2024/12/10",62.8,"N/A"],[88,"GPT-4.1-nano-20250414",null,"","","2025/04/16",62.8,"N/A"],[89,"QTuneVL1.5-3B",3.75,"Qwen2.5-3B","QwenViT","2025/08/11",62.8,"N/A"],[90,"InternVL2.5-2B",2.0,"InternLM2.5-1.8B","InternViT-300M-v2.5","2024/12/10",62.6,"N/A"],[91,"valley2_dpo",8.88,"Qwen2.5-7B","SigLIP-400M","2025/05/30",62.3,"N/A"],[92,"POINTS1.5-Qwen2.5-7B",8.3,"Qwen-2.5-7B","NaViT","2024/12/06",62.2,"N/A"],[93,"valley2",8.88,"Qwen2.5-7B","SigLIP-400M","2025/05/30",62.1,"N/A"],[94,"InternVL2-40B",40.0,"Nous-Hermes-2-Yi-34B","InternViT-6B","2024/07/11",61.8,"N/A"],[95,"BlueLM-V-3B",3.0,"BlueLM-3B","SigLIP-400M","2024/10/30",61.8,"N/A"],[96,"Qwen2-VL-7B",8.0,"Qwen2-7B","QwenViT","2024/09/12",61.8,"N/A"],[97,"Qwen-VL-Max",null,"QwenLM","","2024/02/02",61.8,"N/A"],[98,"BlueLM-2.5-3B",2.9,"BlueLM-base-3B","Siglip2-So400M","2025/07/16",61.7,"N/A"],[99,"InternVL2.5-4B",4.0,"Qwen-2.5-3B","InternViT-300M-v2.5","2024/12/10",61.5,"N/A"],[100,"Valley-Eagle",8.9,"Qwen2.5-7B","Qwen-ViT
SigLIP-400M","2024/12/29",61.3,"N/A"],[101,"Molmo-72B",73.3,"Qwen2-72B","CLIP ViT-L/14","2024/10/28",61.1,"N/A"],[102,"Ristretto-3B",3.84,"Qwen2.5-3B","SigLIP-400M","2025/04/01",60.7,"N/A"],[103,"GLM-4v",null,"","","2024/05/20",60.7,"N/A"],[104,"LLaVA-OneVision-72B",73.0,"Qwen2-72B","SigLIP-400M","2024/09/19",60.6,"N/A"],[105,"DeepSeek-VL2",27.5,"DeepSeekMoE-27B","SigLIP-400M","2025/01/01",60.0,"N/A"],[106,"MiniCPM-V-2.6",8.0,"Qwen2-7B","SigLIP-400M","2024/08/08",60.0,"N/A"],[107,"InternVL2-26B",26.0,"InternLM2-20B","InternViT-6B","2024/07/11",60.0,"N/A"],[108,"Qwen2.5-VL-3B",3.75,"Qwen2.5-3B","QwenViT","2025/02/02",60.0,"N/A"],[109,"Qwen-VL-Plus-0809",null,"","","2024/09/17",59.6,"N/A"],[110,"LLaVA-CoT",11.0,"","","2025/01/05",59.5,"N/A"],[111,"bailingMM-mini",17.0,"bailing-mini","bailingMM-encoder-1B
InternViT-6B","2024/10/24",59.2,"N/A"],[112,"LLaVA-OneVision-72B (SI)",73.0,"Qwen2-72B","SigLIP-400M","2024/09/19",59.1,"N/A"],[113,"NVLM-D-72B",79.4,"Qwen2-72B","InternViT-6B","2024/10/19",58.9,"N/A"],[114,"SAIL-VL-1.5-2B",2.47,"Qwen2.5-1.5B","AIMv2 Huge","2025/04/23",58.8,"N/A"],[115,"InternVL3-1B",0.94,"Qwen2.5-0.5B","InternViT-300M-v2.5","2025/04/14",58.7,"N/A"],[116,"DeepSeek-VL2-Small",16.1,"DeepSeekMoE-16B","SigLIP-400M","2025/01/01",58.6,"N/A"],[117,"Gemini-1.0-Pro",null,"","","2023/12/23",58.6,"N/A"],[118,"Pixtral-12B",13.0,"Nemo-12B","ViT-400M","2024/09/16",58.5,"N/A"],[119,"MMAlaya2",26.0,"InternLM2-20B","InternViT-6B","2024/08/27",58.5,"N/A"],[120,"Ovis2-2B",2.46,"Qwen2.5-1.5B","AIMv2 Large","2025/02/18",58.3,"N/A"],[121,"GLM-4v-9B",9.0,"GLM-4-9B","EVA-02-5B","2024/06/14",58.0,"N/A"],[122,"CogVLM2-19B-Chat",19.0,"Llama-3-8B-Instruct","EVA2-CLIP-E","2024/05/31",57.8,"N/A"],[123,"Gemma3-4B",4.3,"Gemma3-4B","SigLIP-400M","2025/03/19",57.8,"N/A"],[124,"Ovis1.6-Llama3.2-3B",4.1,"Llama-3.2-3B","SigLIP-400M","2024/10/24",57.6,"N/A"],[125,"Yi-Vision",null,"","","2024/08/03",57.6,"N/A"],[126,"Llama-3.2-11B-Vision-Instruct",11.0,"Llama-3.1-8B","","2024/10/07",57.6,"N/A"],[127,"CongRong",null,"","","2024/06/26",57.5,"N/A"],[128,"Aria",25.3,"Aria-MoE","SigLIP-400M","2024/12/05",56.9,"N/A"],[129,"GPT-4v (1106, detail-low)",null,"","","2023/12/23",56.8,"N/A"],[130,"InternVL2-8B-MPO",8.0,"InternLM2.5-7B","InternViT-300M","2024/11/25",55.8,"N/A"],[131,"Qwen-VL-Plus",null,"QwenLM","","2024/01/10",55.7,"N/A"],[132,"InternVL2-8B-MPO-CoT",8.0,"InternLM2.5-7B","InternViT-300M","2024/11/25",55.7,"N/A"],[133,"InternVL-Chat-V1.5",26.0,"InternLM2-20B","InternViT-6B","2024/04/17",55.4,"N/A"],[134,"CogVLM-17B-Chat",17.0,"Vicuna-v1.5-7B","EVA2-CLIP-E","2024/01/03",54.5,"N/A"],[135,"InternVL2-8B",8.0,"InternLM2.5-7B","InternViT-300M","2024/07/11",54.3,"N/A"],[136,"Ovis1.5-Gemma2-9B",11.4,"Gemma2-9B-It","SigLIP-400M","2024/08/04",53.8,"N/A"],[137,"VARCO-VISION-2.0-1.7B",2.12,"Qwen3-1.7B","SigLIP-400M","2025/08/04",53.4,"N/A"],[138,"Cambrian-34B",34.0,"Nous-Hermes-2-Yi-34B","CLIP ViT-L/14","2024/07/18",53.2,"N/A"],[139,"VARCO-VISION-14B",15.2,"Qwen2.5-14B","SigLIP-400M","2025/01/02",53.0,"N/A"],[140,"MiniCPM-Llama3-V2.5",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/05/27",52.8,"N/A"],[141,"VITA-1.5",8.3,"Qwen2-7B","InternViT-300M","2025/01/01",52.7,"N/A"],[142,"OmChat-v2.0-13B",13.0,"Qwen2-7B","InternViT-6B","2024/08/22",52.6,"N/A"],[143,"DeepSeek-VL2-Tiny",3.4,"DeepSeekMoE-3B","SigLIP-400M","2025/01/01",52.5,"N/A"],[144,"RekaFlash",null,"","","2024/05/07",52.5,"N/A"],[145,"moonshot-v1-8k",null,"","","2025/03/03",52.0,"N/A"],[146,"Phi-4-MultiModal",5.57,"Phi-4-Mini","SigLIP-400M","2025/03/13",51.9,"N/A"],[147,"LLaVA-OneVision-7B",8.0,"Qwen2-7B","SigLIP-400M","2024/09/16",51.9,"N/A"],[148,"Claude3-Sonnet",null,"","","2024/03/28",51.7,"N/A"],[149,"Claude3-Opus",null,"","","2024/03/28",51.7,"N/A"],[150,"Qwen2-VL-2B",2.0,"Qwen2-1.5B","QwenViT","2024/09/12",51.5,"N/A"],[151,"VILA1.5-40B",40.0,"Yi-34B","InternViT-6B","2024/08/25",51.2,"N/A"],[152,"InternVL2-4B",4.0,"Phi-3","InternViT-300M","2024/07/11",50.9,"N/A"],[153,"Ovis1.5-Llama3-8B",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/07/29",50.9,"N/A"],[154,"LLaVA-Next-Yi-34B",34.8,"Yi-34B","CLIP ViT-L/14","2024/03/25",50.7,"N/A"],[155,"LLaVA-OneVision-7B (SI)",8.0,"Qwen2-7B","SigLIP-400M","2024/09/17",50.6,"N/A"],[156,"RBDash-v1.5",79.0,"Qwen2-72B","CLIP ViT-L/14
InternViT-6B","2024/11/17",50.0,"N/A"],[157,"LLaVA-Next-Qwen-32B",33.0,"Qwen-1.5-32B","SigLIP-400M","2024/08/08",50.0,"N/A"],[158,"Ovis2-1B",1.27,"Qwen2.5-0.5B","AIMv2 Large","2025/02/18",50.0,"N/A"],[159,"InternLM-XComposer2.5",8.0,"InternLM2-7B","CLIP ViT-L/14","2024/07/11",49.3,"N/A"],[160,"POINTS-Yi-1.5-9B",9.5,"Yi-1.5-9B","CLIP ViT-L/14","2024/10/11",49.2,"N/A"],[161,"GPT-4v (1106, detail-high)",null,"","","2024/04/22",49.0,"N/A"],[162,"Cambrian-13B",13.0,"Vicuna-v1.5-13B","CLIP ViT-L/14","2024/07/29",48.9,"N/A"],[163,"Flash-VL-2B-Dynamic-ISS",2.53,"Qwen-2.5-1.5B-Instruct","SigLIP2-400M-512","2025/05/30",48.6,"N/A"],[164,"InternLM-XComposer2-4KHD",7.0,"InternLM2-7B","CLIP ViT-L/14","2024/06/09",48.2,"N/A"],[165,"Cambrian-8B",8.0,"Vicuna-v1.5-7B","CLIP ViT-L/14","2024/07/11",48.0,"N/A"],[166,"POINTS-Qwen2.5-7B",8.3,"Qwen-2.5-7B","CLIP ViT-L/14","2024/10/19",47.9,"N/A"],[167,"OmniLMM-12B",12.0,"Zephyr-7B-β","EVA-02-5B","2024/02/07",47.4,"N/A"],[168,"Qwen-VL-Chat",9.6,"Qwen-7B","ViT-G/16","2023/08/24",47.3,"N/A"],[169,"InternVL2.5-1B",1.0,"Qwen-2.5-0.5B","InternViT-300M-v2.5","2024/12/10",47.2,"N/A"],[170,"InternVL2.5-1B-MPO",1.0,"Qwen-2.5-0.5B","InternViT-300M-v2.5","2024/12/28",47.2,"N/A"],[171,"InternLM-XComposer2",7.0,"InternLM2-7B","CLIP ViT-L/14","2024/01/26",46.7,"N/A"],[172,"Claude3-Haiku",null,"","","2024/03/28",46.4,"N/A"],[173,"Janus-Pro-7B",7.42,"DeepSeek-7B","SigLIP-400M","2025/02/02",45.1,"N/A"],[174,"granite-vision-3.3-2b",2.98,"granite-3.1-2b-instruct","SigLIP2-400M","2025/06/20",45.0,"N/A"],[175,"VILA1.5-13B",13.0,"Vicuna-v1.5-13B","SigLIP-400M","2024/08/25",45.0,"N/A"],[176,"WeMM",7.0,"InternLM2-7B","SigLIP-400M","2024/06/09",45.0,"N/A"],[177,"LLaVA-Next-Vicuna-13B",13.4,"Vicuna-v1.5-13B","CLIP ViT-L/14","2024/03/25",44.9,"N/A"],[178,"LLaVA-Next-Llama3",8.0,"Llama-3-8B-Instruct","CLIP ViT-L/14","2024/07/29",44.4,"N/A"],[179,"SAIL-VL-2B",2.1,"Qwen2.5-1.5B","InternViT-300M","2024/12/25",44.2,"N/A"],[180,"Phi-3-Vision",4.2,"Phi-3","CLIP ViT-L/14","2024/05/31",44.1,"N/A"],[181,"Aquila-VL-2B",2.2,"Qwen-2.5-1.5B","SigLIP-400M","2024/10/24",43.8,"N/A"],[182,"Mini-InternVL-Chat-4B-V1.5",4.0,"Phi-3","InternViT-300M","2024/06/10",43.6,"N/A"],[183,"Ross-Qwen2-7B",8.2,"Qwen2-7B","CLIP ViT-L/14","2025/01/17",43.2,"N/A"],[184,"VITA",47.0,"Mixtral-8x7B","InternViT-300M","2025/01/20",43.2,"N/A"],[185,"Phi-3.5-Vision",4.0,"Phi-3.5","CLIP ViT-L/14","2024/08/28",43.2,"N/A"],[186,"Eagle-X5-13B",15.0,"Vicuna-v1.5-13B","Clip-448
ConvNeXT-1024
SAM-1024
DET-1024
Pix2Struct-1024","2024/09/26",42.6,"N/A"],[187,"Eagle-X5-34B-Chat",36.8,"Yi-34B","Clip-448
ConvNeXT-1024
SAM-1024
DET-1024
Pix2Struct-1024","2024/11/29",42.4,"N/A"],[188,"XinYuan-VL-2B-Instruct",2.0,"Qwen2-1.5B","QwenViT","2024/09/27",42.3,"N/A"],[189,"LLaVA-Next-Mistral-7B",7.6,"Mistral-7B","CLIP ViT-L/14","2024/03/25",42.2,"N/A"],[190,"Llama-3-VILA1.5-8B",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/08/25",41.9,"N/A"],[191,"Idefics3-8B-Llama3",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/08/27",41.7,"N/A"],[192,"Molmo-7B-D",8.0,"Qwen2-7B","CLIP ViT-L/14","2024/10/12",41.5,"N/A"],[193,"H2OVL-2B",2.2,"H2O-DANUBE2-1.8B","InternViT-300M","2024/10/31",41.1,"N/A"],[194,"Llama-3-MixSense-v1.1",8.0,"Llama-3-8B-Instruct","Florence-2-Large-FT","2024/08/21",41.1,"N/A"],[195,"ShareGPT4V-13B",13.4,"Vicuna-v1.5-13B","CLIP ViT-L/14","2023/12/08",41.1,43.1],[196,"XGen-MM-Instruct-DPO-v1.5",4.4,"Phi-3","SigLIP-400M","2024/09/06",41.0,"N/A"],[197,"MiniCPM-V-2",2.8,"MiniCPM-2.4B","SigLIP-400M","2024/04/15",41.0,"N/A"],[198,"Monkey-Chat",9.8,"Qwen-7B","ViT-BigHuge","2024/01/16",41.0,"N/A"],[199,"Molmo-7B-O",8.0,"Qwen2-7B","CLIP ViT-L/14","2024/10/20",40.6,"N/A"],[200,"RekaEdge",null,"","","2024/05/31",40.5,"N/A"],[201,"granite-vision-3.2-2b",2.98,"granite-3.1-2b-instruct","SigLip","2025/06/20",40.5,"N/A"],[202,"Moondream2",1.9,"SigLIP-400M","Phi-1.5","2024/10/20",40.4,"N/A"],[203,"LLaVA-Next-Vicuna-7B",7.1,"Vicuna-v1.5-7B","CLIP ViT-L/14","2024/03/25",40.2,"N/A"],[204,"XGen-MM-Instruct-Interleave-v1.5",4.4,"Phi-3","SigLIP-400M","2024/09/06",40.2,"N/A"],[205,"Slime-8B",8.0,"Llama-3-8B-Instruct","CLIP ViT-L/14","2024/09/14",40.0,"N/A"],[206,"LLaVA-Next-Interleave-7B-DPO",8.0,"Qwen-1.5-7B","SigLIP-400M","2024/07/29",39.8,"N/A"],[207,"IDEFICS-80B-Instruct",80.0,"Llama-65B","CLIP ViT-H/14","2023/07/25",39.7,"N/A"],[208,"DeepSeek-VL-7B",7.3,"DeekSeek-7B","SAM-B
SigLIP-L","2024/03/21",39.7,"N/A"],[209,"InternVL2-2B",2.0,"InternLM2-1.8B","InternViT-300M","2024/07/11",39.7,"N/A"],[210,"granite-vision-3.1-2b-preview",2.98,"granite-3.1-2b-instruct","SigLip","2025/06/20",39.6,"N/A"],[211,"Mantis-8B-Idefics2",8.0,"Mistral-7B","SigLIP-400M","2024/08/08",39.3,"N/A"],[212,"LLaVA-Next-Interleave-7B",8.0,"Qwen-1.5-7B","SigLIP-400M","2024/08/08",39.1,"N/A"],[213,"Bunny-Llama3-8B",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/07/18",39.1,"N/A"],[214,"HawkVL-2B",2.44,"Qwen2.5-1.5B","QwenViT","2025/06/16",38.9,"N/A"],[215,"Slime-13B",13.0,"Vicuna-v1.5-13B","CLIP ViT-L/14","2024/09/14",38.9,"N/A"],[216,"VILA1.5-3B",3.0,"Sheared-LLaMA-2.7B","SigLIP-400M","2024/08/25",38.8,"N/A"],[217,"Monkey",9.8,"Qwen-7B","ViT-BigHuge","2024/01/11",38.1,"N/A"],[218,"MiniMonkey",2.2,"InternLM2-1.8B","InternViT-300M","2024/09/26",38.0,"N/A"],[219,"XVERSE-V-13B",13.0,"XVERSE-13B","CLIP ViT-L/14","2024/05/10",37.8,"N/A"],[220,"MolmoE-1B",7.2,"OLMoE-1B-7B-0924","CLIP ViT-L/14","2024/10/21",37.8,"N/A"],[221,"Vintern-3B-beta",3.7,"Qwen-2.5-3B","InternViT-300M","2024/10/24",37.8,"N/A"],[222,"Janus-1.3B",2.1,"DeepSeek-1B","SigLIP-400M","2024/10/24",37.5,"N/A"],[223,"LLaVA-InternLM2-20B (QLoRA)",20.2,"InternLM2-20B","CLIP ViT-L/14","2024/01/17",37.2,"N/A"],[224,"Falcon2-VLM-11B",11.4,"Falcon2-11B","CLIP ViT-L/14","2024/10/30",37.2,"N/A"],[225,"TransCore-M",13.4,"PCITransGPT-13B","CLIP ViT-L/14","2024/04/16",36.9,"N/A"],[226,"AKI-4B",4.33,"Phi-3.5","SigLIP-400M","2025/03/25",36.2,"N/A"],[227,"LLaVA-InternLM2-7B (QLoRA)",8.1,"InternLM2-7B","CLIP ViT-L/14","2024/01/17",35.9,"N/A"],[228,"LLaVA-v1.5-13B (QLoRA)",13.4,"Vicuna-v1.5-13B","CLIP ViT-L/14","2023/12/28",35.9,"N/A"],[229,"mPLUG-Owl2",8.2,"Llama-2-7B","CLIP ViT-L/14","2023/11/10",35.7,"36.3±0.1"],[230,"LLaVA-v1.5-13B",13.4,"Vicuna-v1.5-13B","CLIP ViT-L/14","2023/10/05",35.6,"36.3±0.2"],[231,"Mini-InternVL-Chat-2B-V1.5",2.0,"InternLM2-1.8B","InternViT-300M","2024/06/10",35.5,"N/A"],[232,"InternLM-XComposer",8.0,"InternLM-7B","EVA-G","2023/09/26",35.2,"N/A"],[233,"SmolVLM2",2.25,"SmolLM2-1.7M","SigLIP-400M","2025/03/13",34.9,"N/A"],[234,"Mantis-8B-siglip-llama3",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/08/08",34.4,"N/A"],[235,"LLaVA-LLaMA-3-8B",8.0,"Llama-3-8B-Instruct","CLIP ViT-L/14","2024/05/07",34.1,"N/A"],[236,"IDEFICS2-8B",8.0,"Mistral-7B","SigLIP-400M","2024/04/26",34.0,"N/A"],[237,"Slime-7B",7.0,"Vicuna-v1.5-7B","CLIP ViT-L/14","2024/09/14",33.9,"N/A"],[238,"SmolVLM-Instruct",2.3,"SmolLM2-1.7B","SigLIP-400M","2025/01/27",33.8,"N/A"],[239,"ShareGPT4V-7B",7.2,"Vicuna-v1.5-7B","CLIP ViT-L/14","2023/12/08",33.4,37.6],[240,"Eagle-X5-7B",9.0,"Vicuna-v1.5-7B","Clip-448
ConvNeXT-1024
SAM-1024
DET-1024
Pix2Struct-1024","2024/09/26",33.3,"N/A"],[241,"InstructBLIP-7B",8.0,"Vicuna-7B","EVA-G","2023/05/11",33.1,"26.2±0.2"],[242,"PaliGemma-3B-mix-448",3.0,"Gemma-2B","SigLIP-400M","2024/05/17",33.1,"N/A"],[243,"LLaVA-v1.5-7B",7.2,"Vicuna-v1.5-7B","CLIP ViT-L/14","2023/10/05",32.9,"31.1±0.2"],[244,"Yi-VL-34B",34.6,"Yi-34B","CLIP ViT-H/14","2024/01/25",32.7,"N/A"],[245,"LLaVA-InternLM-7B (QLoRA)",7.6,"InternLM-7B","CLIP ViT-L/14","2023/12/28",32.4,"N/A"],[246,"LLaVA-OneVision-0.5B (SI)",1.0,"Qwen2-0.5B","SigLIP-400M","2024/09/17",32.2,"N/A"],[247,"LLaVA-v1.5-7B (QLoRA)",7.2,"Vicuna-v1.5-7B","CLIP ViT-L/14","2023/12/28",32.2,"N/A"],[248,"abab6.5s",null,"","","2024/12/11",32.2,"N/A"],[249,"Yi-VL-6B",6.6,"Yi-6B","CLIP ViT-H/14","2024/01/25",32.1,"N/A"],[250,"LLaVA-OneVision-0.5B",1.0,"Qwen2-0.5B","SigLIP-400M","2024/09/16",31.5,"N/A"],[251,"InternVL2-1B",1.0,"Qwen2-0.5B","InternViT-300M","2024/07/11",31.5,"N/A"],[252,"InternLM-XComposer2-1.8B",2.0,"InternLM2-1.8B","CLIP ViT-L/14","2024/06/09",31.2,"N/A"],[253,"MiniCPM-V",3.0,"MiniCPM-2.4B","SigLIP-400M","2024/02/07",31.1,"N/A"],[254,"Emu2_chat",37.0,"Llama-33B","EVA-02-CLIP-E-plus","2024/01/17",31.0,"N/A"],[255,"Long-VITA-16K",14.0,"Qwen2.5-14B","InternViT-300M","2025/06/13",31.0,"N/A"],[256,"H2OVL-800M",0.83,"H2O-DANUBE3-500M","InternViT-300M","2024/10/31",30.2,"N/A"],[257,"ShareCaptioner",8.0,"InternLM-7B","EVA-G","2024/01/03",30.1,"N/A"],[258,"IDEFICS-9B-Instruct",9.0,"Llama-7B","CLIP ViT-H/14","2023/07/25",30.0,"N/A"],[259,"SmolVLM2-500M",0.51,"SmolLM2-360M","ViT-93M","2025/03/13",29.9,"N/A"],[260,"Parrot-7B",8.0,"Qwen2-7B","CLIP ViT-L/14","2024/08/22",29.8,"N/A"],[261,"SmolVLM-Instruct-DPO",2.3,"SmolLM2-1.7B","SigLIP-400M","2025/01/27",29.3,"N/A"],[262,"SmolVLM-Synthetic",2.3,"SmolLM2-1.7B","SigLIP-400M","2025/01/27",29.3,"N/A"],[263,"DeepSeek-VL-1.3B",2.0,"DeekSeek-1B","SAM-B
SigLIP-L","2024/03/21",29.2,"N/A"],[264,"Emu3_chat",8.49,"","","2025/01/26",29.1,"N/A"],[265,"Mantis-8B-clip-llama3",8.0,"Llama-3-8B-Instruct","CLIP ViT-L/14","2024/08/08",28.6,"N/A"],[266,"LLaVA-v1-7B",7.2,"Llama-7B","CLIP ViT-L/14","2023/04/17",28.3,"23.8±0.6"],[267,"Mantis-8B-Fuyu",8.0,"Fuyu-8B","","2024/09/07",27.3,"N/A"],[268,"Vintern-1B-v2",3.7,"Qwen2-0.5B","InternViT-300M","2024/11/16",26.4,"N/A"],[269,"Moondream1",1.9,"SigLIP-400M","Phi-1.5","2024/09/26",26.0,"N/A"],[270,"SmolVLM-500M",0.51,"SmolLM2-360M","ViT-93M","2025/01/27",25.7,"N/A"],[271,"SmolVLM2-256M",0.26,"SmolLM2-135M","ViT-93M","2025/03/13",25.5,"N/A"],[272,"360VL-70B",70.0,"Llama-3-70B-Instruct","CLIP ViT-L/14","2024/05/25",24.7,"N/A"],[273,"Kosmos2",1.7,"","","2024/10/19",23.7,"N/A"],[274,"OpenFlamingo v2",9.0,"MPT 7B","CLIP ViT-L/14","2023/06/28",23.3,"24.8±0.2"],[275,"MMAlaya",7.8,"Alaya-7B-Chat","EVA-G","2024/01/29",22.2,"N/A"],[276,"SmolVLM-256M",0.26,"SmolLM2-135M","ViT-93M","2025/01/27",21.1,"N/A"],[277,"PandaGPT-13B",14.0,"Vicuna-13B","ImageBind ViT-H/14","2023/05/25",19.6,"N/A"],[278,"InternVL2.5-78B",78.0,"Qwen-2.5-72B","InternViT-6B-v2.5","2024/12/10",16.9,"N/A"],[279,"MiniGPT-4-v1-7B",8.0,"Vicuna-7B","EVA-G","2023/04/20",15.6,"22.1±0.1"],[280,"VisualGLM",8.0,"ChatGLM 6B","EVA-CLIP","2023/05/17",14.8,"N/A"],[281,"Qwen-VL",9.6,"Qwen-7B","ViT-G/16","2023/08/24",13.0,"N/A"],[282,"MiniGPT-4-v2",8.0,"Llama-2-13B","EVA-G","2023/10/27",10.5,"N/A"],[283,"Chameleon-30B",30.0,"","","2024/07/29",9.7,"N/A"],[284,"Chameleon-7B",7.0,"","","2024/07/29",8.3,"N/A"]],"metadata":null},"headers":["1","2","3"],"row_count":[1,"dynamic"],"col_count":[3,"dynamic"],"datatype":["number","html","number","html","html","str","number","number"],"type":"pandas","latex_delimiters":[{"left":"$$","right":"$$","display":true}],"show_label":true,"height":500,"min_width":160,"interactive":false,"visible":true,"elem_classes":[],"wrap":true,"line_breaks":true,"column_widths":[],"name":"dataframe","_selectable":false},"skip_api":false,"component_class_id":"6a51bb3357f2e94c40fb8d4fbe06aa8e","key":null,"api_info":{"properties":{"headers":{"items":{"type":"string"},"title":"Headers","type":"array"},"data":{"items":{"items":{},"type":"array"},"title":"Data","type":"array"},"metadata":{"anyOf":[{"additionalProperties":{"anyOf":[{"items":{},"type":"array"},{"type":"null"}]},"type":"object"},{"type":"null"}],"default":null,"title":"Metadata"}},"required":["headers","data"],"title":"DataframeData","type":"object"},"example_inputs":{"headers":["a","b"],"data":[["foo","bar"]]}},{"id":105,"type":"textbox","props":{"value":"MMVet","lines":1,"max_lines":20,"label":"MMVet","show_label":true,"container":true,"min_width":160,"visible":false,"autofocus":false,"autoscroll":true,"elem_classes":[],"type":"text","rtl":false,"show_copy_button":false,"name":"textbox","_selectable":false},"skip_api":false,"component_class_id":"d0491bb0fbd427bdb2a4549c4d1ac869","key":null,"api_info":{"type":"string"},"example_inputs":"Hello!!"},{"id":106,"type":"form","props":{"scale":0,"min_width":0,"name":"form"},"skip_api":true,"component_class_id":"43cda85c6ff7a5dd8f83d29496b014ee","key":null},{"id":107,"type":"form","props":{"scale":0,"min_width":0,"name":"form"},"skip_api":true,"component_class_id":"43cda85c6ff7a5dd8f83d29496b014ee","key":null},{"id":108,"type":"tabitem","props":{"label":"📊 MMMU_VAL Leaderboard","visible":true,"interactive":true,"id":10,"elem_id":"MMMU_VAL","name":"tab"},"skip_api":true,"component_class_id":"18f46968e2b273dc5dbda0fe78433d7e","key":null},{"id":109,"type":"markdown","props":{"value":"## MMMU Validation Evaluation Results\n\n- For MMMU, we support the evaluation of the `dev` (150 samples) and `validation` (900 samples) set. Here we only report the results on the `validation` set. \n- **Answer Inference:**\n - For models with `interleave_generate` interface (accept interleaved images & texts as inputs), all testing samples can be inferred. **`interleave_generate` is adopted for inference.**\n - For models without `interleave_generate` interface, samples with more than one images are skipped (42 out of 1050, directly count as wrong). **`generate` is adopted for inference.**\n- **Evaluation**:\n - MMMU include two types of questions: **multi-choice questions** & **open-ended QA**. \n - For **open-ended QA (62/1050)**, we re-formulate it as multi-choice questions: `{'question': 'QQQ', 'answer': 'AAA'} -> {'question': 'QQQ', 'A': 'AAA', 'B': 'Other Answers', 'answer': 'A'}`, and then adopt the same evaluation paradigm for **multi-choice questions**. \n - For **multi-choice questions (988/1050)**, we use **GPT-3.5-Turbo-0613** for matching prediction with options if heuristic matching does not work. ","show_label":true,"rtl":false,"latex_delimiters":[{"left":"$$","right":"$$","display":true}],"visible":true,"elem_classes":[],"sanitize_html":true,"line_breaks":false,"header_links":false,"show_copy_button":false,"name":"markdown","_selectable":false},"skip_api":false,"component_class_id":"0f35515b9a3362b42bb6721c836157a0","key":null,"api_info":{"type":"string"},"example_inputs":"# Hello!"},{"id":110,"type":"checkboxgroup","props":{"choices":[["Overall","Overall"],["Art & Design","Art & Design"],["Business","Business"],["Science","Science"],["Health & Medicine","Health & Medicine"],["Humanities & Social Science","Humanities & Social Science"],["Tech & Engineering","Tech & Engineering"],["FG-Accounting","FG-Accounting"],["FG-Agriculture","FG-Agriculture"],["FG-Architecture_and_Engineering","FG-Architecture_and_Engineering"],["FG-Art","FG-Art"],["FG-Art_Theory","FG-Art_Theory"],["FG-Basic_Medical_Science","FG-Basic_Medical_Science"],["FG-Biology","FG-Biology"],["FG-Chemistry","FG-Chemistry"],["FG-Clinical_Medicine","FG-Clinical_Medicine"],["FG-Computer_Science","FG-Computer_Science"],["FG-Design","FG-Design"],["FG-Diagnostics_and_Laboratory_Medicine","FG-Diagnostics_and_Laboratory_Medicine"],["FG-Economics","FG-Economics"],["FG-Electronics","FG-Electronics"],["FG-Energy_and_Power","FG-Energy_and_Power"],["FG-Finance","FG-Finance"],["FG-Geography","FG-Geography"],["FG-History","FG-History"],["FG-Literature","FG-Literature"],["FG-Manage","FG-Manage"],["FG-Marketing","FG-Marketing"],["FG-Materials","FG-Materials"],["FG-Math","FG-Math"],["FG-Mechanical_Engineering","FG-Mechanical_Engineering"],["FG-Music","FG-Music"],["FG-Pharmacy","FG-Pharmacy"],["FG-Physics","FG-Physics"],["FG-Psychology","FG-Psychology"],["FG-Public_Health","FG-Public_Health"],["FG-Sociology","FG-Sociology"]],"value":["Overall"],"type":"value","label":"MMMU_VAL CheckBoxes","show_label":true,"container":true,"min_width":160,"interactive":true,"visible":true,"elem_classes":[],"name":"checkboxgroup","_selectable":false},"skip_api":false,"component_class_id":"0635a5d3bf87369f1c2c1c69f8a3d0cc","key":null,"api_info":{"items":{"enum":["Overall","Art & Design","Business","Science","Health & Medicine","Humanities & Social Science","Tech & Engineering","FG-Accounting","FG-Agriculture","FG-Architecture_and_Engineering","FG-Art","FG-Art_Theory","FG-Basic_Medical_Science","FG-Biology","FG-Chemistry","FG-Clinical_Medicine","FG-Computer_Science","FG-Design","FG-Diagnostics_and_Laboratory_Medicine","FG-Economics","FG-Electronics","FG-Energy_and_Power","FG-Finance","FG-Geography","FG-History","FG-Literature","FG-Manage","FG-Marketing","FG-Materials","FG-Math","FG-Mechanical_Engineering","FG-Music","FG-Pharmacy","FG-Physics","FG-Psychology","FG-Public_Health","FG-Sociology"],"type":"string"},"title":"Checkbox Group","type":"array"},"example_inputs":["Overall"]},{"id":111,"type":"row","props":{"variant":"default","visible":true,"equal_height":true,"show_progress":false,"name":"row"},"skip_api":true,"component_class_id":"b5cf3d15e2293fb5ccc071d7b8d69f64","key":null},{"id":112,"type":"textbox","props":{"value":"Input the Model Name (fuzzy, case insensitive)","lines":1,"max_lines":20,"label":"Model Name","show_label":true,"container":true,"min_width":160,"interactive":true,"visible":true,"autofocus":false,"autoscroll":true,"elem_classes":[],"type":"text","rtl":false,"show_copy_button":false,"name":"textbox","_selectable":false},"skip_api":false,"component_class_id":"d0491bb0fbd427bdb2a4549c4d1ac869","key":null,"api_info":{"type":"string"},"example_inputs":"Hello!!"},{"id":113,"type":"checkboxgroup","props":{"choices":[["<4B","<4B"],["4B-10B","4B-10B"],["10B-20B","10B-20B"],["20B-40B","20B-40B"],[">40B",">40B"],["Unknown","Unknown"]],"value":["<4B","4B-10B","10B-20B","20B-40B",">40B","Unknown"],"type":"value","label":"Model Size","show_label":true,"container":true,"min_width":160,"interactive":true,"visible":true,"elem_classes":[],"name":"checkboxgroup","_selectable":false},"skip_api":false,"component_class_id":"0635a5d3bf87369f1c2c1c69f8a3d0cc","key":null,"api_info":{"items":{"enum":["<4B","4B-10B","10B-20B","20B-40B",">40B","Unknown"],"type":"string"},"title":"Checkbox Group","type":"array"},"example_inputs":["<4B"]},{"id":114,"type":"checkboxgroup","props":{"choices":[["API","API"],["OpenSource","OpenSource"]],"value":["API","OpenSource"],"type":"value","label":"Model Type","show_label":true,"container":true,"min_width":160,"interactive":true,"visible":true,"elem_classes":[],"name":"checkboxgroup","_selectable":false},"skip_api":false,"component_class_id":"0635a5d3bf87369f1c2c1c69f8a3d0cc","key":null,"api_info":{"items":{"enum":["API","OpenSource"],"type":"string"},"title":"Checkbox Group","type":"array"},"example_inputs":["API"]},{"id":115,"type":"form","props":{"scale":3,"min_width":480,"name":"form"},"skip_api":true,"component_class_id":"43cda85c6ff7a5dd8f83d29496b014ee","key":null},{"id":116,"type":"dataframe","props":{"value":{"headers":["Rank","Method","Param (B)","Language Model","Vision Model","Eval Date","Overall"],"data":[[1,"GPT-5-20250807",null,"","","2025/08/14",81.8],[2,"GPT-5-mini-20250807",null,"","","2025/08/14",78.7],[3,"SenseNova-V6-5-Pro",null,"","","2025/09/03",77.0],[4,"CongRong-v2.0",null,"","","2025/05/20",75.6],[5,"Gemini-2.5-Pro",null,"","","2025/04/07",74.7],[6,"GPT-4.1-20250414",null,"","","2025/04/16",74.0],[7,"ChatGPT-4o-latest",null,"","","2025/04/07",72.9],[8,"GPT-5-nano-20250807",null,"","","2025/08/14",72.6],[9,"Gemini-2.0-Pro",null,"","","2025/02/27",72.6],[10,"InternVL3-78B",78.4,"Qwen2.5-72B","InternViT-6B-v2.5","2025/04/14",72.2],[11,"GPT-4.5",null,"","","2025/03/26",72.1],[12,"Claude3.7-Sonnet",null,"","","2025/02/27",71.0],[13,"HunYuan-Standard-Vision",null,"","","2025/01/15",70.7],[14,"GPT-4o (1120, detail-high)",null,"","","2024/12/02",70.7],[15,"SenseNova-V6-Pro",null,"","","2025/05/05",70.4],[16,"InternVL2.5-78B",78.0,"Qwen-2.5-72B","InternViT-6B-v2.5","2024/12/10",70.0],[17,"GPT-4o (0806, detail-high)",null,"","","2024/08/08",69.9],[18,"GLM-4v-Plus-20250111",null,"","","2025/01/25",69.9],[19,"Step-1o",null,"","","2025/01/13",69.9],[20,"Gemini-2.0-Flash",null,"","","2025/01/02",69.9],[21,"InternVL3-38B",38.4,"Qwen2.5-32B","InternViT-6B-v2.5","2025/04/14",69.7],[22,"SenseNova",null,"","","2024/12/12",69.6],[23,"GPT-4o (0513, detail-high)",null,"","","2024/05/31",69.2],[24,"Qwen2.5-VL-32B",33.5,"Qwen2.5-32B","QwenViT","2025/07/02",68.9],[25,"JT-VL-Chat-V3.0",null,"","","2025/08/04",68.7],[26,"Gemini-1.5-Pro-002",null,"","","2024/12/02",68.6],[27,"InternVL2.5-78B-MPO",78.0,"Qwen-2.5-72B","InternViT-6B-v2.5","2024/12/29",68.2],[28,"Qwen2.5-VL-72B",73.4,"Qwen2.5-72B","QwenViT","2025/02/02",68.2],[29,"grok-2-vision-1212",null,"","","2025/03/03",67.1],[30,"Ovis2-34B",34.9,"Qwen2.5-32B","AIMv2-1B","2025/02/18",66.7],[31,"TeleMM",null,"","","2024/12/31",66.6],[32,"Claude3.5-Sonnet-20241022",null,"","","2024/11/06",66.4],[33,"Claude3.5-Sonnet",null,"","","2024/06/24",65.9],[34,"abab7-preview",null,"","","2024/12/11",64.8],[35,"InternVL3-14B",15.1,"Qwen2.5-14B","InternViT-300M-v2.5","2025/04/14",64.8],[36,"Gemma3-27B",27.4,"Gemma3-27B","SigLIP-400M","2025/03/19",64.8],[37,"R-4B",4.82,"Qwen3-4B","SigLip-400M","2025/08/11",64.7],[38,"Qwen-VL-Max-0809",72.0,"Qwen2-72B","QwenViT","2024/09/12",64.6],[39,"Qwen2-VL-72B",73.4,"Qwen2-72B","QwenViT","2024/10/28",64.3],[40,"InternVL2.5-38B-MPO",38.0,"Qwen-2.5-32B","InternViT-6B-v2.5","2024/12/28",63.8],[41,"InternVL2.5-38B",38.0,"Qwen-2.5-32B","InternViT-6B-v2.5","2024/12/10",63.2],[42,"Kimi-VL-A3B-Thinking-2506",16.4,"Moonlight-16B-A3B","MoonViT","2025/07/02",62.9],[43,"GPT-4o (0513, detail-low)",null,"","","2024/05/15",62.8],[44,"BlueLM-2.6-3B",3.0,"","","2025/09/17",62.4],[45,"GPT-4v (0409, detail-low)",null,"","","2024/05/15",62.3],[46,"InternVL3-8B",7.94,"Qwen2.5-7B","InternViT-300M-v2.5","2025/04/14",62.2],[47,"VARCO-VISION-2.0-14B",15.2,"Qwen3-14B","SigLIP-400M","2025/08/04",61.9],[48,"GPT-4v (0409, detail-high)",null,"","","2024/05/15",61.7],[49,"GLM-4v-Plus",null,"","","2024/12/11",61.7],[50,"Step-1.5V",null,"Step-1.5","stepencoder","2024/10/11",61.2],[51,"WeThink-Qwen2.5VL-7B",8.29,"Qwen2.5-7B","QwenViT","2025/05/26",61.0],[52,"NVLM-D-72B",79.4,"Qwen2-72B","InternViT-6B","2024/10/19",60.8],[53,"Gemini-1.5-Flash-002",null,"","","2024/12/02",60.7],[54,"Ovis2-16B",16.2,"Qwen2.5-14B","AIMv2 Huge","2025/02/18",60.7],[55,"Gemini-1.5-Pro",null,"","","2024/06/10",60.6],[56,"Taiyi",null,"","","2024/12/11",60.4],[57,"Ovis1.6-Gemma2-27B",28.9,"Gemma2-27B","SigLIP-400M","2024/11/29",60.3],[58,"Llama-3.2-90B-Vision-Instruct",88.6,"Llama-3.1-70B","","2024/10/19",60.3],[59,"Yi-Vision",null,"","","2024/08/03",60.3],[60,"GPT-4o-mini (0718, detail-high)",null,"","","2024/07/20",60.0],[61,"RBDash-v1.5",79.0,"Qwen2-72B","CLIP ViT-L/14
InternViT-6B","2024/11/17",59.9],[62,"InternVL3-9B",9.14,"InternLM3-8B","InternViT-300M-v2.5","2025/04/14",59.4],[63,"GPT-4v (1106, detail-high)",null,"","","2024/04/22",59.3],[64,"BailingMM-Pro-0120",81.0,"Bailing-80B","SigLIP-400M","2025/01/25",59.2],[65,"BlueLM-2.5-3B",2.9,"BlueLM-base-3B","Siglip2-So400M","2025/07/16",58.7],[66,"valley2_dpo",8.88,"Qwen2.5-7B","SigLIP-400M","2025/05/30",58.4],[67,"InternVL2-Llama3-76B",76.0,"Llama-3-70B-Instruct","InternViT-6B","2024/07/19",58.3],[68,"Gemini-1.5-Flash",null,"","","2024/09/16",58.2],[69,"Qwen2.5-VL-7B",8.29,"Qwen2.5-7B","QwenViT","2025/02/02",58.0],[70,"Kimi-VL-A3B-Instruct",16.4,"Moonlight-16B-A3B","MoonViT","2025/04/14",57.8],[71,"moonshot-v1-8k",null,"","","2025/03/03",57.7],[72,"GPT-4.1-nano-20250414",null,"","","2025/04/16",57.6],[73,"Ovis2-8B",8.94,"Qwen2.5-7B","AIMv2 Huge","2025/02/18",57.4],[74,"Ola-7b",8.88,"Qwen2.5-7B","Oryx-ViT","2025/02/05",57.0],[75,"Valley-Eagle",8.9,"Qwen2.5-7B","Qwen-ViT
SigLIP-400M","2024/12/29",57.0],[76,"valley2",8.88,"Qwen2.5-7B","SigLIP-400M","2025/05/30",56.8],[77,"LLaVA-OneVision-72B",73.0,"Qwen2-72B","SigLIP-400M","2024/09/19",56.6],[78,"InternVL2.5-26B-MPO",26.0,"InternLM2.5-20B","InternViT-6B-v2.5","2024/12/28",56.4],[79,"VARCO-VISION-14B",15.2,"Qwen2.5-14B","SigLIP-400M","2025/01/02",56.3],[80,"InternVL2.5-8B",8.0,"InternLM2.5-7B","InternViT-300M-v2.5","2024/12/10",56.2],[81,"InternVL2.5-26B",26.0,"InternLM2.5-20B","InternViT-6B-v2.5","2024/12/10",56.0],[82,"Phi-4-MultiModal",5.57,"Phi-4-Mini","SigLIP-400M","2025/03/13",56.0],[83,"LLaVA-OneVision-72B (SI)",73.0,"Qwen2-72B","SigLIP-400M","2024/09/19",55.7],[84,"SAIL-VL-1.6-8B",8.33,"Qwen2.5-7B","AIMv2 Huge","2025/04/24",55.4],[85,"Gemma3-12B",12.2,"Gemma3-12B","SigLIP-400M","2025/03/19",55.2],[86,"InternVL2-40B",40.0,"Nous-Hermes-2-Yi-34B","InternViT-6B","2024/07/11",55.2],[87,"VILA1.5-40B",40.0,"Yi-34B","InternViT-6B","2024/08/25",55.1],[88,"Ovis1.6-Gemma2-9B",10.2,"Gemma2-9B-It","SigLIP-400M","2024/09/19",55.0],[89,"GPT-4.1-mini-20250414",null,"","","2025/04/16",55.0],[90,"Claude3-Opus",null,"","","2024/03/28",54.9],[91,"InternVL2.5-8B-MPO",8.0,"InternLM2.5-7B","InternViT-300M-v2.5","2024/12/28",54.8],[92,"MUG-U-7B",7.0,"","","2025/03/19",54.3],[93,"SAIL-VL-1.5-8B",7.95,"Qwen2.5-7B","InternViT-300B","2025/04/23",54.3],[94,"Aria",25.3,"Aria-MoE","SigLIP-400M","2024/12/05",54.0],[95,"DeepSeek-VL2",27.5,"DeepSeekMoE-27B","SigLIP-400M","2025/01/01",54.0],[96,"Long-VITA-16K",14.0,"Qwen2.5-14B","InternViT-300M","2025/06/13",53.9],[97,"POINTS1.5-Qwen2.5-7B",8.3,"Qwen-2.5-7B","NaViT","2024/12/06",53.8],[98,"GPT-4v (1106, detail-low)",null,"","","2023/12/23",53.8],[99,"LLaVA-CoT",11.0,"","","2025/01/05",53.7],[100,"Qwen2-VL-7B",8.0,"Qwen2-7B","QwenViT","2024/09/12",53.7],[101,"QTuneVL1.5-3B",3.75,"Qwen2.5-3B","QwenViT","2025/08/11",53.4],[102,"360VL-70B",70.0,"Llama-3-70B-Instruct","CLIP ViT-L/14","2024/05/25",53.4],[103,"Qwen-VL-Plus-0809",null,"","","2024/09/17",53.2],[104,"Molmo-72B",73.3,"Qwen2-72B","CLIP ViT-L/14","2024/10/28",52.8],[105,"VITA-1.5",8.3,"Qwen2-7B","InternViT-300M","2025/01/01",52.6],[106,"Qwen-VL-Max",null,"QwenLM","","2024/02/02",52.0],[107,"InternVL2.5-4B",4.0,"Qwen-2.5-3B","InternViT-300M-v2.5","2024/12/10",51.8],[108,"InternVL2.5-4B-MPO",4.0,"Qwen-2.5-3B","InternViT-300M-v2.5","2024/12/28",51.8],[109,"Step-1.5V-mini",null,"","","2024/12/11",51.7],[110,"POINTS-Qwen2.5-7B",8.3,"Qwen-2.5-7B","CLIP ViT-L/14","2024/10/19",51.4],[111,"Ristretto-3B",3.84,"Qwen2.5-3B","SigLIP-400M","2025/04/01",51.3],[112,"Eagle-X5-34B-Chat",36.8,"Yi-34B","Clip-448
ConvNeXT-1024
SAM-1024
DET-1024
Pix2Struct-1024","2024/11/29",51.2],[113,"InternVL2-8B",8.0,"InternLM2.5-7B","InternViT-300M","2024/07/11",51.2],[114,"Qwen2.5-VL-3B",3.75,"Qwen2.5-3B","QwenViT","2025/02/02",51.2],[115,"Pixtral-12B",13.0,"Nemo-12B","ViT-400M","2024/09/16",51.1],[116,"MiniCPM-o-2.6",8.67,"Qwen2.5-7B","SigLIP-400M","2025/01/21",50.9],[117,"BailingMM-Lite-1203",21.0,"Bailing-20B","SigLIP-400M","2024/12/08",50.9],[118,"Kimi-VL-A3B-Thinking",16.4,"Moonlight-16B-A3B","MoonViT","2025/04/23",50.7],[119,"InternVL2-26B",26.0,"InternLM2-20B","InternViT-6B","2024/07/11",50.7],[120,"Ovis-U1-3B",3.64,"Qwen3-1.7B","aimv2-large-path14-448","2025/07/20",50.6],[121,"Cambrian-34B",34.0,"Nous-Hermes-2-Yi-34B","CLIP ViT-L/14","2024/07/18",50.4],[122,"bailingMM-mini",17.0,"bailing-mini","bailingMM-encoder-1B
InternViT-6B","2024/10/24",50.0],[123,"MiniCPM-V-2.6",8.0,"Qwen2-7B","SigLIP-400M","2024/08/08",49.8],[124,"DeepSeek-VL2-Small",16.1,"DeepSeekMoE-16B","SigLIP-400M","2025/01/01",49.7],[125,"Claude3-Haiku",null,"","","2024/03/28",49.7],[126,"Ovis1.5-Gemma2-9B",11.4,"Gemma2-9B-It","SigLIP-400M","2024/08/04",49.7],[127,"OmChat-v2.0-13B",13.0,"Qwen2-7B","InternViT-6B","2024/08/22",49.6],[128,"Molmo-7B-D",8.0,"Qwen2-7B","CLIP ViT-L/14","2024/10/12",49.1],[129,"Ross-Qwen2-7B",8.2,"Qwen2-7B","CLIP ViT-L/14","2025/01/17",49.0],[130,"Ovis2-4B",4.62,"Qwen2.5-3B","AIMv2 Huge","2025/02/18",49.0],[131,"Gemini-1.0-Pro",null,"","","2023/12/23",49.0],[132,"LLaVA-Next-Yi-34B",34.8,"Yi-34B","CLIP ViT-L/14","2024/03/25",48.8],[133,"QTuneVL1.5-2B",2.09,"Qwen2.5-1.5B","InternViT-300M-v2.5","2025/08/11",48.7],[134,"InternVL3-2B",2.09,"Qwen2.5-1.5B","InternViT-300M-v2.5","2025/04/14",48.7],[135,"InternVL2-4B",4.0,"Phi-3","InternViT-300M","2024/07/11",48.3],[136,"CongRong",null,"","","2024/06/26",48.3],[137,"Ovis1.5-Llama3-8B",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/07/29",48.3],[138,"InternVL2-8B-MPO-CoT",8.0,"InternLM2.5-7B","InternViT-300M","2024/11/25",48.1],[139,"Llama-3.2-11B-Vision-Instruct",11.0,"Llama-3.1-8B","","2024/10/07",48.0],[140,"InternVL2-8B-MPO",8.0,"InternLM2.5-7B","InternViT-300M","2024/11/25",48.0],[141,"LLaVA-OneVision-7B",8.0,"Qwen2-7B","SigLIP-400M","2024/09/16",47.9],[142,"POINTS-Yi-1.5-9B",9.5,"Yi-1.5-9B","CLIP ViT-L/14","2024/10/11",47.6],[143,"VITA",47.0,"Mixtral-8x7B","InternViT-300M","2025/01/20",47.6],[144,"Claude3-Sonnet",null,"","","2024/03/28",47.4],[145,"Gemma3-4B",4.3,"Gemma3-4B","SigLIP-400M","2025/03/19",47.3],[146,"MMAlaya2",26.0,"InternLM2-20B","InternViT-6B","2024/08/27",46.9],[147,"GLM-4v-9B",9.0,"GLM-4-9B","EVA-02-5B","2024/06/14",46.9],[148,"Aquila-VL-2B",2.2,"Qwen-2.5-1.5B","SigLIP-400M","2024/10/24",46.9],[149,"LLaVA-OneVision-7B (SI)",8.0,"Qwen2-7B","SigLIP-400M","2024/09/17",46.8],[150,"InternVL-Chat-V1.5",26.0,"InternLM2-20B","InternViT-6B","2024/04/17",46.8],[151,"Vintern-3B-beta",3.7,"Qwen-2.5-3B","InternViT-300M","2024/10/24",46.7],[152,"Ovis1.6-Llama3.2-3B",4.1,"Llama-3.2-3B","SigLIP-400M","2024/10/24",46.7],[153,"Idefics3-8B-Llama3",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/08/27",46.6],[154,"SAIL-VL-1.5-2B",2.47,"Qwen2.5-1.5B","AIMv2 Huge","2025/04/23",46.4],[155,"Phi-3-Vision",4.2,"Phi-3","CLIP ViT-L/14","2024/05/31",46.1],[156,"MiniCPM-Llama3-V2.5",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/05/27",45.8],[157,"GLM-4v",null,"","","2024/05/20",45.6],[158,"Flash-VL-2B-Dynamic-ISS",2.53,"Qwen-2.5-1.5B-Instruct","SigLIP2-400M-512","2025/05/30",45.6],[159,"Ovis2-2B",2.46,"Qwen2.5-1.5B","AIMv2 Large","2025/02/18",45.6],[160,"WeMM",7.0,"InternLM2-7B","SigLIP-400M","2024/06/09",45.3],[161,"IDEFICS2-8B",8.0,"Mistral-7B","SigLIP-400M","2024/04/26",45.2],[162,"Mini-InternVL-Chat-4B-V1.5",4.0,"Phi-3","InternViT-300M","2024/06/10",45.1],[163,"BlueLM-V-3B",3.0,"BlueLM-3B","SigLIP-400M","2024/10/30",45.1],[164,"Yi-VL-34B",34.6,"Yi-34B","CLIP ViT-H/14","2024/01/25",45.1],[165,"RekaFlash",null,"","","2024/05/07",44.8],[166,"QTuneVL1-2B",2.21,"InternLM2.5-1.8B","InternViT-300M-v2.5","2025/05/05",44.7],[167,"InternVL2.5-2B-MPO",2.0,"InternLM2.5-1.8B","InternViT-300M-v2.5","2024/12/28",44.6],[168,"Phi-3.5-Vision",4.0,"Phi-3.5","CLIP ViT-L/14","2024/08/28",44.6],[169,"VARCO-VISION-2.0-1.7B",2.12,"Qwen3-1.7B","SigLIP-400M","2025/08/04",44.2],[170,"SAIL-VL-2B",2.1,"Qwen2.5-1.5B","InternViT-300M","2024/12/25",44.1],[171,"XVERSE-V-13B",13.0,"XVERSE-13B","CLIP ViT-L/14","2024/05/10",44.1],[172,"HawkVL-2B",2.44,"Qwen2.5-1.5B","QwenViT","2025/06/16",43.6],[173,"Bunny-Llama3-8B",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/07/18",43.4],[174,"InternVL2.5-2B",2.0,"InternLM2.5-1.8B","InternViT-300M-v2.5","2024/12/10",43.2],[175,"InternVL3-1B",0.94,"Qwen2.5-0.5B","InternViT-300M-v2.5","2025/04/14",43.2],[176,"LLaVA-Next-Llama3",8.0,"Llama-3-8B-Instruct","CLIP ViT-L/14","2024/07/29",43.1],[177,"InternLM-XComposer2.5",8.0,"InternLM2-7B","CLIP ViT-L/14","2024/07/11",42.9],[178,"XinYuan-VL-2B-Instruct",2.0,"Qwen2-1.5B","QwenViT","2024/09/27",42.9],[179,"DeepSeek-VL2-Tiny",3.4,"DeepSeekMoE-3B","SigLIP-400M","2025/01/01",42.9],[180,"CogVLM2-19B-Chat",19.0,"Llama-3-8B-Instruct","EVA2-CLIP-E","2024/05/31",42.6],[181,"RekaEdge",null,"","","2024/05/31",42.4],[182,"Qwen2-VL-2B",2.0,"Qwen2-1.5B","QwenViT","2024/09/12",42.2],[183,"Molmo-7B-O",8.0,"Qwen2-7B","CLIP ViT-L/14","2024/10/20",42.2],[184,"LLaVA-Next-Qwen-32B",33.0,"Qwen-1.5-32B","SigLIP-400M","2024/08/08",41.8],[185,"Cambrian-8B",8.0,"Vicuna-v1.5-7B","CLIP ViT-L/14","2024/07/11",41.8],[186,"OmniLMM-12B",12.0,"Zephyr-7B-β","EVA-02-5B","2024/02/07",41.8],[187,"LLaVA-Next-Interleave-7B",8.0,"Qwen-1.5-7B","SigLIP-400M","2024/08/08",41.7],[188,"SmolVLM2",2.25,"SmolLM2-1.7M","SigLIP-400M","2025/03/13",41.6],[189,"Janus-Pro-7B",7.42,"DeepSeek-7B","SigLIP-400M","2025/02/02",41.6],[190,"Mantis-8B-Idefics2",8.0,"Mistral-7B","SigLIP-400M","2024/08/08",41.6],[191,"Cambrian-13B",13.0,"Vicuna-v1.5-13B","CLIP ViT-L/14","2024/07/29",41.6],[192,"InternLM-XComposer2",7.0,"InternLM2-7B","CLIP ViT-L/14","2024/01/26",41.4],[193,"InternVL2.5-1B",1.0,"Qwen-2.5-0.5B","InternViT-300M-v2.5","2024/12/10",41.2],[194,"VILA1.5-13B",13.0,"Vicuna-v1.5-13B","SigLIP-400M","2024/08/25",41.1],[195,"Mantis-8B-siglip-llama3",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/08/08",41.1],[196,"TransCore-M",13.4,"PCITransGPT-13B","CLIP ViT-L/14","2024/04/16",41.0],[197,"XGen-MM-Instruct-Interleave-v1.5",4.4,"Phi-3","SigLIP-400M","2024/09/06",40.9],[198,"Monkey-Chat",9.8,"Qwen-7B","ViT-BigHuge","2024/01/16",40.7],[199,"Yi-VL-6B",6.6,"Yi-6B","CLIP ViT-H/14","2024/01/25",40.3],[200,"InternVL2.5-1B-MPO",1.0,"Qwen-2.5-0.5B","InternViT-300M-v2.5","2024/12/28",40.3],[201,"Mantis-8B-clip-llama3",8.0,"Llama-3-8B-Instruct","CLIP ViT-L/14","2024/08/08",40.2],[202,"LLaVA-InternLM2-7B (QLoRA)",8.1,"InternLM2-7B","CLIP ViT-L/14","2024/01/17",40.1],[203,"LLaVA-Next-Interleave-7B-DPO",8.0,"Qwen-1.5-7B","SigLIP-400M","2024/07/29",40.1],[204,"XGen-MM-Instruct-DPO-v1.5",4.4,"Phi-3","SigLIP-400M","2024/09/06",40.1],[205,"Qwen-VL-Plus",null,"QwenLM","","2024/01/10",39.8],[206,"SmolVLM-Instruct-DPO",2.3,"SmolLM2-1.7B","SigLIP-400M","2025/01/27",39.7],[207,"Eagle-X5-13B",15.0,"Vicuna-v1.5-13B","Clip-448
ConvNeXT-1024
SAM-1024
DET-1024
Pix2Struct-1024","2024/09/26",39.7],[208,"InternLM-XComposer2-4KHD",7.0,"InternLM2-7B","CLIP ViT-L/14","2024/06/09",39.7],[209,"LLaVA-InternLM2-20B (QLoRA)",20.2,"InternLM2-20B","CLIP ViT-L/14","2024/01/17",39.4],[210,"Llama-3-MixSense-v1.1",8.0,"Llama-3-8B-Instruct","Florence-2-Large-FT","2024/08/21",39.3],[211,"LLaVA-LLaMA-3-8B",8.0,"Llama-3-8B-Instruct","CLIP ViT-L/14","2024/05/07",39.2],[212,"Falcon2-VLM-11B",11.4,"Falcon2-11B","CLIP ViT-L/14","2024/10/30",39.1],[213,"granite-vision-3.2-2b",2.98,"granite-3.1-2b-instruct","SigLip","2025/06/20",39.0],[214,"granite-vision-3.3-2b",2.98,"granite-3.1-2b-instruct","SigLIP2-400M","2025/06/20",39.0],[215,"Monkey",9.8,"Qwen-7B","ViT-BigHuge","2024/01/11",38.9],[216,"SmolVLM-Instruct",2.3,"SmolLM2-1.7B","SigLIP-400M","2025/01/27",38.8],[217,"Slime-8B",8.0,"Llama-3-8B-Instruct","CLIP ViT-L/14","2024/09/14",38.8],[218,"Chameleon-30B",30.0,"","","2024/07/29",38.8],[219,"SmolVLM-Synthetic",2.3,"SmolLM2-1.7B","SigLIP-400M","2025/01/27",38.6],[220,"DeepSeek-VL-7B",7.3,"DeekSeek-7B","SAM-B
SigLIP-L","2024/03/21",38.3],[221,"MiniCPM-V",3.0,"MiniCPM-2.4B","SigLIP-400M","2024/02/07",38.3],[222,"MiniCPM-V-2",2.8,"MiniCPM-2.4B","SigLIP-400M","2024/04/15",38.2],[223,"Eagle-X5-7B",9.0,"Vicuna-v1.5-7B","Clip-448
ConvNeXT-1024
SAM-1024
DET-1024
Pix2Struct-1024","2024/09/26",37.6],[224,"LLaVA-Next-Vicuna-7B",7.1,"Vicuna-v1.5-7B","CLIP ViT-L/14","2024/03/25",37.6],[225,"Llama-3-VILA1.5-8B",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/08/25",37.4],[226,"Mini-InternVL-Chat-2B-V1.5",2.0,"InternLM2-1.8B","InternViT-300M","2024/06/10",37.4],[227,"LLaVA-Next-Vicuna-13B",13.4,"Vicuna-v1.5-13B","CLIP ViT-L/14","2024/03/25",37.3],[228,"CogVLM-17B-Chat",17.0,"Vicuna-v1.5-7B","EVA2-CLIP-E","2024/01/03",37.3],[229,"ShareGPT4V-7B",7.2,"Vicuna-v1.5-7B","CLIP ViT-L/14","2023/12/08",37.2],[230,"Qwen-VL-Chat",9.6,"Qwen-7B","ViT-G/16","2023/08/24",37.0],[231,"LLaVA-Next-Mistral-7B",7.6,"Mistral-7B","CLIP ViT-L/14","2024/03/25",37.0],[232,"LLaVA-v1.5-13B",13.4,"Vicuna-v1.5-13B","CLIP ViT-L/14","2023/10/05",37.0],[233,"LLaVA-InternLM-7B (QLoRA)",7.6,"InternLM-7B","CLIP ViT-L/14","2023/12/28",36.9],[234,"Parrot-7B",8.0,"Qwen2-7B","CLIP ViT-L/14","2024/08/22",36.7],[235,"InternVL2-1B",1.0,"Qwen2-0.5B","InternViT-300M","2024/07/11",36.7],[236,"ShareGPT4V-13B",13.4,"Vicuna-v1.5-13B","CLIP ViT-L/14","2023/12/08",36.6],[237,"Slime-7B",7.0,"Vicuna-v1.5-7B","CLIP ViT-L/14","2024/09/14",36.6],[238,"Slime-13B",13.0,"Vicuna-v1.5-13B","CLIP ViT-L/14","2024/09/14",36.4],[239,"H2OVL-2B",2.2,"H2O-DANUBE2-1.8B","InternViT-300M","2024/10/31",36.3],[240,"ShareCaptioner",8.0,"InternLM-7B","EVA-G","2024/01/03",36.3],[241,"InternVL2-2B",2.0,"InternLM2-1.8B","InternViT-300M","2024/07/11",36.3],[242,"AKI-4B",4.33,"Phi-3.5","SigLIP-400M","2025/03/25",36.3],[243,"LLaVA-OneVision-0.5B (SI)",1.0,"Qwen2-0.5B","SigLIP-400M","2024/09/17",36.2],[244,"Ovis2-1B",1.27,"Qwen2.5-0.5B","AIMv2 Large","2025/02/18",36.1],[245,"LLaVA-v1.5-7B",7.2,"Vicuna-v1.5-7B","CLIP ViT-L/14","2023/10/05",35.7],[246,"InternLM-XComposer",8.0,"InternLM-7B","EVA-G","2023/09/26",35.6],[247,"granite-vision-3.1-2b-preview",2.98,"granite-3.1-2b-instruct","SigLip","2025/06/20",35.4],[248,"LLaVA-v1.5-13B (QLoRA)",13.4,"Vicuna-v1.5-13B","CLIP ViT-L/14","2023/12/28",35.2],[249,"MiniMonkey",2.2,"InternLM2-1.8B","InternViT-300M","2024/09/26",35.0],[250,"Emu2_chat",37.0,"Llama-33B","EVA-02-CLIP-E-plus","2024/01/17",35.0],[251,"PaliGemma-3B-mix-448",3.0,"Gemma-2B","SigLIP-400M","2024/05/17",34.9],[252,"mPLUG-Owl2",8.2,"Llama-2-7B","CLIP ViT-L/14","2023/11/10",34.7],[253,"VILA1.5-3B",3.0,"Sheared-LLaMA-2.7B","SigLIP-400M","2024/08/25",34.2],[254,"LLaVA-v1-7B",7.2,"Llama-7B","CLIP ViT-L/14","2023/04/17",34.1],[255,"SmolVLM2-500M",0.51,"SmolLM2-360M","ViT-93M","2025/03/13",34.1],[256,"abab6.5s",null,"","","2024/12/11",34.0],[257,"Emu3_chat",8.49,"","","2025/01/26",33.9],[258,"MolmoE-1B",7.2,"OLMoE-1B-7B-0924","CLIP ViT-L/14","2024/10/21",33.9],[259,"DeepSeek-VL-1.3B",2.0,"DeekSeek-1B","SAM-B
SigLIP-L","2024/03/21",33.8],[260,"LLaVA-v1.5-7B (QLoRA)",7.2,"Vicuna-v1.5-7B","CLIP ViT-L/14","2023/12/28",33.7],[261,"SmolVLM-500M",0.51,"SmolLM2-360M","ViT-93M","2025/01/27",33.6],[262,"PandaGPT-13B",14.0,"Vicuna-13B","ImageBind ViT-H/14","2023/05/25",32.9],[263,"LLaVA-OneVision-0.5B",1.0,"Qwen2-0.5B","SigLIP-400M","2024/09/16",32.7],[264,"H2OVL-800M",0.83,"H2O-DANUBE3-500M","InternViT-300M","2024/10/31",32.1],[265,"MMAlaya",7.8,"Alaya-7B-Chat","EVA-G","2024/01/29",32.0],[266,"Vintern-1B-v2",3.7,"Qwen2-0.5B","InternViT-300M","2024/11/16",31.6],[267,"Moondream1",1.9,"SigLIP-400M","Phi-1.5","2024/09/26",31.4],[268,"Janus-1.3B",2.1,"DeepSeek-1B","SigLIP-400M","2024/10/24",31.2],[269,"Mantis-8B-Fuyu",8.0,"Fuyu-8B","","2024/09/07",30.8],[270,"InstructBLIP-7B",8.0,"Vicuna-7B","EVA-G","2023/05/11",30.6],[271,"VisualGLM",8.0,"ChatGLM 6B","EVA-CLIP","2023/05/17",29.9],[272,"InternLM-XComposer2-1.8B",2.0,"InternLM2-1.8B","CLIP ViT-L/14","2024/06/09",29.7],[273,"Qwen-VL",9.6,"Qwen-7B","ViT-G/16","2023/08/24",29.6],[274,"Moondream2",1.9,"SigLIP-400M","Phi-1.5","2024/10/20",29.3],[275,"SmolVLM2-256M",0.26,"SmolLM2-135M","ViT-93M","2025/03/13",29.0],[276,"SmolVLM-256M",0.26,"SmolLM2-135M","ViT-93M","2025/01/27",28.9],[277,"OpenFlamingo v2",9.0,"MPT 7B","CLIP ViT-L/14","2023/06/28",28.8],[278,"MiMo-VL-7B",8.31,"Mimo-7B","Qwen2.5-ViT","2025/07/02",26.4],[279,"MiniGPT-4-v2",8.0,"Llama-2-13B","EVA-G","2023/10/27",25.0],[280,"IDEFICS-80B-Instruct",80.0,"Llama-65B","CLIP ViT-H/14","2023/07/25",24.0],[281,"Kosmos2",1.7,"","","2024/10/19",23.7],[282,"MiniGPT-4-v1-7B",8.0,"Vicuna-7B","EVA-G","2023/04/20",23.6],[283,"Chameleon-7B",7.0,"","","2024/07/29",22.4],[284,"IDEFICS-9B-Instruct",9.0,"Llama-7B","CLIP ViT-H/14","2023/07/25",18.4]],"metadata":null},"headers":["1","2","3"],"row_count":[1,"dynamic"],"col_count":[3,"dynamic"],"datatype":["number","html","number","html","html","str","number"],"type":"pandas","latex_delimiters":[{"left":"$$","right":"$$","display":true}],"show_label":true,"height":500,"min_width":160,"interactive":false,"visible":true,"elem_classes":[],"wrap":true,"line_breaks":true,"column_widths":[],"name":"dataframe","_selectable":false},"skip_api":false,"component_class_id":"6a51bb3357f2e94c40fb8d4fbe06aa8e","key":null,"api_info":{"properties":{"headers":{"items":{"type":"string"},"title":"Headers","type":"array"},"data":{"items":{"items":{},"type":"array"},"title":"Data","type":"array"},"metadata":{"anyOf":[{"additionalProperties":{"anyOf":[{"items":{},"type":"array"},{"type":"null"}]},"type":"object"},{"type":"null"}],"default":null,"title":"Metadata"}},"required":["headers","data"],"title":"DataframeData","type":"object"},"example_inputs":{"headers":["a","b"],"data":[["foo","bar"]]}},{"id":117,"type":"textbox","props":{"value":"MMMU_VAL","lines":1,"max_lines":20,"label":"MMMU_VAL","show_label":true,"container":true,"min_width":160,"visible":false,"autofocus":false,"autoscroll":true,"elem_classes":[],"type":"text","rtl":false,"show_copy_button":false,"name":"textbox","_selectable":false},"skip_api":false,"component_class_id":"d0491bb0fbd427bdb2a4549c4d1ac869","key":null,"api_info":{"type":"string"},"example_inputs":"Hello!!"},{"id":118,"type":"form","props":{"scale":0,"min_width":0,"name":"form"},"skip_api":true,"component_class_id":"43cda85c6ff7a5dd8f83d29496b014ee","key":null},{"id":119,"type":"form","props":{"scale":0,"min_width":0,"name":"form"},"skip_api":true,"component_class_id":"43cda85c6ff7a5dd8f83d29496b014ee","key":null},{"id":120,"type":"tabitem","props":{"label":"📊 MathVista Leaderboard","visible":true,"interactive":true,"id":11,"elem_id":"MathVista","name":"tab"},"skip_api":true,"component_class_id":"18f46968e2b273dc5dbda0fe78433d7e","key":null},{"id":121,"type":"markdown","props":{"value":"## MMMU TestMini Evaluation Results\n\n- We report the evaluation results on MathVista **TestMini**, which include 1000 test samples. \n- We adopt `GPT-4-Turbo (1106)` as the answer extractor when we failed to extract the answer with heuristic matching. \n- The performance of **Human (High school)** and **Random Choice** are copied from the official leaderboard. \n**Category Definitions:** **FQA:** figure QA, **GPS:** geometry problem solving, **MWP:** math word problem, **TQA:** textbook QA, **VQA:** visual QA, **ALG:** algebraic, **ARI:** arithmetic, **GEO:** geometry, **LOG:** logical , **NUM:** numeric, **SCI:** scientific, **STA:** statistical.","show_label":true,"rtl":false,"latex_delimiters":[{"left":"$$","right":"$$","display":true}],"visible":true,"elem_classes":[],"sanitize_html":true,"line_breaks":false,"header_links":false,"show_copy_button":false,"name":"markdown","_selectable":false},"skip_api":false,"component_class_id":"0f35515b9a3362b42bb6721c836157a0","key":null,"api_info":{"type":"string"},"example_inputs":"# Hello!"},{"id":122,"type":"checkboxgroup","props":{"choices":[["Overall","Overall"],["SCI","SCI"],["TQA","TQA"],["NUM","NUM"],["ARI","ARI"],["VQA","VQA"],["GEO","GEO"],["ALG","ALG"],["GPS","GPS"],["MWP","MWP"],["LOG","LOG"],["FQA","FQA"],["STA","STA"]],"value":["Overall"],"type":"value","label":"MathVista CheckBoxes","show_label":true,"container":true,"min_width":160,"interactive":true,"visible":true,"elem_classes":[],"name":"checkboxgroup","_selectable":false},"skip_api":false,"component_class_id":"0635a5d3bf87369f1c2c1c69f8a3d0cc","key":null,"api_info":{"items":{"enum":["Overall","SCI","TQA","NUM","ARI","VQA","GEO","ALG","GPS","MWP","LOG","FQA","STA"],"type":"string"},"title":"Checkbox Group","type":"array"},"example_inputs":["Overall"]},{"id":123,"type":"row","props":{"variant":"default","visible":true,"equal_height":true,"show_progress":false,"name":"row"},"skip_api":true,"component_class_id":"b5cf3d15e2293fb5ccc071d7b8d69f64","key":null},{"id":124,"type":"textbox","props":{"value":"Input the Model Name (fuzzy, case insensitive)","lines":1,"max_lines":20,"label":"Model Name","show_label":true,"container":true,"min_width":160,"interactive":true,"visible":true,"autofocus":false,"autoscroll":true,"elem_classes":[],"type":"text","rtl":false,"show_copy_button":false,"name":"textbox","_selectable":false},"skip_api":false,"component_class_id":"d0491bb0fbd427bdb2a4549c4d1ac869","key":null,"api_info":{"type":"string"},"example_inputs":"Hello!!"},{"id":125,"type":"checkboxgroup","props":{"choices":[["<4B","<4B"],["4B-10B","4B-10B"],["10B-20B","10B-20B"],["20B-40B","20B-40B"],[">40B",">40B"],["Unknown","Unknown"]],"value":["<4B","4B-10B","10B-20B","20B-40B",">40B","Unknown"],"type":"value","label":"Model Size","show_label":true,"container":true,"min_width":160,"interactive":true,"visible":true,"elem_classes":[],"name":"checkboxgroup","_selectable":false},"skip_api":false,"component_class_id":"0635a5d3bf87369f1c2c1c69f8a3d0cc","key":null,"api_info":{"items":{"enum":["<4B","4B-10B","10B-20B","20B-40B",">40B","Unknown"],"type":"string"},"title":"Checkbox Group","type":"array"},"example_inputs":["<4B"]},{"id":126,"type":"checkboxgroup","props":{"choices":[["API","API"],["OpenSource","OpenSource"]],"value":["API","OpenSource"],"type":"value","label":"Model Type","show_label":true,"container":true,"min_width":160,"interactive":true,"visible":true,"elem_classes":[],"name":"checkboxgroup","_selectable":false},"skip_api":false,"component_class_id":"0635a5d3bf87369f1c2c1c69f8a3d0cc","key":null,"api_info":{"items":{"enum":["API","OpenSource"],"type":"string"},"title":"Checkbox Group","type":"array"},"example_inputs":["API"]},{"id":127,"type":"form","props":{"scale":3,"min_width":480,"name":"form"},"skip_api":true,"component_class_id":"43cda85c6ff7a5dd8f83d29496b014ee","key":null},{"id":128,"type":"dataframe","props":{"value":{"headers":["Rank","Method","Param (B)","Language Model","Vision Model","Eval Date","Overall"],"data":[[1,"SenseNova-V6-5-Pro",null,"","","2025/09/03",82.8],[2,"BlueLM-2.6-3B",3.0,"","","2025/09/17",82.3],[3,"GPT-5-20250807",null,"","","2025/08/14",81.9],[4,"Gemini-2.5-Pro",null,"","","2025/04/07",80.9],[5,"Kimi-VL-A3B-Thinking-2506",16.4,"Moonlight-16B-A3B","MoonViT","2025/07/02",79.5],[6,"GPT-5-mini-20250807",null,"","","2025/08/14",79.2],[7,"InternVL3-78B",78.4,"Qwen2.5-72B","InternViT-6B-v2.5","2025/04/14",79.0],[8,"SenseNova",null,"","","2024/12/12",78.4],[9,"R-4B",4.82,"Qwen3-4B","SigLip-400M","2025/08/11",78.0],[10,"MiMo-VL-7B",8.31,"Mimo-7B","Qwen2.5-ViT","2025/07/02",77.4],[11,"SenseNova-V6-Pro",null,"","","2025/05/05",76.9],[12,"CongRong-v2.0",null,"","","2025/05/20",76.8],[13,"BlueLM-2.5-3B",2.9,"BlueLM-base-3B","Siglip2-So400M","2025/07/16",76.7],[14,"InternVL2.5-78B-MPO",78.0,"Qwen-2.5-72B","InternViT-6B-v2.5","2024/12/29",76.6],[15,"InternVL3-38B",38.4,"Qwen2.5-32B","InternViT-6B-v2.5","2025/04/14",76.3],[16,"Ovis2-34B",34.9,"Qwen2.5-32B","AIMv2-1B","2025/02/18",76.1],[17,"TeleMM",null,"","","2024/12/31",75.7],[18,"MUG-U-7B",7.0,"","","2025/03/19",74.8],[19,"Step-1o",null,"","","2025/01/13",74.7],[20,"BailingMM-Lite-1203",21.0,"Bailing-20B","SigLIP-400M","2024/12/08",74.5],[21,"InternVL3-14B",15.1,"Qwen2.5-14B","InternViT-300M-v2.5","2025/04/14",74.4],[22,"Qwen2.5-VL-72B",73.4,"Qwen2.5-72B","QwenViT","2025/02/02",74.2],[23,"SAIL-VL-1.6-8B",8.33,"Qwen2.5-7B","AIMv2 Huge","2025/04/24",74.2],[24,"Ovis2-16B",16.2,"Qwen2.5-14B","AIMv2 Huge","2025/02/18",73.7],[25,"InternVL2.5-38B-MPO",38.0,"Qwen-2.5-32B","InternViT-6B-v2.5","2024/12/28",73.6],[26,"GLM-4v-Plus-20250111",null,"","","2025/01/25",73.5],[27,"SAIL-VL-1.5-8B",7.95,"Qwen2.5-7B","InternViT-300B","2025/04/23",73.4],[28,"MiniCPM-o-2.6",8.67,"Qwen2.5-7B","SigLIP-400M","2025/01/21",73.3],[29,"VARCO-VISION-2.0-14B",15.2,"Qwen3-14B","SigLIP-400M","2025/08/04",73.2],[30,"GPT-5-nano-20250807",null,"","","2025/08/14",73.1],[31,"JT-VL-Chat-V3.0",null,"","","2025/08/04",72.8],[32,"Qwen2.5-VL-32B",33.5,"Qwen2.5-32B","QwenViT","2025/07/02",72.8],[33,"Taiyi",null,"","","2024/12/11",72.6],[34,"InternVL2.5-38B",38.0,"Qwen-2.5-32B","InternViT-6B-v2.5","2024/12/10",72.4],[35,"BailingMM-Pro-0120",81.0,"Bailing-80B","SigLIP-400M","2025/01/25",72.3],[36,"Ovis2-8B",8.94,"Qwen2.5-7B","AIMv2 Huge","2025/02/18",71.8],[37,"ChatGPT-4o-latest",null,"","","2025/04/07",71.6],[38,"WeThink-Qwen2.5VL-7B",8.29,"Qwen2.5-7B","QwenViT","2025/05/26",71.6],[39,"InternVL2.5-26B-MPO",26.0,"InternLM2.5-20B","InternViT-6B-v2.5","2024/12/28",71.5],[40,"Gemini-2.0-Pro",null,"","","2025/02/27",71.3],[41,"GPT-4.1-mini-20250414",null,"","","2025/04/16",70.9],[42,"bailingMM-mini",17.0,"bailing-mini","bailingMM-encoder-1B
InternViT-6B","2024/10/24",70.8],[43,"InternVL2.5-78B",78.0,"Qwen-2.5-72B","InternViT-6B-v2.5","2024/12/10",70.6],[44,"GPT-4.5",null,"","","2025/03/26",70.5],[45,"InternVL3-8B",7.94,"Qwen2.5-7B","InternViT-300M-v2.5","2025/04/14",70.5],[46,"Gemini-2.0-Flash",null,"","","2025/01/02",70.4],[47,"GPT-4.1-20250414",null,"","","2025/04/16",70.4],[48,"Ovis1.6-Gemma2-27B",28.9,"Gemma2-27B","SigLIP-400M","2024/11/29",70.2],[49,"Qwen2-VL-72B",73.4,"Qwen2-72B","QwenViT","2024/10/28",69.7],[50,"Ovis2-4B",4.62,"Qwen2.5-3B","AIMv2 Huge","2025/02/18",69.6],[51,"Step-1.5V",null,"Step-1.5","stepencoder","2024/10/11",69.4],[52,"InternVL3-9B",9.14,"InternLM3-8B","InternViT-300M-v2.5","2025/04/14",69.0],[53,"Ovis-U1-3B",3.64,"Qwen3-1.7B","aimv2-large-path14-448","2025/07/20",68.9],[54,"GLM-4v-Plus",null,"","","2024/12/11",68.8],[55,"valley2_dpo",8.88,"Qwen2.5-7B","SigLIP-400M","2025/05/30",68.7],[56,"Ola-7b",8.88,"Qwen2.5-7B","Oryx-ViT","2025/02/05",68.4],[57,"LLaVA-OneVision-72B",73.0,"Qwen2-72B","SigLIP-400M","2024/09/19",68.4],[58,"Qwen-VL-Max-0809",72.0,"Qwen2-72B","QwenViT","2024/09/12",68.3],[59,"InternVL2.5-26B",26.0,"InternLM2.5-20B","InternViT-6B-v2.5","2024/12/10",68.2],[60,"Qwen2.5-VL-7B",8.29,"Qwen2.5-7B","QwenViT","2025/02/02",68.1],[61,"Gemini-1.5-Pro-002",null,"","","2024/12/02",67.9],[62,"InternVL2.5-8B-MPO",8.0,"InternLM2.5-7B","InternViT-300M-v2.5","2024/12/28",67.9],[63,"Ristretto-3B",3.84,"Qwen2.5-3B","SigLIP-400M","2025/04/01",67.6],[64,"Kimi-VL-A3B-Thinking",16.4,"Moonlight-16B-A3B","MoonViT","2025/04/23",67.6],[65,"VARCO-VISION-14B",15.2,"Qwen2.5-14B","SigLIP-400M","2025/01/02",67.6],[66,"abab7-preview",null,"","","2024/12/11",67.5],[67,"Ovis1.6-Gemma2-9B",10.2,"Gemma2-9B-It","SigLIP-400M","2024/09/19",67.3],[68,"LLaVA-OneVision-72B (SI)",73.0,"Qwen2-72B","SigLIP-400M","2024/09/19",67.1],[69,"SAIL-VL-1.5-2B",2.47,"Qwen2.5-1.5B","AIMv2 Huge","2025/04/23",67.0],[70,"moonshot-v1-8k",null,"","","2025/03/03",66.9],[71,"Claude3.7-Sonnet",null,"","","2025/02/27",66.8],[72,"grok-2-vision-1212",null,"","","2025/03/03",66.6],[73,"POINTS1.5-Qwen2.5-7B",8.3,"Qwen-2.5-7B","NaViT","2024/12/06",66.4],[74,"VITA-1.5",8.3,"Qwen2-7B","InternViT-300M","2025/01/01",66.2],[75,"HunYuan-Standard-Vision",null,"","","2025/01/15",66.1],[76,"Kimi-VL-A3B-Instruct",16.4,"Moonlight-16B-A3B","MoonViT","2025/04/14",66.0],[77,"InternVL2-8B-MPO-CoT",8.0,"InternLM2.5-7B","InternViT-300M","2024/11/25",65.9],[78,"InternVL2-8B-MPO",8.0,"InternLM2.5-7B","InternViT-300M","2024/11/25",65.8],[79,"Phi-4-MultiModal",5.57,"Phi-4-Mini","SigLIP-400M","2025/03/13",65.8],[80,"InternVL2-Llama3-76B",76.0,"Llama-3-70B-Instruct","InternViT-6B","2024/07/19",65.6],[81,"Ovis1.5-Gemma2-9B",11.4,"Gemma2-9B-It","SigLIP-400M","2024/08/04",65.6],[82,"Claude3.5-Sonnet-20241022",null,"","","2024/11/06",65.3],[83,"Long-VITA-16K",14.0,"Qwen2.5-14B","InternViT-300M","2025/06/13",64.8],[84,"Valley-Eagle",8.9,"Qwen2.5-7B","Qwen-ViT
SigLIP-400M","2024/12/29",64.6],[85,"InternVL2.5-8B",8.0,"InternLM2.5-7B","InternViT-300M-v2.5","2024/12/10",64.5],[86,"QTuneVL1.5-3B",3.75,"Qwen2.5-3B","QwenViT","2025/08/11",64.4],[87,"InternVL2-40B",40.0,"Nous-Hermes-2-Yi-34B","InternViT-6B","2024/07/11",64.3],[88,"Ovis2-2B",2.46,"Qwen2.5-1.5B","AIMv2 Large","2025/02/18",64.1],[89,"InternVL2.5-4B-MPO",4.0,"Qwen-2.5-3B","InternViT-300M-v2.5","2024/12/28",64.1],[90,"NVLM-D-72B",79.4,"Qwen2-72B","InternViT-6B","2024/10/19",64.0],[91,"InternLM-XComposer2.5",8.0,"InternLM2-7B","CLIP ViT-L/14","2024/07/11",64.0],[92,"DeepSeek-VL2",27.5,"DeepSeekMoE-27B","SigLIP-400M","2025/01/01",63.9],[93,"Gemini-1.5-Flash-002",null,"","","2024/12/02",63.7],[94,"Ovis1.5-Llama3-8B",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/07/29",63.3],[95,"POINTS-Yi-1.5-9B",9.5,"Yi-1.5-9B","CLIP ViT-L/14","2024/10/11",63.2],[96,"POINTS-Qwen2.5-7B",8.3,"Qwen-2.5-7B","CLIP ViT-L/14","2024/10/19",63.1],[97,"GPT-4o (0806, detail-high)",null,"","","2024/08/08",62.9],[98,"SAIL-VL-2B",2.1,"Qwen2.5-1.5B","InternViT-300M","2024/12/25",62.8],[99,"LLaVA-OneVision-7B",8.0,"Qwen2-7B","SigLIP-400M","2024/09/16",62.6],[100,"Aria",25.3,"Aria-MoE","SigLIP-400M","2024/12/05",62.4],[101,"DeepSeek-VL2-Small",16.1,"DeepSeekMoE-16B","SigLIP-400M","2025/01/01",61.9],[102,"GPT-4o (0513, detail-high)",null,"","","2024/05/31",61.8],[103,"Claude3.5-Sonnet",null,"","","2024/06/24",61.8],[104,"valley2",8.88,"Qwen2.5-7B","SigLIP-400M","2025/05/30",61.7],[105,"Flash-VL-2B-Dynamic-ISS",2.53,"Qwen-2.5-1.5B-Instruct","SigLIP2-400M-512","2025/05/30",61.7],[106,"Qwen2-VL-7B",8.0,"Qwen2-7B","QwenViT","2024/09/12",61.6],[107,"RBDash-v1.5",79.0,"Qwen2-72B","CLIP ViT-L/14
InternViT-6B","2024/11/17",61.5],[108,"Qwen2.5-VL-3B",3.75,"Qwen2.5-3B","QwenViT","2025/02/02",61.2],[109,"Qwen-VL-Plus-0809",null,"","","2024/09/17",61.2],[110,"CongRong",null,"","","2024/06/26",61.1],[111,"BlueLM-V-3B",3.0,"BlueLM-3B","SigLIP-400M","2024/10/30",60.9],[112,"InternVL2.5-4B",4.0,"Qwen-2.5-3B","InternViT-300M-v2.5","2024/12/10",60.8],[113,"MiniCPM-V-2.6",8.0,"Qwen2-7B","SigLIP-400M","2024/08/08",60.8],[114,"granite-vision-3.1-2b-preview",2.98,"granite-3.1-2b-instruct","SigLip","2025/06/20",60.5],[115,"granite-vision-3.3-2b",2.98,"granite-3.1-2b-instruct","SigLIP2-400M","2025/06/20",60.2],[116,"GPT-4o (1120, detail-high)",null,"","","2024/12/02",60.0],[117,"Gemma3-27B",27.4,"Gemma3-27B","SigLIP-400M","2025/03/19",59.8],[118,"InternLM-XComposer2",7.0,"InternLM2-7B","CLIP ViT-L/14","2024/01/26",59.8],[119,"granite-vision-3.2-2b",2.98,"granite-3.1-2b-instruct","SigLip","2025/06/20",59.7],[120,"InternVL2-26B",26.0,"InternLM2-20B","InternViT-6B","2024/07/11",59.6],[121,"InternLM-XComposer2-4KHD",7.0,"InternLM2-7B","CLIP ViT-L/14","2024/06/09",59.5],[122,"Ovis2-1B",1.27,"Qwen2.5-0.5B","AIMv2 Large","2025/02/18",59.4],[123,"Aquila-VL-2B",2.2,"Qwen-2.5-1.5B","SigLIP-400M","2024/10/24",59.1],[124,"Ovis1.6-Llama3.2-3B",4.1,"Llama-3.2-3B","SigLIP-400M","2024/10/24",58.9],[125,"Idefics3-8B-Llama3",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/08/27",58.7],[126,"LLaVA-OneVision-7B (SI)",8.0,"Qwen2-7B","SigLIP-400M","2024/09/17",58.6],[127,"InternVL2-4B",4.0,"Phi-3","InternViT-300M","2024/07/11",58.5],[128,"InternVL2-8B",8.0,"InternLM2.5-7B","InternViT-300M","2024/07/11",58.3],[129,"Gemini-1.5-Pro",null,"","","2024/06/10",58.3],[130,"Llama-3.2-90B-Vision-Instruct",88.6,"Llama-3.1-70B","","2024/10/19",58.2],[131,"Yi-Vision",null,"","","2024/08/03",57.8],[132,"Step-1.5V-mini",null,"","","2024/12/11",57.8],[133,"InternVL3-2B",2.09,"Qwen2.5-1.5B","InternViT-300M-v2.5","2025/04/14",57.6],[134,"OmChat-v2.0-13B",13.0,"Qwen2-7B","InternViT-6B","2024/08/22",57.2],[135,"GPT-4o (0513, detail-low)",null,"","","2024/05/15",57.2],[136,"H2OVL-2B",2.2,"H2O-DANUBE2-1.8B","InternViT-300M","2024/10/31",56.9],[137,"Pixtral-12B",13.0,"Nemo-12B","ViT-400M","2024/09/16",56.3],[138,"QTuneVL1.5-2B",2.09,"Qwen2.5-1.5B","InternViT-300M-v2.5","2025/08/11",56.1],[139,"Gemma3-12B",12.2,"Gemma3-12B","SigLIP-400M","2025/03/19",56.1],[140,"InternVL-Chat-V1.5",26.0,"InternLM2-20B","InternViT-6B","2024/04/17",56.1],[141,"VARCO-VISION-2.0-1.7B",2.12,"Qwen3-1.7B","SigLIP-400M","2025/08/04",55.8],[142,"Molmo-72B",73.3,"Qwen2-72B","CLIP ViT-L/14","2024/10/28",55.2],[143,"GPT-4v (0409, detail-high)",null,"","","2024/05/15",55.2],[144,"Mini-InternVL-Chat-4B-V1.5",4.0,"Phi-3","InternViT-300M","2024/06/10",55.0],[145,"WeMM",7.0,"InternLM2-7B","SigLIP-400M","2024/06/09",54.9],[146,"MiniCPM-Llama3-V2.5",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/05/27",54.5],[147,"MMAlaya2",26.0,"InternLM2-20B","InternViT-6B","2024/08/27",54.1],[148,"DeepSeek-VL2-Tiny",3.4,"DeepSeekMoE-3B","SigLIP-400M","2025/01/01",54.0],[149,"GPT-4.1-nano-20250414",null,"","","2025/04/16",53.7],[150,"InternVL2.5-2B-MPO",2.0,"InternLM2.5-1.8B","InternViT-300M-v2.5","2024/12/28",53.4],[151,"Eagle-X5-34B-Chat",36.8,"Yi-34B","Clip-448
ConvNeXT-1024
SAM-1024
DET-1024
Pix2Struct-1024","2024/11/29",52.7],[152,"IDEFICS2-8B",8.0,"Mistral-7B","SigLIP-400M","2024/04/26",52.5],[153,"Ross-Qwen2-7B",8.2,"Qwen2-7B","CLIP ViT-L/14","2025/01/17",52.5],[154,"GPT-4o-mini (0718, detail-high)",null,"","","2024/07/20",52.5],[155,"LLaVA-CoT",11.0,"","","2025/01/05",52.5],[156,"GLM-4v-9B",9.0,"GLM-4-9B","EVA-02-5B","2024/06/14",52.2],[157,"GPT-4v (0409, detail-low)",null,"","","2024/05/15",51.8],[158,"SmolVLM2",2.25,"SmolLM2-1.7M","SigLIP-400M","2025/03/13",51.5],[159,"Gemini-1.5-Flash",null,"","","2024/09/16",51.3],[160,"InternVL2.5-2B",2.0,"InternLM2.5-1.8B","InternViT-300M-v2.5","2024/12/10",51.1],[161,"Cambrian-34B",34.0,"Nous-Hermes-2-Yi-34B","CLIP ViT-L/14","2024/07/18",50.9],[162,"Llama-3-MixSense-v1.1",8.0,"Llama-3-8B-Instruct","Florence-2-Large-FT","2024/08/21",50.4],[163,"InternLM-XComposer2-1.8B",2.0,"InternLM2-1.8B","CLIP ViT-L/14","2024/06/09",50.3],[164,"VILA1.5-40B",40.0,"Yi-34B","InternViT-6B","2024/08/25",49.7],[165,"GPT-4v (1106, detail-low)",null,"","","2023/12/23",49.4],[166,"QTuneVL1-2B",2.21,"InternLM2.5-1.8B","InternViT-300M-v2.5","2025/05/05",48.8],[167,"Molmo-7B-D",8.0,"Qwen2-7B","CLIP ViT-L/14","2024/10/12",48.7],[168,"GPT-4v (1106, detail-high)",null,"","","2024/04/22",48.4],[169,"Cambrian-8B",8.0,"Vicuna-v1.5-7B","CLIP ViT-L/14","2024/07/11",48.1],[170,"Qwen2-VL-2B",2.0,"Qwen2-1.5B","QwenViT","2024/09/12",48.0],[171,"XinYuan-VL-2B-Instruct",2.0,"Qwen2-1.5B","QwenViT","2024/09/27",47.7],[172,"Llama-3.2-11B-Vision-Instruct",11.0,"Llama-3.1-8B","","2024/10/07",47.7],[173,"Cambrian-13B",13.0,"Vicuna-v1.5-13B","CLIP ViT-L/14","2024/07/29",47.7],[174,"InternVL2.5-1B-MPO",1.0,"Qwen-2.5-0.5B","InternViT-300M-v2.5","2024/12/28",47.7],[175,"RekaFlash",null,"","","2024/05/07",47.7],[176,"Emu3_chat",8.49,"","","2025/01/26",47.6],[177,"InternVL2.5-1B",1.0,"Qwen-2.5-0.5B","InternViT-300M-v2.5","2024/12/10",47.1],[178,"InternVL2-2B",2.0,"InternLM2-1.8B","InternViT-300M","2024/07/11",47.0],[179,"InternVL3-1B",0.94,"Qwen2.5-0.5B","InternViT-300M-v2.5","2025/04/14",46.9],[180,"Gemini-1.0-Pro",null,"","","2023/12/23",46.5],[181,"Gemma3-4B",4.3,"Gemma3-4B","SigLIP-400M","2025/03/19",46.3],[182,"Claude3-Opus",null,"","","2024/03/28",46.1],[183,"GLM-4v",null,"","","2024/05/20",45.9],[184,"MiniMonkey",2.2,"InternLM2-1.8B","InternViT-300M","2024/09/26",45.6],[185,"XVERSE-V-13B",13.0,"XVERSE-13B","CLIP ViT-L/14","2024/05/10",45.1],[186,"Claude3-Sonnet",null,"","","2024/03/28",45.0],[187,"Phi-3-Vision",4.2,"Phi-3","CLIP ViT-L/14","2024/05/31",44.8],[188,"VITA",47.0,"Mixtral-8x7B","InternViT-300M","2025/01/20",44.5],[189,"Molmo-7B-O",8.0,"Qwen2-7B","CLIP ViT-L/14","2024/10/20",43.9],[190,"SmolVLM-Instruct",2.3,"SmolLM2-1.7B","SigLIP-400M","2025/01/27",43.6],[191,"Qwen-VL-Max",null,"QwenLM","","2024/02/02",43.6],[192,"Vintern-3B-beta",3.7,"Qwen-2.5-3B","InternViT-300M","2024/10/24",43.6],[193,"Phi-3.5-Vision",4.0,"Phi-3.5","CLIP ViT-L/14","2024/08/28",43.3],[194,"HawkVL-2B",2.44,"Qwen2.5-1.5B","QwenViT","2025/06/16",43.3],[195,"SmolVLM-Instruct-DPO",2.3,"SmolLM2-1.7B","SigLIP-400M","2025/01/27",42.9],[196,"Claude3-Haiku",null,"","","2024/03/28",42.6],[197,"Janus-Pro-7B",7.42,"DeepSeek-7B","SigLIP-400M","2025/02/02",42.5],[198,"VILA1.5-13B",13.0,"Vicuna-v1.5-13B","SigLIP-400M","2024/08/25",42.3],[199,"Slime-8B",8.0,"Llama-3-8B-Instruct","CLIP ViT-L/14","2024/09/14",41.8],[200,"Mini-InternVL-Chat-2B-V1.5",2.0,"InternLM2-1.8B","InternViT-300M","2024/06/10",41.3],[201,"Mantis-8B-Idefics2",8.0,"Mistral-7B","SigLIP-400M","2024/08/08",41.2],[202,"Eagle-X5-13B",15.0,"Vicuna-v1.5-13B","Clip-448
ConvNeXT-1024
SAM-1024
DET-1024
Pix2Struct-1024","2024/09/26",40.8],[203,"LLaVA-LLaMA-3-8B",8.0,"Llama-3-8B-Instruct","CLIP ViT-L/14","2024/05/07",40.6],[204,"XGen-MM-Instruct-Interleave-v1.5",4.4,"Phi-3","SigLIP-400M","2024/09/06",40.6],[205,"LLaVA-Next-Yi-34B",34.8,"Yi-34B","CLIP ViT-L/14","2024/03/25",40.5],[206,"InternVL2-1B",1.0,"Qwen2-0.5B","InternViT-300M","2024/07/11",40.4],[207,"XGen-MM-Instruct-DPO-v1.5",4.4,"Phi-3","SigLIP-400M","2024/09/06",40.1],[208,"SmolVLM-500M",0.51,"SmolLM2-360M","ViT-93M","2025/01/27",39.8],[209,"H2OVL-800M",0.83,"H2O-DANUBE3-500M","InternViT-300M","2024/10/31",39.8],[210,"MiniCPM-V-2",2.8,"MiniCPM-2.4B","SigLIP-400M","2024/04/15",39.8],[211,"LLaVA-Next-Qwen-32B",33.0,"Qwen-1.5-32B","SigLIP-400M","2024/08/08",39.6],[212,"Eagle-X5-7B",9.0,"Vicuna-v1.5-7B","Clip-448
ConvNeXT-1024
SAM-1024
DET-1024
Pix2Struct-1024","2024/09/26",38.8],[213,"CogVLM2-19B-Chat",19.0,"Llama-3-8B-Instruct","EVA2-CLIP-E","2024/05/31",38.7],[214,"Qwen-VL-Plus",null,"QwenLM","","2024/01/10",38.2],[215,"360VL-70B",70.0,"Llama-3-70B-Instruct","CLIP ViT-L/14","2024/05/25",37.9],[216,"LLaVA-Next-Llama3",8.0,"Llama-3-8B-Instruct","CLIP ViT-L/14","2024/07/29",37.7],[217,"MolmoE-1B",7.2,"OLMoE-1B-7B-0924","CLIP ViT-L/14","2024/10/21",37.6],[218,"Falcon2-VLM-11B",11.4,"Falcon2-11B","CLIP ViT-L/14","2024/10/30",37.6],[219,"SmolVLM2-500M",0.51,"SmolLM2-360M","ViT-93M","2025/03/13",37.5],[220,"RekaEdge",null,"","","2024/05/31",37.5],[221,"Llama-3-VILA1.5-8B",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/08/25",37.4],[222,"DeepSeek-VL-7B",7.3,"DeekSeek-7B","SAM-B
SigLIP-L","2024/03/21",37.2],[223,"SmolVLM-256M",0.26,"SmolLM2-135M","ViT-93M","2025/01/27",37.0],[224,"Slime-7B",7.0,"Vicuna-v1.5-7B","CLIP ViT-L/14","2024/09/14",36.9],[225,"Monkey-Chat",9.8,"Qwen-7B","ViT-BigHuge","2024/01/16",36.0],[226,"LLaVA-OneVision-0.5B",1.0,"Qwen2-0.5B","SigLIP-400M","2024/09/16",35.9],[227,"CogVLM-17B-Chat",17.0,"Vicuna-v1.5-7B","EVA2-CLIP-E","2024/01/03",35.3],[228,"LLaVA-Next-Interleave-7B-DPO",8.0,"Qwen-1.5-7B","SigLIP-400M","2024/07/29",35.3],[229,"Qwen-VL-Chat",9.6,"Qwen-7B","ViT-G/16","2023/08/24",35.3],[230,"Bunny-Llama3-8B",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/07/18",35.2],[231,"OmniLMM-12B",12.0,"Zephyr-7B-β","EVA-02-5B","2024/02/07",35.2],[232,"LLaVA-Next-Vicuna-13B",13.4,"Vicuna-v1.5-13B","CLIP ViT-L/14","2024/03/25",35.1],[233,"LLaVA-Next-Mistral-7B",7.6,"Mistral-7B","CLIP ViT-L/14","2024/03/25",34.9],[234,"Slime-13B",13.0,"Vicuna-v1.5-13B","CLIP ViT-L/14","2024/09/14",34.5],[235,"SmolVLM2-256M",0.26,"SmolLM2-135M","ViT-93M","2025/03/13",34.0],[236,"LLaVA-Next-Interleave-7B",8.0,"Qwen-1.5-7B","SigLIP-400M","2024/08/08",34.0],[237,"Moondream2",1.9,"SigLIP-400M","Phi-1.5","2024/10/20",33.8],[238,"Janus-1.3B",2.1,"DeepSeek-1B","SigLIP-400M","2024/10/24",33.7],[239,"Monkey",9.8,"Qwen-7B","ViT-BigHuge","2024/01/11",33.5],[240,"Vintern-1B-v2",3.7,"Qwen2-0.5B","InternViT-300M","2024/11/16",33.1],[241,"LLaVA-OneVision-0.5B (SI)",1.0,"Qwen2-0.5B","SigLIP-400M","2024/09/17",32.7],[242,"Mantis-8B-siglip-llama3",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/08/08",32.7],[243,"TransCore-M",13.4,"PCITransGPT-13B","CLIP ViT-L/14","2024/04/16",32.5],[244,"LLaVA-Next-Vicuna-7B",7.1,"Vicuna-v1.5-7B","CLIP ViT-L/14","2024/03/25",32.5],[245,"VILA1.5-3B",3.0,"Sheared-LLaMA-2.7B","SigLIP-400M","2024/08/25",31.8],[246,"Yi-VL-34B",34.6,"Yi-34B","CLIP ViT-H/14","2024/01/25",31.6],[247,"SmolVLM-Synthetic",2.3,"SmolLM2-1.7B","SigLIP-400M","2025/01/27",31.5],[248,"Emu2_chat",37.0,"Llama-33B","EVA-02-CLIP-E-plus","2024/01/17",31.3],[249,"DeepSeek-VL-1.3B",2.0,"DeekSeek-1B","SAM-B
SigLIP-L","2024/03/21",30.7],[250,"MiniCPM-V",3.0,"MiniCPM-2.4B","SigLIP-400M","2024/02/07",30.6],[251,"Mantis-8B-clip-llama3",8.0,"Llama-3-8B-Instruct","CLIP ViT-L/14","2024/08/08",30.4],[252,"Mantis-8B-Fuyu",8.0,"Fuyu-8B","","2024/09/07",30.2],[253,"InternLM-XComposer",8.0,"InternLM-7B","EVA-G","2023/09/26",29.9],[254,"Yi-VL-6B",6.6,"Yi-6B","CLIP ViT-H/14","2024/01/25",29.7],[255,"ShareCaptioner",8.0,"InternLM-7B","EVA-G","2024/01/03",29.5],[256,"ShareGPT4V-13B",13.4,"Vicuna-v1.5-13B","CLIP ViT-L/14","2023/12/08",29.4],[257,"LLaVA-InternLM2-7B (QLoRA)",8.1,"InternLM2-7B","CLIP ViT-L/14","2024/01/17",28.9],[258,"IDEFICS-80B-Instruct",80.0,"Llama-65B","CLIP ViT-H/14","2023/07/25",28.9],[259,"PaliGemma-3B-mix-448",3.0,"Gemma-2B","SigLIP-400M","2024/05/17",28.5],[260,"LLaVA-InternLM2-20B (QLoRA)",20.2,"InternLM2-20B","CLIP ViT-L/14","2024/01/17",28.5],[261,"LLaVA-v1.5-13B (QLoRA)",13.4,"Vicuna-v1.5-13B","CLIP ViT-L/14","2023/12/28",28.5],[262,"AKI-4B",4.33,"Phi-3.5","SigLIP-400M","2025/03/25",28.5],[263,"LLaVA-v1.5-13B",13.4,"Vicuna-v1.5-13B","CLIP ViT-L/14","2023/10/05",27.7],[264,"Parrot-7B",8.0,"Qwen2-7B","CLIP ViT-L/14","2024/08/22",27.2],[265,"LLaVA-InternLM-7B (QLoRA)",7.6,"InternLM-7B","CLIP ViT-L/14","2023/12/28",27.1],[266,"ShareGPT4V-7B",7.2,"Vicuna-v1.5-7B","CLIP ViT-L/14","2023/12/08",26.6],[267,"PandaGPT-13B",14.0,"Vicuna-13B","ImageBind ViT-H/14","2023/05/25",25.6],[268,"LLaVA-v1.5-7B",7.2,"Vicuna-v1.5-7B","CLIP ViT-L/14","2023/10/05",25.5],[269,"mPLUG-Owl2",8.2,"Llama-2-7B","CLIP ViT-L/14","2023/11/10",25.5],[270,"LLaVA-v1-7B",7.2,"Llama-7B","CLIP ViT-L/14","2023/04/17",25.4],[271,"LLaVA-v1.5-7B (QLoRA)",7.2,"Vicuna-v1.5-7B","CLIP ViT-L/14","2023/12/28",25.4],[272,"IDEFICS-9B-Instruct",9.0,"Llama-7B","CLIP ViT-H/14","2023/07/25",25.1],[273,"Moondream1",1.9,"SigLIP-400M","Phi-1.5","2024/09/26",24.7],[274,"InstructBLIP-7B",8.0,"Vicuna-7B","EVA-G","2023/05/11",24.6],[275,"Kosmos2",1.7,"","","2024/10/19",24.5],[276,"MiniGPT-4-v2",8.0,"Llama-2-13B","EVA-G","2023/10/27",24.0],[277,"VisualGLM",8.0,"ChatGLM 6B","EVA-CLIP","2023/05/17",23.9],[278,"Chameleon-30B",30.0,"","","2024/07/29",23.8],[279,"abab6.5s",null,"","","2024/12/11",23.5],[280,"MMAlaya",7.8,"Alaya-7B-Chat","EVA-G","2024/01/29",22.9],[281,"Chameleon-7B",7.0,"","","2024/07/29",22.5],[282,"MiniGPT-4-v1-7B",8.0,"Vicuna-7B","EVA-G","2023/04/20",21.3],[283,"OpenFlamingo v2",9.0,"MPT 7B","CLIP ViT-L/14","2023/06/28",19.9],[284,"Qwen-VL",9.6,"Qwen-7B","ViT-G/16","2023/08/24",18.1]],"metadata":null},"headers":["1","2","3"],"row_count":[1,"dynamic"],"col_count":[3,"dynamic"],"datatype":["number","html","number","html","html","str","number"],"type":"pandas","latex_delimiters":[{"left":"$$","right":"$$","display":true}],"show_label":true,"height":500,"min_width":160,"interactive":false,"visible":true,"elem_classes":[],"wrap":true,"line_breaks":true,"column_widths":[],"name":"dataframe","_selectable":false},"skip_api":false,"component_class_id":"6a51bb3357f2e94c40fb8d4fbe06aa8e","key":null,"api_info":{"properties":{"headers":{"items":{"type":"string"},"title":"Headers","type":"array"},"data":{"items":{"items":{},"type":"array"},"title":"Data","type":"array"},"metadata":{"anyOf":[{"additionalProperties":{"anyOf":[{"items":{},"type":"array"},{"type":"null"}]},"type":"object"},{"type":"null"}],"default":null,"title":"Metadata"}},"required":["headers","data"],"title":"DataframeData","type":"object"},"example_inputs":{"headers":["a","b"],"data":[["foo","bar"]]}},{"id":129,"type":"textbox","props":{"value":"MathVista","lines":1,"max_lines":20,"label":"MathVista","show_label":true,"container":true,"min_width":160,"visible":false,"autofocus":false,"autoscroll":true,"elem_classes":[],"type":"text","rtl":false,"show_copy_button":false,"name":"textbox","_selectable":false},"skip_api":false,"component_class_id":"d0491bb0fbd427bdb2a4549c4d1ac869","key":null,"api_info":{"type":"string"},"example_inputs":"Hello!!"},{"id":130,"type":"form","props":{"scale":0,"min_width":0,"name":"form"},"skip_api":true,"component_class_id":"43cda85c6ff7a5dd8f83d29496b014ee","key":null},{"id":131,"type":"form","props":{"scale":0,"min_width":0,"name":"form"},"skip_api":true,"component_class_id":"43cda85c6ff7a5dd8f83d29496b014ee","key":null},{"id":132,"type":"tabitem","props":{"label":"📊 HallusionBench Leaderboard","visible":true,"interactive":true,"id":12,"elem_id":"HallusionBench","name":"tab"},"skip_api":true,"component_class_id":"18f46968e2b273dc5dbda0fe78433d7e","key":null},{"id":133,"type":"markdown","props":{"value":"[**HallusionBench**](https://github.com/tianyi-lab/HallusionBench) is a benchmark to evaluate hallucination of VLMs. It asks a set of visual questions with one original image and one modified image (the answers for a question can be different, considering the image content). \n\n**Examples in HallusionBench:**\n\n| Original Figure | Modified Figure |\n| ------------------------------------------------------------ | ------------------------------------------------------------ |\n| ![](http://opencompass.openxlab.space/utils/Hallu0.png) | ![](http://opencompass.openxlab.space/utils/Hallu1.png) |\n| **Q1.** Is the right orange circle the same size as the left orange circle? **A1. Yes** | **Q1.** Is the right orange circle the same size as the left orange circle? **A1. No** |\n| **Q2.** Is the right orange circle larger than the left orange circle? **A2. No** | **Q2.** Is the right orange circle larger than the left orange circle? **A2. Yes** |\n| **Q3.** Is the right orange circle smaller than the left orange circle? **A3. No** | **Q3.** Is the right orange circle smaller than the left orange circle? **A3. No** |\n\n**Metrics**:\n\n>- aAcc: The overall accuracy of **all** atomic questions. \n>\n>- qAcc: The mean accuracy of unique **questions**. One question can be asked multiple times with different figures, we consider VLM correctly solved a unique question only if it succeeds in all pairs for this unique question.\n>- fAcc: The mean accuracy of all **figures**. One figure is associated with multiple questions, we consider VLM correct on a figure only if it succeeds to solve all questions of this figure. \n\n**Evaluation Setting**:\n\n> 1. **No-visual** Questions (questions asked without the associated figure) in HallusionBench are **skipped** during evaluation.\n> 2. When we failed to extract Yes / No from the VLM prediction, we adopt **GPT-3.5-Turbo-0613** as the answer extractor.\n> 3. We report aAcc, qAcc, and fAcc for all evaluated VLMs. \n\n## HallusionBench Evaluation Results","show_label":true,"rtl":false,"latex_delimiters":[{"left":"$$","right":"$$","display":true}],"visible":true,"elem_classes":[],"sanitize_html":true,"line_breaks":false,"header_links":false,"show_copy_button":false,"name":"markdown","_selectable":false},"skip_api":false,"component_class_id":"0f35515b9a3362b42bb6721c836157a0","key":null,"api_info":{"type":"string"},"example_inputs":"# Hello!"},{"id":134,"type":"checkboxgroup","props":{"choices":[["Overall","Overall"],["aAcc","aAcc"],["fAcc","fAcc"],["qAcc","qAcc"]],"value":["Overall"],"type":"value","label":"HallusionBench CheckBoxes","show_label":true,"container":true,"min_width":160,"interactive":true,"visible":true,"elem_classes":[],"name":"checkboxgroup","_selectable":false},"skip_api":false,"component_class_id":"0635a5d3bf87369f1c2c1c69f8a3d0cc","key":null,"api_info":{"items":{"enum":["Overall","aAcc","fAcc","qAcc"],"type":"string"},"title":"Checkbox Group","type":"array"},"example_inputs":["Overall"]},{"id":135,"type":"row","props":{"variant":"default","visible":true,"equal_height":true,"show_progress":false,"name":"row"},"skip_api":true,"component_class_id":"b5cf3d15e2293fb5ccc071d7b8d69f64","key":null},{"id":136,"type":"textbox","props":{"value":"Input the Model Name (fuzzy, case insensitive)","lines":1,"max_lines":20,"label":"Model Name","show_label":true,"container":true,"min_width":160,"interactive":true,"visible":true,"autofocus":false,"autoscroll":true,"elem_classes":[],"type":"text","rtl":false,"show_copy_button":false,"name":"textbox","_selectable":false},"skip_api":false,"component_class_id":"d0491bb0fbd427bdb2a4549c4d1ac869","key":null,"api_info":{"type":"string"},"example_inputs":"Hello!!"},{"id":137,"type":"checkboxgroup","props":{"choices":[["<4B","<4B"],["4B-10B","4B-10B"],["10B-20B","10B-20B"],["20B-40B","20B-40B"],[">40B",">40B"],["Unknown","Unknown"]],"value":["<4B","4B-10B","10B-20B","20B-40B",">40B","Unknown"],"type":"value","label":"Model Size","show_label":true,"container":true,"min_width":160,"interactive":true,"visible":true,"elem_classes":[],"name":"checkboxgroup","_selectable":false},"skip_api":false,"component_class_id":"0635a5d3bf87369f1c2c1c69f8a3d0cc","key":null,"api_info":{"items":{"enum":["<4B","4B-10B","10B-20B","20B-40B",">40B","Unknown"],"type":"string"},"title":"Checkbox Group","type":"array"},"example_inputs":["<4B"]},{"id":138,"type":"checkboxgroup","props":{"choices":[["API","API"],["OpenSource","OpenSource"]],"value":["API","OpenSource"],"type":"value","label":"Model Type","show_label":true,"container":true,"min_width":160,"interactive":true,"visible":true,"elem_classes":[],"name":"checkboxgroup","_selectable":false},"skip_api":false,"component_class_id":"0635a5d3bf87369f1c2c1c69f8a3d0cc","key":null,"api_info":{"items":{"enum":["API","OpenSource"],"type":"string"},"title":"Checkbox Group","type":"array"},"example_inputs":["API"]},{"id":139,"type":"form","props":{"scale":3,"min_width":480,"name":"form"},"skip_api":true,"component_class_id":"43cda85c6ff7a5dd8f83d29496b014ee","key":null},{"id":140,"type":"dataframe","props":{"value":{"headers":["Rank","Method","Param (B)","Language Model","Vision Model","Eval Date","Overall"],"data":[[1,"SenseNova-V6-Pro",null,"","","2025/05/05",67.1],[2,"SenseNova-V6-5-Pro",null,"","","2025/09/03",66.7],[3,"GPT-5-20250807",null,"","","2025/08/14",65.2],[4,"JT-VL-Chat-V3.0",null,"","","2025/08/04",64.4],[5,"Gemini-2.5-Pro",null,"","","2025/04/07",64.1],[6,"MiMo-VL-7B",8.31,"Mimo-7B","Qwen2.5-ViT","2025/07/02",63.8],[7,"CongRong-v2.0",null,"","","2025/05/20",63.2],[8,"BlueLM-2.6-3B",3.0,"","","2025/09/17",63.1],[9,"GPT-5-mini-20250807",null,"","","2025/08/14",62.5],[10,"GPT-5-nano-20250807",null,"","","2025/08/14",60.9],[11,"TeleMM",null,"","","2024/12/31",60.6],[12,"BailingMM-Lite-1203",21.0,"Bailing-20B","SigLIP-400M","2024/12/08",60.1],[13,"GPT-4.5",null,"","","2025/03/26",60.0],[14,"R-4B",4.82,"Qwen3-4B","SigLip-400M","2025/08/11",60.0],[15,"BlueLM-2.5-3B",2.9,"BlueLM-base-3B","Siglip2-So400M","2025/07/16",60.0],[16,"Kimi-VL-A3B-Thinking-2506",16.4,"Moonlight-16B-A3B","MoonViT","2025/07/02",59.8],[17,"InternVL2.5-38B-MPO",38.0,"Qwen-2.5-32B","InternViT-6B-v2.5","2024/12/28",59.7],[18,"BailingMM-Pro-0120",81.0,"Bailing-80B","SigLIP-400M","2025/01/25",59.4],[19,"Qwen-VL-Max-0809",72.0,"Qwen2-72B","QwenViT","2024/09/12",59.2],[20,"InternVL3-78B",78.4,"Qwen2.5-72B","InternViT-6B-v2.5","2025/04/14",59.1],[21,"Ovis2-34B",34.9,"Qwen2.5-32B","AIMv2-1B","2025/02/18",58.8],[22,"Qwen2-VL-72B",73.4,"Qwen2-72B","QwenViT","2024/10/28",58.7],[23,"GLM-4v-Plus-20250111",null,"","","2025/01/25",58.5],[24,"GPT-4.1-20250414",null,"","","2025/04/16",58.5],[25,"InternVL3-38B",38.4,"Qwen2.5-32B","InternViT-6B-v2.5","2025/04/14",58.4],[26,"Qwen2.5-VL-32B",33.5,"Qwen2.5-32B","QwenViT","2025/07/02",58.4],[27,"InternVL2.5-78B-MPO",78.0,"Qwen-2.5-72B","InternViT-6B-v2.5","2024/12/29",58.1],[28,"Gemini-2.0-Flash",null,"","","2025/01/02",58.0],[29,"InternVL2.5-38B",38.0,"Qwen-2.5-32B","InternViT-6B-v2.5","2024/12/10",57.9],[30,"HunYuan-Standard-Vision",null,"","","2025/01/15",57.7],[31,"SenseNova",null,"","","2024/12/12",57.4],[32,"InternVL2.5-78B",78.0,"Qwen-2.5-72B","InternViT-6B-v2.5","2024/12/10",57.4],[33,"ChatGPT-4o-latest",null,"","","2025/04/07",57.0],[34,"Taiyi",null,"","","2024/12/11",56.8],[35,"Ovis2-16B",16.2,"Qwen2.5-14B","AIMv2 Huge","2025/02/18",56.8],[36,"InternVL2-40B",40.0,"Nous-Hermes-2-Yi-34B","InternViT-6B","2024/07/11",56.5],[37,"Ovis2-8B",8.94,"Qwen2.5-7B","AIMv2 Huge","2025/02/18",56.3],[38,"GPT-4o (1120, detail-high)",null,"","","2024/12/02",56.2],[39,"Gemini-1.5-Pro-002",null,"","","2024/12/02",55.9],[40,"InternVL3-14B",15.1,"Qwen2.5-14B","InternViT-300M-v2.5","2025/04/14",55.9],[41,"Step-1o",null,"","","2025/01/13",55.8],[42,"Ovis-U1-3B",3.64,"Qwen3-1.7B","aimv2-large-path14-448","2025/07/20",55.8],[43,"InternVL2.5-26B",26.0,"InternLM2.5-20B","InternViT-6B-v2.5","2024/12/10",55.8],[44,"GLM-4v-Plus",null,"","","2024/12/11",55.6],[45,"Claude3.5-Sonnet-20241022",null,"","","2024/11/06",55.5],[46,"InternVL2-Llama3-76B",76.0,"Llama-3-70B-Instruct","InternViT-6B","2024/07/19",55.4],[47,"Claude3.7-Sonnet",null,"","","2025/02/27",55.4],[48,"WeThink-Qwen2.5VL-7B",8.29,"Qwen2.5-7B","QwenViT","2025/05/26",55.3],[49,"GPT-4o (0513, detail-high)",null,"","","2024/05/31",55.0],[50,"Qwen2.5-VL-72B",73.4,"Qwen2.5-72B","QwenViT","2025/02/02",54.6],[51,"SAIL-VL-1.5-8B",7.95,"Qwen2.5-7B","InternViT-300B","2025/04/23",54.5],[52,"SAIL-VL-1.6-8B",8.33,"Qwen2.5-7B","AIMv2 Huge","2025/04/24",54.4],[53,"Step-1.5V",null,"Step-1.5","stepencoder","2024/10/11",54.3],[54,"GPT-4o (0806, detail-high)",null,"","","2024/08/08",54.2],[55,"Ovis1.6-Gemma2-27B",28.9,"Gemma2-27B","SigLIP-400M","2024/11/29",54.1],[56,"Gemini-1.5-Flash-002",null,"","","2024/12/02",53.9],[57,"Ovis2-4B",4.62,"Qwen2.5-3B","AIMv2 Huge","2025/02/18",53.8],[58,"Ola-7b",8.88,"Qwen2.5-7B","Oryx-ViT","2025/02/05",53.5],[59,"VARCO-VISION-2.0-14B",15.2,"Qwen3-14B","SigLIP-400M","2025/08/04",53.2],[60,"valley2_dpo",8.88,"Qwen2.5-7B","SigLIP-400M","2025/05/30",52.4],[61,"InternVL2.5-26B-MPO",26.0,"InternLM2.5-20B","InternViT-6B-v2.5","2024/12/28",52.4],[62,"Kimi-VL-A3B-Thinking",16.4,"Moonlight-16B-A3B","MoonViT","2025/04/23",52.3],[63,"Ovis1.6-Gemma2-9B",10.2,"Gemma2-9B-It","SigLIP-400M","2024/09/19",52.2],[64,"Qwen2.5-VL-7B",8.29,"Qwen2.5-7B","QwenViT","2025/02/02",51.9],[65,"GPT-4o (0513, detail-low)",null,"","","2024/05/15",51.7],[66,"abab7-preview",null,"","","2024/12/11",51.7],[67,"InternVL2.5-8B-MPO",8.0,"InternLM2.5-7B","InternViT-300M-v2.5","2024/12/28",51.7],[68,"grok-2-vision-1212",null,"","","2025/03/03",51.7],[69,"InternVL2-26B",26.0,"InternLM2-20B","InternViT-6B","2024/07/11",51.5],[70,"MUG-U-7B",7.0,"","","2025/03/19",51.3],[71,"MiniCPM-o-2.6",8.67,"Qwen2.5-7B","SigLIP-400M","2025/01/21",51.1],[72,"Qwen-VL-Plus-0809",null,"","","2024/09/17",51.1],[73,"InternVL3-9B",9.14,"InternLM3-8B","InternViT-300M-v2.5","2025/04/14",50.8],[74,"CongRong",null,"","","2024/06/26",50.6],[75,"Qwen2-VL-7B",8.0,"Qwen2-7B","QwenViT","2024/09/12",50.4],[76,"Yi-Vision",null,"","","2024/08/03",50.3],[77,"Ovis2-2B",2.46,"Qwen2.5-1.5B","AIMv2 Large","2025/02/18",50.2],[78,"Ristretto-3B",3.84,"Qwen2.5-3B","SigLIP-400M","2025/04/01",50.2],[79,"SAIL-VL-1.5-2B",2.47,"Qwen2.5-1.5B","AIMv2 Huge","2025/04/23",50.0],[80,"POINTS1.5-Qwen2.5-7B",8.3,"Qwen-2.5-7B","NaViT","2024/12/06",50.0],[81,"Claude3.5-Sonnet",null,"","","2024/06/24",49.9],[82,"Gemini-2.0-Pro",null,"","","2025/02/27",49.8],[83,"NVLM-D-72B",79.4,"Qwen2-72B","InternViT-6B","2024/10/19",49.7],[84,"MMAlaya2",26.0,"InternLM2-20B","InternViT-6B","2024/08/27",49.3],[85,"GPT-4.1-mini-20250414",null,"","","2025/04/16",49.3],[86,"RBDash-v1.5",79.0,"Qwen2-72B","CLIP ViT-L/14
InternViT-6B","2024/11/17",49.1],[87,"LLaVA-OneVision-72B (SI)",73.0,"Qwen2-72B","SigLIP-400M","2024/09/19",49.0],[88,"InternVL2.5-8B",8.0,"InternLM2.5-7B","InternViT-300M-v2.5","2024/12/10",49.0],[89,"InternVL3-8B",7.94,"Qwen2.5-7B","InternViT-300M-v2.5","2025/04/14",49.0],[90,"QTuneVL1.5-3B",3.75,"Qwen2.5-3B","QwenViT","2025/08/11",49.0],[91,"Gemma3-27B",27.4,"Gemma3-27B","SigLIP-400M","2025/03/19",48.8],[92,"Gemini-1.5-Flash",null,"","","2024/09/16",48.5],[93,"Flash-VL-2B-Dynamic-ISS",2.53,"Qwen-2.5-1.5B-Instruct","SigLIP2-400M-512","2025/05/30",48.5],[94,"OmChat-v2.0-13B",13.0,"Qwen2-7B","InternViT-6B","2024/08/22",48.4],[95,"Kimi-VL-A3B-Instruct",16.4,"Moonlight-16B-A3B","MoonViT","2025/04/14",48.4],[96,"Ovis1.5-Gemma2-9B",11.4,"Gemma2-9B-It","SigLIP-400M","2024/08/04",48.2],[97,"MiniCPM-V-2.6",8.0,"Qwen2-7B","SigLIP-400M","2024/08/08",48.1],[98,"Valley-Eagle",8.9,"Qwen2.5-7B","Qwen-ViT
SigLIP-400M","2024/12/29",48.0],[99,"BlueLM-V-3B",3.0,"BlueLM-3B","SigLIP-400M","2024/10/30",48.0],[100,"LLaVA-OneVision-72B",73.0,"Qwen2-72B","SigLIP-400M","2024/09/19",47.9],[101,"POINTS-Yi-1.5-9B",9.5,"Yi-1.5-9B","CLIP ViT-L/14","2024/10/11",47.8],[102,"InternVL2-8B-MPO",8.0,"InternLM2.5-7B","InternViT-300M","2024/11/25",47.7],[103,"LLaVA-CoT",11.0,"","","2025/01/05",47.7],[104,"valley2",8.88,"Qwen2.5-7B","SigLIP-400M","2025/05/30",47.6],[105,"LLaVA-OneVision-7B (SI)",8.0,"Qwen2-7B","SigLIP-400M","2024/09/17",47.5],[106,"InternVL2.5-4B-MPO",4.0,"Qwen-2.5-3B","InternViT-300M-v2.5","2024/12/28",47.5],[107,"WeMM",7.0,"InternLM2-7B","SigLIP-400M","2024/06/09",47.5],[108,"InternVL-Chat-V1.5",26.0,"InternLM2-20B","InternViT-6B","2024/04/17",47.4],[109,"Gemma3-12B",12.2,"Gemma3-12B","SigLIP-400M","2025/03/19",47.2],[110,"Pixtral-12B",13.0,"Nemo-12B","ViT-400M","2024/09/16",47.0],[111,"granite-vision-3.3-2b",2.98,"granite-3.1-2b-instruct","SigLIP2-400M","2025/06/20",47.0],[112,"VARCO-VISION-14B",15.2,"Qwen2.5-14B","SigLIP-400M","2025/01/02",46.8],[113,"Step-1.5V-mini",null,"","","2024/12/11",46.7],[114,"Qwen2.5-VL-3B",3.75,"Qwen2.5-3B","QwenViT","2025/02/02",46.6],[115,"Molmo-72B",73.3,"Qwen2-72B","CLIP ViT-L/14","2024/10/28",46.6],[116,"InternVL2.5-4B",4.0,"Qwen-2.5-3B","InternViT-300M-v2.5","2024/12/10",46.6],[117,"GPT-4v (1106, detail-low)",null,"","","2023/12/23",46.5],[118,"Molmo-7B-D",8.0,"Qwen2-7B","CLIP ViT-L/14","2024/10/12",46.4],[119,"moonshot-v1-8k",null,"","","2025/03/03",46.1],[120,"GPT-4o-mini (0718, detail-high)",null,"","","2024/07/20",46.1],[121,"SAIL-VL-2B",2.1,"Qwen2.5-1.5B","InternViT-300M","2024/12/25",45.9],[122,"Gemini-1.0-Pro",null,"","","2023/12/23",45.7],[123,"Gemini-1.5-Pro",null,"","","2024/06/10",45.6],[124,"POINTS-Qwen2.5-7B",8.3,"Qwen-2.5-7B","CLIP ViT-L/14","2024/10/19",45.6],[125,"Long-VITA-16K",14.0,"Qwen2.5-14B","InternViT-300M","2025/06/13",45.5],[126,"bailingMM-mini",17.0,"bailing-mini","bailingMM-encoder-1B
InternViT-6B","2024/10/24",45.4],[127,"DeepSeek-VL2",27.5,"DeepSeekMoE-27B","SigLIP-400M","2025/01/01",45.3],[128,"Ovis2-1B",1.27,"Qwen2.5-0.5B","AIMv2 Large","2025/02/18",45.2],[129,"InternVL2-8B-MPO-CoT",8.0,"InternLM2.5-7B","InternViT-300M","2024/11/25",45.1],[130,"InternVL2-8B",8.0,"InternLM2.5-7B","InternViT-300M","2024/07/11",45.0],[131,"GLM-4v-9B",9.0,"GLM-4-9B","EVA-02-5B","2024/06/14",45.0],[132,"GLM-4v",null,"","","2024/05/20",44.9],[133,"Aria",25.3,"Aria-MoE","SigLIP-400M","2024/12/05",44.8],[134,"VITA-1.5",8.3,"Qwen2-7B","InternViT-300M","2025/01/01",44.6],[135,"Llama-3.2-90B-Vision-Instruct",88.6,"Llama-3.1-70B","","2024/10/19",44.1],[136,"GPT-4v (0409, detail-high)",null,"","","2024/05/15",43.9],[137,"DeepSeek-VL2-Small",16.1,"DeepSeekMoE-16B","SigLIP-400M","2025/01/01",43.8],[138,"Ovis1.6-Llama3.2-3B",4.1,"Llama-3.2-3B","SigLIP-400M","2024/10/24",43.8],[139,"Idefics3-8B-Llama3",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/08/27",43.7],[140,"QTuneVL1.5-2B",2.09,"Qwen2.5-1.5B","InternViT-300M-v2.5","2025/08/11",43.4],[141,"Vintern-3B-beta",3.7,"Qwen-2.5-3B","InternViT-300M","2024/10/24",43.2],[142,"InternLM-XComposer2.5",8.0,"InternLM2-7B","CLIP ViT-L/14","2024/07/11",43.1],[143,"Mini-InternVL-Chat-4B-V1.5",4.0,"Phi-3","InternViT-300M","2024/06/10",43.0],[144,"Aquila-VL-2B",2.2,"Qwen-2.5-1.5B","SigLIP-400M","2024/10/24",43.0],[145,"InternLM-XComposer2-4KHD",7.0,"InternLM2-7B","CLIP ViT-L/14","2024/06/09",42.5],[146,"QTuneVL1-2B",2.21,"InternLM2.5-1.8B","InternViT-300M-v2.5","2025/05/05",42.4],[147,"InternVL2-4B",4.0,"Phi-3","InternViT-300M","2024/07/11",42.4],[148,"Qwen2-VL-2B",2.0,"Qwen2-1.5B","QwenViT","2024/09/12",42.4],[149,"MiniCPM-Llama3-V2.5",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/05/27",42.4],[150,"Ovis1.5-Llama3-8B",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/07/29",42.3],[151,"InternVL2.5-2B",2.0,"InternLM2.5-1.8B","InternViT-300M-v2.5","2024/12/10",42.3],[152,"InternVL3-2B",2.09,"Qwen2.5-1.5B","InternViT-300M-v2.5","2025/04/14",41.9],[153,"Cambrian-34B",34.0,"Nous-Hermes-2-Yi-34B","CLIP ViT-L/14","2024/07/18",41.6],[154,"GPT-4v (0409, detail-low)",null,"","","2024/05/15",41.6],[155,"granite-vision-3.1-2b-preview",2.98,"granite-3.1-2b-instruct","SigLip","2025/06/20",41.4],[156,"CogVLM2-19B-Chat",19.0,"Llama-3-8B-Instruct","EVA2-CLIP-E","2024/05/31",41.3],[157,"Claude3-Sonnet",null,"","","2024/03/28",41.3],[158,"Qwen-VL-Max",null,"QwenLM","","2024/02/02",41.2],[159,"VITA",47.0,"Mixtral-8x7B","InternViT-300M","2025/01/20",41.0],[160,"InternLM-XComposer2",7.0,"InternLM2-7B","CLIP ViT-L/14","2024/01/26",41.0],[161,"HawkVL-2B",2.44,"Qwen2.5-1.5B","QwenViT","2025/06/16",40.9],[162,"VILA1.5-40B",40.0,"Yi-34B","InternViT-6B","2024/08/25",40.9],[163,"Gemma3-4B",4.3,"Gemma3-4B","SigLIP-400M","2025/03/19",40.8],[164,"InternVL2.5-2B-MPO",2.0,"InternLM2.5-1.8B","InternViT-300M-v2.5","2024/12/28",40.7],[165,"granite-vision-3.2-2b",2.98,"granite-3.1-2b-instruct","SigLip","2025/06/20",40.7],[166,"SmolVLM2",2.25,"SmolLM2-1.7M","SigLIP-400M","2025/03/13",40.6],[167,"Qwen-VL-Plus",null,"QwenLM","","2024/01/10",40.6],[168,"Phi-4-MultiModal",5.57,"Phi-4-Mini","SigLIP-400M","2025/03/13",40.5],[169,"Phi-3.5-Vision",4.0,"Phi-3.5","CLIP ViT-L/14","2024/08/28",40.5],[170,"Llama-3.2-11B-Vision-Instruct",11.0,"Llama-3.1-8B","","2024/10/07",40.3],[171,"SmolVLM-Instruct-DPO",2.3,"SmolLM2-1.7B","SigLIP-400M","2025/01/27",39.8],[172,"XGen-MM-Instruct-Interleave-v1.5",4.4,"Phi-3","SigLIP-400M","2024/09/06",39.8],[173,"DeepSeek-VL2-Tiny",3.4,"DeepSeekMoE-3B","SigLIP-400M","2025/01/01",39.6],[174,"SmolVLM-Instruct",2.3,"SmolLM2-1.7B","SigLIP-400M","2025/01/27",39.5],[175,"Janus-Pro-7B",7.42,"DeepSeek-7B","SigLIP-400M","2025/02/02",39.5],[176,"Cambrian-13B",13.0,"Vicuna-v1.5-13B","CLIP ViT-L/14","2024/07/29",39.4],[177,"InternVL2.5-1B",1.0,"Qwen-2.5-0.5B","InternViT-300M-v2.5","2024/12/10",39.4],[178,"Molmo-7B-O",8.0,"Qwen2-7B","CLIP ViT-L/14","2024/10/20",39.4],[179,"Monkey-Chat",9.8,"Qwen-7B","ViT-BigHuge","2024/01/16",39.3],[180,"LLaVA-Next-Qwen-32B",33.0,"Qwen-1.5-32B","SigLIP-400M","2024/08/08",39.3],[181,"GPT-4v (1106, detail-high)",null,"","","2024/04/22",39.3],[182,"VILA1.5-13B",13.0,"Vicuna-v1.5-13B","SigLIP-400M","2024/08/25",39.3],[183,"RekaFlash",null,"","","2024/05/07",39.2],[184,"Claude3-Haiku",null,"","","2024/03/28",39.2],[185,"IDEFICS2-8B",8.0,"Mistral-7B","SigLIP-400M","2024/04/26",39.1],[186,"Phi-3-Vision",4.2,"Phi-3","CLIP ViT-L/14","2024/05/31",39.0],[187,"MiniMonkey",2.2,"InternLM2-1.8B","InternViT-300M","2024/09/26",38.7],[188,"Ross-Qwen2-7B",8.2,"Qwen2-7B","CLIP ViT-L/14","2025/01/17",38.7],[189,"VARCO-VISION-2.0-1.7B",2.12,"Qwen3-1.7B","SigLIP-400M","2025/08/04",38.6],[190,"Eagle-X5-34B-Chat",36.8,"Yi-34B","Clip-448
ConvNeXT-1024
SAM-1024
DET-1024
Pix2Struct-1024","2024/11/29",38.1],[191,"MolmoE-1B",7.2,"OLMoE-1B-7B-0924","CLIP ViT-L/14","2024/10/21",38.0],[192,"InternVL2-2B",2.0,"InternLM2-1.8B","InternViT-300M","2024/07/11",38.0],[193,"Claude3-Opus",null,"","","2024/03/28",37.8],[194,"Eagle-X5-13B",15.0,"Vicuna-v1.5-13B","Clip-448
ConvNeXT-1024
SAM-1024
DET-1024
Pix2Struct-1024","2024/09/26",37.8],[195,"Bunny-Llama3-8B",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/07/18",37.7],[196,"Vintern-1B-v2",3.7,"Qwen2-0.5B","InternViT-300M","2024/11/16",37.7],[197,"Mini-InternVL-Chat-2B-V1.5",2.0,"InternLM2-1.8B","InternViT-300M","2024/06/10",37.3],[198,"InternVL3-1B",0.94,"Qwen2.5-0.5B","InternViT-300M-v2.5","2025/04/14",37.2],[199,"Mantis-8B-Idefics2",8.0,"Mistral-7B","SigLIP-400M","2024/08/08",37.1],[200,"XGen-MM-Instruct-DPO-v1.5",4.4,"Phi-3","SigLIP-400M","2024/09/06",37.0],[201,"GPT-4.1-nano-20250414",null,"","","2025/04/16",36.9],[202,"Qwen-VL-Chat",9.6,"Qwen-7B","ViT-G/16","2023/08/24",36.8],[203,"LLaVA-Next-Interleave-7B-DPO",8.0,"Qwen-1.5-7B","SigLIP-400M","2024/07/29",36.8],[204,"Llama-3-MixSense-v1.1",8.0,"Llama-3-8B-Instruct","Florence-2-Large-FT","2024/08/21",36.2],[205,"MiniCPM-V",3.0,"MiniCPM-2.4B","SigLIP-400M","2024/02/07",36.2],[206,"MiniCPM-V-2",2.8,"MiniCPM-2.4B","SigLIP-400M","2024/04/15",36.1],[207,"Yi-VL-6B",6.6,"Yi-6B","CLIP ViT-H/14","2024/01/25",36.0],[208,"InternLM-XComposer",8.0,"InternLM-7B","EVA-G","2023/09/26",36.0],[209,"H2OVL-2B",2.2,"H2O-DANUBE2-1.8B","InternViT-300M","2024/10/31",35.9],[210,"Falcon2-VLM-11B",11.4,"Falcon2-11B","CLIP ViT-L/14","2024/10/30",35.9],[211,"OmniLMM-12B",12.0,"Zephyr-7B-β","EVA-02-5B","2024/02/07",35.8],[212,"CogVLM-17B-Chat",17.0,"Vicuna-v1.5-7B","EVA2-CLIP-E","2024/01/03",35.4],[213,"Eagle-X5-7B",9.0,"Vicuna-v1.5-7B","Clip-448
ConvNeXT-1024
SAM-1024
DET-1024
Pix2Struct-1024","2024/09/26",35.4],[214,"Yi-VL-34B",34.6,"Yi-34B","CLIP ViT-H/14","2024/01/25",35.3],[215,"Llama-3-VILA1.5-8B",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/08/25",35.3],[216,"Parrot-7B",8.0,"Qwen2-7B","CLIP ViT-L/14","2024/08/22",35.2],[217,"RekaEdge",null,"","","2024/05/31",35.1],[218,"Monkey",9.8,"Qwen-7B","ViT-BigHuge","2024/01/11",34.9],[219,"XinYuan-VL-2B-Instruct",2.0,"Qwen2-1.5B","QwenViT","2024/09/27",34.9],[220,"SmolVLM-Synthetic",2.3,"SmolLM2-1.7B","SigLIP-400M","2025/01/27",34.8],[221,"LLaVA-Next-Yi-34B",34.8,"Yi-34B","CLIP ViT-L/14","2024/03/25",34.8],[222,"360VL-70B",70.0,"Llama-3-70B-Instruct","CLIP ViT-L/14","2024/05/25",34.8],[223,"LLaVA-Next-Interleave-7B",8.0,"Qwen-1.5-7B","SigLIP-400M","2024/08/08",34.8],[224,"InternVL2.5-1B-MPO",1.0,"Qwen-2.5-0.5B","InternViT-300M-v2.5","2024/12/28",34.8],[225,"DeepSeek-VL-7B",7.3,"DeekSeek-7B","SAM-B
SigLIP-L","2024/03/21",34.5],[226,"InternVL2-1B",1.0,"Qwen2-0.5B","InternViT-300M","2024/07/11",34.3],[227,"Mantis-8B-siglip-llama3",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/08/08",34.2],[228,"ShareCaptioner",8.0,"InternLM-7B","EVA-G","2024/01/03",34.2],[229,"AKI-4B",4.33,"Phi-3.5","SigLIP-400M","2025/03/25",33.9],[230,"InternLM-XComposer2-1.8B",2.0,"InternLM2-1.8B","CLIP ViT-L/14","2024/06/09",33.7],[231,"abab6.5s",null,"","","2024/12/11",33.4],[232,"XVERSE-V-13B",13.0,"XVERSE-13B","CLIP ViT-L/14","2024/05/10",33.3],[233,"LLaVA-Next-Llama3",8.0,"Llama-3-8B-Instruct","CLIP ViT-L/14","2024/07/29",33.1],[234,"Moondream2",1.9,"SigLIP-400M","Phi-1.5","2024/10/20",33.0],[235,"MMAlaya",7.8,"Alaya-7B-Chat","EVA-G","2024/01/29",32.9],[236,"Slime-7B",7.0,"Vicuna-v1.5-7B","CLIP ViT-L/14","2024/09/14",32.8],[237,"PaliGemma-3B-mix-448",3.0,"Gemma-2B","SigLIP-400M","2024/05/17",32.2],[238,"Slime-13B",13.0,"Vicuna-v1.5-13B","CLIP ViT-L/14","2024/09/14",32.1],[239,"MiniGPT-4-v1-7B",8.0,"Vicuna-7B","EVA-G","2023/04/20",31.9],[240,"LLaVA-Next-Vicuna-13B",13.4,"Vicuna-v1.5-13B","CLIP ViT-L/14","2024/03/25",31.8],[241,"Slime-8B",8.0,"Llama-3-8B-Instruct","CLIP ViT-L/14","2024/09/14",31.8],[242,"LLaVA-OneVision-0.5B (SI)",1.0,"Qwen2-0.5B","SigLIP-400M","2024/09/17",31.7],[243,"Emu3_chat",8.49,"","","2025/01/26",31.7],[244,"LLaVA-OneVision-7B",8.0,"Qwen2-7B","SigLIP-400M","2024/09/16",31.6],[245,"Mantis-8B-clip-llama3",8.0,"Llama-3-8B-Instruct","CLIP ViT-L/14","2024/08/08",31.3],[246,"VILA1.5-3B",3.0,"Sheared-LLaMA-2.7B","SigLIP-400M","2024/08/25",31.2],[247,"InstructBLIP-7B",8.0,"Vicuna-7B","EVA-G","2023/05/11",31.2],[248,"SmolVLM-500M",0.51,"SmolLM2-360M","ViT-93M","2025/01/27",31.1],[249,"Cambrian-8B",8.0,"Vicuna-v1.5-7B","CLIP ViT-L/14","2024/07/11",30.6],[250,"Janus-1.3B",2.1,"DeepSeek-1B","SigLIP-400M","2024/10/24",30.3],[251,"MiniGPT-4-v2",8.0,"Llama-2-13B","EVA-G","2023/10/27",30.0],[252,"Qwen-VL",9.6,"Qwen-7B","ViT-G/16","2023/08/24",29.9],[253,"Mantis-8B-Fuyu",8.0,"Fuyu-8B","","2024/09/07",29.8],[254,"H2OVL-800M",0.83,"H2O-DANUBE3-500M","InternViT-300M","2024/10/31",29.6],[255,"Emu2_chat",37.0,"Llama-33B","EVA-02-CLIP-E-plus","2024/01/17",29.5],[256,"OpenFlamingo v2",9.0,"MPT 7B","CLIP ViT-L/14","2023/06/28",29.4],[257,"mPLUG-Owl2",8.2,"Llama-2-7B","CLIP ViT-L/14","2023/11/10",29.4],[258,"Moondream1",1.9,"SigLIP-400M","Phi-1.5","2024/09/26",29.2],[259,"LLaVA-Next-Mistral-7B",7.6,"Mistral-7B","CLIP ViT-L/14","2024/03/25",29.1],[260,"LLaVA-InternLM-7B (QLoRA)",7.6,"InternLM-7B","CLIP ViT-L/14","2023/12/28",28.9],[261,"LLaVA-LLaMA-3-8B",8.0,"Llama-3-8B-Instruct","CLIP ViT-L/14","2024/05/07",28.7],[262,"ShareGPT4V-7B",7.2,"Vicuna-v1.5-7B","CLIP ViT-L/14","2023/12/08",28.6],[263,"ShareGPT4V-13B",13.4,"Vicuna-v1.5-13B","CLIP ViT-L/14","2023/12/08",28.4],[264,"LLaVA-OneVision-0.5B",1.0,"Qwen2-0.5B","SigLIP-400M","2024/09/16",27.9],[265,"SmolVLM-256M",0.26,"SmolLM2-135M","ViT-93M","2025/01/27",27.9],[266,"SmolVLM2-500M",0.51,"SmolLM2-360M","ViT-93M","2025/03/13",27.7],[267,"LLaVA-Next-Vicuna-7B",7.1,"Vicuna-v1.5-7B","CLIP ViT-L/14","2024/03/25",27.6],[268,"LLaVA-v1.5-7B",7.2,"Vicuna-v1.5-7B","CLIP ViT-L/14","2023/10/05",27.6],[269,"DeepSeek-VL-1.3B",2.0,"DeekSeek-1B","SAM-B
SigLIP-L","2024/03/21",27.6],[270,"TransCore-M",13.4,"PCITransGPT-13B","CLIP ViT-L/14","2024/04/16",27.3],[271,"IDEFICS-9B-Instruct",9.0,"Llama-7B","CLIP ViT-H/14","2023/07/25",27.3],[272,"LLaVA-InternLM2-7B (QLoRA)",8.1,"InternLM2-7B","CLIP ViT-L/14","2024/01/17",26.7],[273,"LLaVA-InternLM2-20B (QLoRA)",20.2,"InternLM2-20B","CLIP ViT-L/14","2024/01/17",26.4],[274,"LLaVA-v1.5-13B (QLoRA)",13.4,"Vicuna-v1.5-13B","CLIP ViT-L/14","2023/12/28",26.2],[275,"LLaVA-v1.5-7B (QLoRA)",7.2,"Vicuna-v1.5-7B","CLIP ViT-L/14","2023/12/28",25.2],[276,"VisualGLM",8.0,"ChatGLM 6B","EVA-CLIP","2023/05/17",25.0],[277,"LLaVA-v1.5-13B",13.4,"Vicuna-v1.5-13B","CLIP ViT-L/14","2023/10/05",24.5],[278,"SmolVLM2-256M",0.26,"SmolLM2-135M","ViT-93M","2025/03/13",24.3],[279,"IDEFICS-80B-Instruct",80.0,"Llama-65B","CLIP ViT-H/14","2023/07/25",23.4],[280,"LLaVA-v1-7B",7.2,"Llama-7B","CLIP ViT-L/14","2023/04/17",21.6],[281,"PandaGPT-13B",14.0,"Vicuna-13B","ImageBind ViT-H/14","2023/05/25",20.0],[282,"Kosmos2",1.7,"","","2024/10/19",19.8],[283,"Chameleon-30B",30.0,"","","2024/07/29",18.6],[284,"Chameleon-7B",7.0,"","","2024/07/29",17.1]],"metadata":null},"headers":["1","2","3"],"row_count":[1,"dynamic"],"col_count":[3,"dynamic"],"datatype":["number","html","number","html","html","str","number"],"type":"pandas","latex_delimiters":[{"left":"$$","right":"$$","display":true}],"show_label":true,"height":500,"min_width":160,"interactive":false,"visible":true,"elem_classes":[],"wrap":true,"line_breaks":true,"column_widths":[],"name":"dataframe","_selectable":false},"skip_api":false,"component_class_id":"6a51bb3357f2e94c40fb8d4fbe06aa8e","key":null,"api_info":{"properties":{"headers":{"items":{"type":"string"},"title":"Headers","type":"array"},"data":{"items":{"items":{},"type":"array"},"title":"Data","type":"array"},"metadata":{"anyOf":[{"additionalProperties":{"anyOf":[{"items":{},"type":"array"},{"type":"null"}]},"type":"object"},{"type":"null"}],"default":null,"title":"Metadata"}},"required":["headers","data"],"title":"DataframeData","type":"object"},"example_inputs":{"headers":["a","b"],"data":[["foo","bar"]]}},{"id":141,"type":"textbox","props":{"value":"HallusionBench","lines":1,"max_lines":20,"label":"HallusionBench","show_label":true,"container":true,"min_width":160,"visible":false,"autofocus":false,"autoscroll":true,"elem_classes":[],"type":"text","rtl":false,"show_copy_button":false,"name":"textbox","_selectable":false},"skip_api":false,"component_class_id":"d0491bb0fbd427bdb2a4549c4d1ac869","key":null,"api_info":{"type":"string"},"example_inputs":"Hello!!"},{"id":142,"type":"form","props":{"scale":0,"min_width":0,"name":"form"},"skip_api":true,"component_class_id":"43cda85c6ff7a5dd8f83d29496b014ee","key":null},{"id":143,"type":"form","props":{"scale":0,"min_width":0,"name":"form"},"skip_api":true,"component_class_id":"43cda85c6ff7a5dd8f83d29496b014ee","key":null},{"id":144,"type":"tabitem","props":{"label":"📊 LLaVABench Leaderboard","visible":true,"interactive":true,"id":13,"elem_id":"LLaVABench","name":"tab"},"skip_api":true,"component_class_id":"18f46968e2b273dc5dbda0fe78433d7e","key":null},{"id":145,"type":"markdown","props":{"value":"## LLaVABench Evaluation Results\n\n- In LLaVABench Evaluation, we use GPT-4-Turbo (gpt-4-1106-preview) as the judge LLM to assign scores to the VLM outputs. We only perform the evaluation once due to the limited variance among results of multiple evaluation pass originally reported. \n- No specific prompt template adopted for **ALL VLMs**.\n- We also include the official results (obtained by gpt-4-0314) for applicable models. ","show_label":true,"rtl":false,"latex_delimiters":[{"left":"$$","right":"$$","display":true}],"visible":true,"elem_classes":[],"sanitize_html":true,"line_breaks":false,"header_links":false,"show_copy_button":false,"name":"markdown","_selectable":false},"skip_api":false,"component_class_id":"0f35515b9a3362b42bb6721c836157a0","key":null,"api_info":{"type":"string"},"example_inputs":"# Hello!"},{"id":146,"type":"checkboxgroup","props":{"choices":[["Overall","Overall"],["Overall (official)","Overall (official)"],["Conv","Conv"],["Complex","Complex"],["Detail","Detail"]],"value":["Overall","Overall (official)"],"type":"value","label":"LLaVABench CheckBoxes","show_label":true,"container":true,"min_width":160,"interactive":true,"visible":true,"elem_classes":[],"name":"checkboxgroup","_selectable":false},"skip_api":false,"component_class_id":"0635a5d3bf87369f1c2c1c69f8a3d0cc","key":null,"api_info":{"items":{"enum":["Overall","Overall (official)","Conv","Complex","Detail"],"type":"string"},"title":"Checkbox Group","type":"array"},"example_inputs":["Overall"]},{"id":147,"type":"row","props":{"variant":"default","visible":true,"equal_height":true,"show_progress":false,"name":"row"},"skip_api":true,"component_class_id":"b5cf3d15e2293fb5ccc071d7b8d69f64","key":null},{"id":148,"type":"textbox","props":{"value":"Input the Model Name (fuzzy, case insensitive)","lines":1,"max_lines":20,"label":"Model Name","show_label":true,"container":true,"min_width":160,"interactive":true,"visible":true,"autofocus":false,"autoscroll":true,"elem_classes":[],"type":"text","rtl":false,"show_copy_button":false,"name":"textbox","_selectable":false},"skip_api":false,"component_class_id":"d0491bb0fbd427bdb2a4549c4d1ac869","key":null,"api_info":{"type":"string"},"example_inputs":"Hello!!"},{"id":149,"type":"checkboxgroup","props":{"choices":[["<4B","<4B"],["4B-10B","4B-10B"],["10B-20B","10B-20B"],["20B-40B","20B-40B"],[">40B",">40B"],["Unknown","Unknown"]],"value":["<4B","4B-10B","10B-20B","20B-40B",">40B","Unknown"],"type":"value","label":"Model Size","show_label":true,"container":true,"min_width":160,"interactive":true,"visible":true,"elem_classes":[],"name":"checkboxgroup","_selectable":false},"skip_api":false,"component_class_id":"0635a5d3bf87369f1c2c1c69f8a3d0cc","key":null,"api_info":{"items":{"enum":["<4B","4B-10B","10B-20B","20B-40B",">40B","Unknown"],"type":"string"},"title":"Checkbox Group","type":"array"},"example_inputs":["<4B"]},{"id":150,"type":"checkboxgroup","props":{"choices":[["API","API"],["OpenSource","OpenSource"]],"value":["API","OpenSource"],"type":"value","label":"Model Type","show_label":true,"container":true,"min_width":160,"interactive":true,"visible":true,"elem_classes":[],"name":"checkboxgroup","_selectable":false},"skip_api":false,"component_class_id":"0635a5d3bf87369f1c2c1c69f8a3d0cc","key":null,"api_info":{"items":{"enum":["API","OpenSource"],"type":"string"},"title":"Checkbox Group","type":"array"},"example_inputs":["API"]},{"id":151,"type":"form","props":{"scale":3,"min_width":480,"name":"form"},"skip_api":true,"component_class_id":"43cda85c6ff7a5dd8f83d29496b014ee","key":null},{"id":152,"type":"dataframe","props":{"value":{"headers":["Rank","Method","Param (B)","Language Model","Vision Model","Eval Date","Overall","Overall (official)"],"data":[[1,"Step-1o",null,"","","2025/01/13",107.3,"N/A"],[2,"GPT-4.1-20250414",null,"","","2025/04/16",105.6,"N/A"],[3,"InternVL2.5-78B-MPO",78.0,"Qwen-2.5-72B","InternViT-6B-v2.5","2024/12/29",103.9,"N/A"],[4,"Gemma3-27B",27.4,"Gemma3-27B","SigLIP-400M","2025/03/19",103.1,"N/A"],[5,"GPT-4o (0513, detail-high)",null,"","","2024/05/31",102.0,"N/A"],[6,"InternVL2-40B",40.0,"Nous-Hermes-2-Yi-34B","InternViT-6B","2024/07/11",101.4,"N/A"],[7,"Gemini-2.0-Pro",null,"","","2025/02/27",100.8,"N/A"],[8,"InternVL3-78B",78.4,"Qwen2.5-72B","InternViT-6B-v2.5","2025/04/14",100.4,"N/A"],[9,"grok-2-vision-1212",null,"","","2025/03/03",100.0,"N/A"],[10,"GPT-4v (0409, detail-high)",null,"","","2024/05/15",99.8,"N/A"],[11,"GPT-4.1-mini-20250414",null,"","","2025/04/16",99.6,"N/A"],[12,"InternVL2.5-38B-MPO",38.0,"Qwen-2.5-32B","InternViT-6B-v2.5","2024/12/28",99.6,"N/A"],[13,"Step-1.5V",null,"Step-1.5","stepencoder","2024/10/11",99.1,"N/A"],[14,"GPT-4o-mini (0718, detail-high)",null,"","","2024/07/20",98.7,"N/A"],[15,"Qwen2.5-VL-72B",73.4,"Qwen2.5-72B","QwenViT","2025/02/02",98.7,"N/A"],[16,"abab7-preview",null,"","","2024/12/11",98.0,"N/A"],[17,"Gemini-2.0-Flash",null,"","","2025/01/02",97.7,"N/A"],[18,"GPT-4o (0513, detail-low)",null,"","","2024/05/15",97.2,"N/A"],[19,"GPT-4o (0806, detail-high)",null,"","","2024/08/08",96.5,"N/A"],[20,"InternVL2-Llama3-76B",76.0,"Llama-3-70B-Instruct","InternViT-6B","2024/07/19",96.3,"N/A"],[21,"Gemini-1.5-Pro",null,"","","2024/06/10",95.3,"N/A"],[22,"GPT-4v (0409, detail-low)",null,"","","2024/05/15",95.3,"N/A"],[23,"BailingMM-Pro-0120",81.0,"Bailing-80B","SigLIP-400M","2025/01/25",95.1,"N/A"],[24,"InternVL2.5-26B-MPO",26.0,"InternLM2.5-20B","InternViT-6B-v2.5","2024/12/28",94.7,"N/A"],[25,"InternVL3-38B",38.4,"Qwen2.5-32B","InternViT-6B-v2.5","2025/04/14",94.7,"N/A"],[26,"Claude3.7-Sonnet",null,"","","2025/02/27",94.4,"N/A"],[27,"Ovis2-34B",34.9,"Qwen2.5-32B","AIMv2-1B","2025/02/18",93.3,"N/A"],[28,"InternVL2-26B",26.0,"InternLM2-20B","InternViT-6B","2024/07/11",93.1,"N/A"],[29,"GPT-4v (1106, detail-low)",null,"","","2023/12/23",93.1,"N/A"],[30,"Gemma3-12B",12.2,"Gemma3-12B","SigLIP-400M","2025/03/19",93.0,"N/A"],[31,"Ovis2-16B",16.2,"Qwen2.5-14B","AIMv2 Huge","2025/02/18",93.0,"N/A"],[32,"GLM-4v-Plus",null,"","","2024/12/11",92.9,"N/A"],[33,"GLM-4v-Plus-20250111",null,"","","2025/01/25",92.7,"N/A"],[34,"Gemma3-4B",4.3,"Gemma3-4B","SigLIP-400M","2025/03/19",92.5,"N/A"],[35,"Taiyi",null,"","","2024/12/11",92.2,"N/A"],[36,"GLM-4v-9B",9.0,"GLM-4-9B","EVA-02-5B","2024/06/14",92.1,"N/A"],[37,"Ovis1.6-Gemma2-27B",28.9,"Gemma2-27B","SigLIP-400M","2024/11/29",91.0,"N/A"],[38,"Qwen2.5-VL-7B",8.29,"Qwen2.5-7B","QwenViT","2025/02/02",91.0,"N/A"],[39,"Step-1.5V-mini",null,"","","2024/12/11",90.6,"N/A"],[40,"LLaVA-OneVision-72B (SI)",73.0,"Qwen2-72B","SigLIP-400M","2024/09/19",90.4,"N/A"],[41,"DeepSeek-VL2",27.5,"DeepSeekMoE-27B","SigLIP-400M","2025/01/01",89.7,"N/A"],[42,"Claude3.5-Sonnet-20241022",null,"","","2024/11/06",89.4,"N/A"],[43,"Ovis1.6-Gemma2-9B",10.2,"Gemma2-9B-It","SigLIP-400M","2024/09/19",89.0,"N/A"],[44,"GPT-4.1-nano-20250414",null,"","","2025/04/16",88.8,"N/A"],[45,"GPT-4v (1106, detail-high)",null,"","","2024/04/22",88.0,"N/A"],[46,"GLM-4v",null,"","","2024/05/20",87.5,"N/A"],[47,"Ovis2-4B",4.62,"Qwen2.5-3B","AIMv2 Huge","2025/02/18",87.4,"N/A"],[48,"InternVL2.5-8B-MPO",8.0,"InternLM2.5-7B","InternViT-300M-v2.5","2024/12/28",87.3,"N/A"],[49,"MiniCPM-o-2.6",8.67,"Qwen2.5-7B","SigLIP-400M","2025/01/21",87.1,"N/A"],[50,"Ovis2-8B",8.94,"Qwen2.5-7B","AIMv2 Huge","2025/02/18",87.0,"N/A"],[51,"NVLM-D-72B",79.4,"Qwen2-72B","InternViT-6B","2024/10/19",86.8,"N/A"],[52,"MiniCPM-Llama3-V2.5",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/05/27",86.7,"N/A"],[53,"Llama-3.2-90B-Vision-Instruct",88.6,"Llama-3.1-70B","","2024/10/19",86.5,"N/A"],[54,"LLaVA-OneVision-72B",73.0,"Qwen2-72B","SigLIP-400M","2024/09/19",86.3,"N/A"],[55,"RekaFlash",null,"","","2024/05/07",86.3,"N/A"],[56,"DeepSeek-VL2-Small",16.1,"DeepSeekMoE-16B","SigLIP-400M","2025/01/01",86.1,"N/A"],[57,"Llama-3.2-11B-Vision-Instruct",11.0,"Llama-3.1-8B","","2024/10/07",85.8,"N/A"],[58,"Kimi-VL-A3B-Instruct",16.4,"Moonlight-16B-A3B","MoonViT","2025/04/14",85.6,"N/A"],[59,"MiniCPM-V-2.6",8.0,"Qwen2-7B","SigLIP-400M","2024/08/08",85.4,"N/A"],[60,"InternVL3-8B",7.94,"Qwen2.5-7B","InternViT-300M-v2.5","2025/04/14",85.2,"N/A"],[61,"InternVL3-14B",15.1,"Qwen2.5-14B","InternViT-300M-v2.5","2025/04/14",84.4,"N/A"],[62,"InternVL2.5-4B-MPO",4.0,"Qwen-2.5-3B","InternViT-300M-v2.5","2024/12/28",84.3,"N/A"],[63,"Ovis1.6-Llama3.2-3B",4.1,"Llama-3.2-3B","SigLIP-400M","2024/10/24",84.2,"N/A"],[64,"MMAlaya2",26.0,"InternLM2-20B","InternViT-6B","2024/08/27",83.9,"N/A"],[65,"InternVL3-9B",9.14,"InternLM3-8B","InternViT-300M-v2.5","2025/04/14",83.8,"N/A"],[66,"InternVL-Chat-V1.5",26.0,"InternLM2-20B","InternViT-6B","2024/04/17",83.3,"N/A"],[67,"CogVLM2-19B-Chat",19.0,"Llama-3-8B-Instruct","EVA2-CLIP-E","2024/05/31",83.0,"N/A"],[68,"Molmo-72B",73.3,"Qwen2-72B","CLIP ViT-L/14","2024/10/28",82.4,"N/A"],[69,"Qwen-VL-Max",null,"QwenLM","","2024/02/02",82.3,"N/A"],[70,"LLaVA-Next-Qwen-32B",33.0,"Qwen-1.5-32B","SigLIP-400M","2024/08/08",82.0,"N/A"],[71,"Cambrian-34B",34.0,"Nous-Hermes-2-Yi-34B","CLIP ViT-L/14","2024/07/18",82.0,"N/A"],[72,"LLaVA-Next-Yi-34B",34.8,"Yi-34B","CLIP ViT-L/14","2024/03/25",81.8,"N/A"],[73,"RekaEdge",null,"","","2024/05/31",81.6,"N/A"],[74,"Pixtral-12B",13.0,"Nemo-12B","ViT-400M","2024/09/16",81.5,"N/A"],[75,"Aria",25.3,"Aria-MoE","SigLIP-400M","2024/12/05",81.4,"N/A"],[76,"LLaVA-OneVision-7B",8.0,"Qwen2-7B","SigLIP-400M","2024/09/16",81.0,"N/A"],[77,"Claude3.5-Sonnet",null,"","","2024/06/24",81.0,"N/A"],[78,"RBDash-v1.5",79.0,"Qwen2-72B","CLIP ViT-L/14
InternViT-6B","2024/11/17",80.8,"N/A"],[79,"HunYuan-Standard-Vision",null,"","","2025/01/15",80.8,"N/A"],[80,"CongRong",null,"","","2024/06/26",80.7,"N/A"],[81,"Gemini-1.5-Flash",null,"","","2024/09/16",80.0,"N/A"],[82,"POINTS1.5-Qwen2.5-7B",8.3,"Qwen-2.5-7B","NaViT","2024/12/06",79.9,"N/A"],[83,"Gemini-1.0-Pro",null,"","","2023/12/23",79.9,"N/A"],[84,"Ovis1.5-Llama3-8B",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/07/29",79.9,"N/A"],[85,"InternVL2-8B-MPO-CoT",8.0,"InternLM2.5-7B","InternViT-300M","2024/11/25",78.7,"N/A"],[86,"DeepSeek-VL-7B",7.3,"DeekSeek-7B","SAM-B
SigLIP-L","2024/03/21",77.8,"N/A"],[87,"Eagle-X5-34B-Chat",36.8,"Yi-34B","Clip-448
ConvNeXT-1024
SAM-1024
DET-1024
Pix2Struct-1024","2024/11/29",77.7,"N/A"],[88,"LLaVA-OneVision-7B (SI)",8.0,"Qwen2-7B","SigLIP-400M","2024/09/17",77.6,"N/A"],[89,"Qwen2-VL-72B",73.4,"Qwen2-72B","QwenViT","2024/10/28",77.1,"N/A"],[90,"Qwen2.5-VL-3B",3.75,"Qwen2.5-3B","QwenViT","2025/02/02",77.0,"N/A"],[91,"Ovis2-2B",2.46,"Qwen2.5-1.5B","AIMv2 Large","2025/02/18",76.6,"N/A"],[92,"InternVL2-8B-MPO",8.0,"InternLM2.5-7B","InternViT-300M","2024/11/25",76.5,"N/A"],[93,"TeleMM",null,"","","2024/12/31",76.5,"N/A"],[94,"moonshot-v1-8k",null,"","","2025/03/03",76.5,"N/A"],[95,"Ovis2-1B",1.27,"Qwen2.5-0.5B","AIMv2 Large","2025/02/18",76.2,"N/A"],[96,"Cambrian-13B",13.0,"Vicuna-v1.5-13B","CLIP ViT-L/14","2024/07/29",76.1,"N/A"],[97,"Yi-Vision",null,"","","2024/08/03",76.0,"N/A"],[98,"OmniLMM-12B",12.0,"Zephyr-7B-β","EVA-02-5B","2024/02/07",75.8,"N/A"],[99,"DeepSeek-VL2-Tiny",3.4,"DeepSeekMoE-3B","SigLIP-400M","2025/01/01",75.7,"N/A"],[100,"VILA1.5-40B",40.0,"Yi-34B","InternViT-6B","2024/08/25",75.6,"N/A"],[101,"BailingMM-Lite-1203",21.0,"Bailing-20B","SigLIP-400M","2024/12/08",75.4,"N/A"],[102,"360VL-70B",70.0,"Llama-3-70B-Instruct","CLIP ViT-L/14","2024/05/25",75.1,"N/A"],[103,"Qwen-VL-Max-0809",72.0,"Qwen2-72B","QwenViT","2024/09/12",74.9,"N/A"],[104,"Janus-Pro-7B",7.42,"DeepSeek-7B","SigLIP-400M","2025/02/02",74.4,"N/A"],[105,"CogVLM-17B-Chat",17.0,"Vicuna-v1.5-7B","EVA2-CLIP-E","2024/01/03",73.9,"N/A"],[106,"Claude3-Opus",null,"","","2024/03/28",73.9,"N/A"],[107,"LLaVA-Next-Vicuna-13B",13.4,"Vicuna-v1.5-13B","CLIP ViT-L/14","2024/03/25",73.9,"N/A"],[108,"Qwen-VL-Plus",null,"QwenLM","","2024/01/10",73.7,"N/A"],[109,"VILA1.5-13B",13.0,"Vicuna-v1.5-13B","SigLIP-400M","2024/08/25",73.5,"N/A"],[110,"Ovis1.5-Gemma2-9B",11.4,"Gemma2-9B-It","SigLIP-400M","2024/08/04",73.4,"N/A"],[111,"Qwen-VL-Plus-0809",null,"","","2024/09/17",73.4,"N/A"],[112,"InternVL2-8B",8.0,"InternLM2.5-7B","InternViT-300M","2024/07/11",73.3,"N/A"],[113,"Claude3-Sonnet",null,"","","2024/03/28",73.2,"N/A"],[114,"VARCO-VISION-14B",15.2,"Qwen2.5-14B","SigLIP-400M","2025/01/02",72.8,"N/A"],[115,"VITA-1.5",8.3,"Qwen2-7B","InternViT-300M","2025/01/01",72.8,"N/A"],[116,"LLaVA-Next-Vicuna-7B",7.1,"Vicuna-v1.5-7B","CLIP ViT-L/14","2024/03/25",72.7,"N/A"],[117,"InternLM-XComposer2",7.0,"InternLM2-7B","CLIP ViT-L/14","2024/01/26",72.6,"N/A"],[118,"Molmo-7B-O",8.0,"Qwen2-7B","CLIP ViT-L/14","2024/10/20",72.4,"N/A"],[119,"POINTS-Qwen2.5-7B",8.3,"Qwen-2.5-7B","CLIP ViT-L/14","2024/10/19",72.3,"N/A"],[120,"InternVL3-2B",2.09,"Qwen2.5-1.5B","InternViT-300M-v2.5","2025/04/14",72.1,"N/A"],[121,"Llama-3-VILA1.5-8B",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/08/25",71.7,"N/A"],[122,"bailingMM-mini",17.0,"bailing-mini","bailingMM-encoder-1B
InternViT-6B","2024/10/24",71.5,"N/A"],[123,"LLaVA-Next-Interleave-7B",8.0,"Qwen-1.5-7B","SigLIP-400M","2024/08/08",71.5,"N/A"],[124,"Cambrian-8B",8.0,"Vicuna-v1.5-7B","CLIP ViT-L/14","2024/07/11",71.0,"N/A"],[125,"WeMM",7.0,"InternLM2-7B","SigLIP-400M","2024/06/09",70.9,"N/A"],[126,"POINTS-Yi-1.5-9B",9.5,"Yi-1.5-9B","CLIP ViT-L/14","2024/10/11",70.6,"N/A"],[127,"abab6.5s",null,"","","2024/12/11",70.4,"N/A"],[128,"InternLM-XComposer2.5",8.0,"InternLM2-7B","CLIP ViT-L/14","2024/07/11",70.2,"N/A"],[129,"Eagle-X5-13B",15.0,"Vicuna-v1.5-13B","Clip-448
ConvNeXT-1024
SAM-1024
DET-1024
Pix2Struct-1024","2024/09/26",70.2,"N/A"],[130,"MUG-U-7B",7.0,"","","2025/03/19",70.2,"N/A"],[131,"Qwen2-VL-7B",8.0,"Qwen2-7B","QwenViT","2024/09/12",70.1,"N/A"],[132,"LLaVA-Next-Interleave-7B-DPO",8.0,"Qwen-1.5-7B","SigLIP-400M","2024/07/29",69.9,"N/A"],[133,"XGen-MM-Instruct-DPO-v1.5",4.4,"Phi-3","SigLIP-400M","2024/09/06",69.8,"N/A"],[134,"BlueLM-V-3B",3.0,"BlueLM-3B","SigLIP-400M","2024/10/30",69.3,"N/A"],[135,"MiniCPM-V-2",2.8,"MiniCPM-2.4B","SigLIP-400M","2024/04/15",69.2,"N/A"],[136,"LLaVA-LLaMA-3-8B",8.0,"Llama-3-8B-Instruct","CLIP ViT-L/14","2024/05/07",69.2,"N/A"],[137,"ShareGPT4V-13B",13.4,"Vicuna-v1.5-13B","CLIP ViT-L/14","2023/12/08",69.1,79.9],[138,"Aquila-VL-2B",2.2,"Qwen-2.5-1.5B","SigLIP-400M","2024/10/24",68.8,"N/A"],[139,"Slime-13B",13.0,"Vicuna-v1.5-13B","CLIP ViT-L/14","2024/09/14",68.8,"N/A"],[140,"InternVL2-4B",4.0,"Phi-3","InternViT-300M","2024/07/11",68.6,"N/A"],[141,"Mini-InternVL-Chat-4B-V1.5",4.0,"Phi-3","InternViT-300M","2024/06/10",68.6,"N/A"],[142,"SmolVLM2",2.25,"SmolLM2-1.7M","SigLIP-400M","2025/03/13",68.1,"N/A"],[143,"LLaVA-Next-Mistral-7B",7.6,"Mistral-7B","CLIP ViT-L/14","2024/03/25",67.8,"N/A"],[144,"Qwen-VL-Chat",9.6,"Qwen-7B","ViT-G/16","2023/08/24",67.7,"N/A"],[145,"Claude3-Haiku",null,"","","2024/03/28",67.4,"N/A"],[146,"ShareGPT4V-7B",7.2,"Vicuna-v1.5-7B","CLIP ViT-L/14","2023/12/08",66.9,72.6],[147,"granite-vision-3.3-2b",2.98,"granite-3.1-2b-instruct","SigLIP2-400M","2025/06/20",66.9,"N/A"],[148,"TransCore-M",13.4,"PCITransGPT-13B","CLIP ViT-L/14","2024/04/16",66.8,"N/A"],[149,"InternVL2.5-2B-MPO",2.0,"InternLM2.5-1.8B","InternViT-300M-v2.5","2024/12/28",66.7,"N/A"],[150,"MolmoE-1B",7.2,"OLMoE-1B-7B-0924","CLIP ViT-L/14","2024/10/21",66.7,"N/A"],[151,"XGen-MM-Instruct-Interleave-v1.5",4.4,"Phi-3","SigLIP-400M","2024/09/06",66.7,"N/A"],[152,"Phi-4-MultiModal",5.57,"Phi-4-Mini","SigLIP-400M","2025/03/13",66.5,"N/A"],[153,"Idefics3-8B-Llama3",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/08/27",66.3,"N/A"],[154,"OmChat-v2.0-13B",13.0,"Qwen2-7B","InternViT-6B","2024/08/22",66.1,"N/A"],[155,"LLaVA-v1.5-13B",13.4,"Vicuna-v1.5-13B","CLIP ViT-L/14","2023/10/05",66.1,70.7],[156,"AKI-4B",4.33,"Phi-3.5","SigLIP-400M","2025/03/25",66.1,"N/A"],[157,"LLaVA-Next-Llama3",8.0,"Llama-3-8B-Instruct","CLIP ViT-L/14","2024/07/29",66.0,"N/A"],[158,"granite-vision-3.2-2b",2.98,"granite-3.1-2b-instruct","SigLip","2025/06/20",65.7,"N/A"],[159,"H2OVL-2B",2.2,"H2O-DANUBE2-1.8B","InternViT-300M","2024/10/31",65.7,"N/A"],[160,"VILA1.5-3B",3.0,"Sheared-LLaMA-2.7B","SigLIP-400M","2024/08/25",65.5,"N/A"],[161,"Falcon2-VLM-11B",11.4,"Falcon2-11B","CLIP ViT-L/14","2024/10/30",65.5,"N/A"],[162,"Phi-3-Vision",4.2,"Phi-3","CLIP ViT-L/14","2024/05/31",63.9,"N/A"],[163,"SAIL-VL-2B",2.1,"Qwen2.5-1.5B","InternViT-300M","2024/12/25",63.8,"N/A"],[164,"LLaVA-InternLM2-20B (QLoRA)",20.2,"InternLM2-20B","CLIP ViT-L/14","2024/01/17",63.7,"N/A"],[165,"Phi-3.5-Vision",4.0,"Phi-3.5","CLIP ViT-L/14","2024/08/28",63.7,"N/A"],[166,"Bunny-Llama3-8B",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/07/18",63.6,"N/A"],[167,"LLaVA-v1.5-13B (QLoRA)",13.4,"Vicuna-v1.5-13B","CLIP ViT-L/14","2023/12/28",63.6,"N/A"],[168,"XVERSE-V-13B",13.0,"XVERSE-13B","CLIP ViT-L/14","2024/05/10",62.9,"N/A"],[169,"Llama-3-MixSense-v1.1",8.0,"Llama-3-8B-Instruct","Florence-2-Large-FT","2024/08/21",62.9,"N/A"],[170,"Slime-8B",8.0,"Llama-3-8B-Instruct","CLIP ViT-L/14","2024/09/14",62.4,"N/A"],[171,"Yi-VL-34B",34.6,"Yi-34B","CLIP ViT-H/14","2024/01/25",62.3,"N/A"],[172,"Vintern-3B-beta",3.7,"Qwen-2.5-3B","InternViT-300M","2024/10/24",62.2,"N/A"],[173,"InternVL3-1B",0.94,"Qwen2.5-0.5B","InternViT-300M-v2.5","2025/04/14",62.1,"N/A"],[174,"MiniMonkey",2.2,"InternLM2-1.8B","InternViT-300M","2024/09/26",62.0,"N/A"],[175,"LLaVA-v1.5-7B",7.2,"Vicuna-v1.5-7B","CLIP ViT-L/14","2023/10/05",61.8,63.4],[176,"InternLM-XComposer2-4KHD",7.0,"InternLM2-7B","CLIP ViT-L/14","2024/06/09",61.8,"N/A"],[177,"LLaVA-OneVision-0.5B (SI)",1.0,"Qwen2-0.5B","SigLIP-400M","2024/09/17",61.7,"N/A"],[178,"Moondream2",1.9,"SigLIP-400M","Phi-1.5","2024/10/20",61.4,"N/A"],[179,"Mantis-8B-clip-llama3",8.0,"Llama-3-8B-Instruct","CLIP ViT-L/14","2024/08/08",61.1,"N/A"],[180,"Mantis-8B-Idefics2",8.0,"Mistral-7B","SigLIP-400M","2024/08/08",60.6,"N/A"],[181,"Monkey-Chat",9.8,"Qwen-7B","ViT-BigHuge","2024/01/16",60.5,"N/A"],[182,"Ross-Qwen2-7B",8.2,"Qwen2-7B","CLIP ViT-L/14","2025/01/17",60.2,"N/A"],[183,"InternVL2.5-1B-MPO",1.0,"Qwen-2.5-0.5B","InternViT-300M-v2.5","2024/12/28",60.2,"N/A"],[184,"InternVL2-2B",2.0,"InternLM2-1.8B","InternViT-300M","2024/07/11",60.0,"N/A"],[185,"mPLUG-Owl2",8.2,"Llama-2-7B","CLIP ViT-L/14","2023/11/10",59.9,"N/A"],[186,"LLaVA-OneVision-0.5B",1.0,"Qwen2-0.5B","SigLIP-400M","2024/09/16",59.9,"N/A"],[187,"InstructBLIP-7B",8.0,"Vicuna-7B","EVA-G","2023/05/11",59.8,60.9],[188,"LLaVA-InternLM-7B (QLoRA)",7.6,"InternLM-7B","CLIP ViT-L/14","2023/12/28",59.7,"N/A"],[189,"Eagle-X5-7B",9.0,"Vicuna-v1.5-7B","Clip-448
ConvNeXT-1024
SAM-1024
DET-1024
Pix2Struct-1024","2024/09/26",59.5,"N/A"],[190,"Slime-7B",7.0,"Vicuna-v1.5-7B","CLIP ViT-L/14","2024/09/14",59.4,"N/A"],[191,"Janus-1.3B",2.1,"DeepSeek-1B","SigLIP-400M","2024/10/24",58.8,"N/A"],[192,"Mini-InternVL-Chat-2B-V1.5",2.0,"InternLM2-1.8B","InternViT-300M","2024/06/10",57.3,"N/A"],[193,"LLaVA-v1.5-7B (QLoRA)",7.2,"Vicuna-v1.5-7B","CLIP ViT-L/14","2023/12/28",57.2,"N/A"],[194,"LLaVA-v1-7B",7.2,"Llama-7B","CLIP ViT-L/14","2023/04/17",57.2,"N/A"],[195,"IDEFICS-80B-Instruct",80.0,"Llama-65B","CLIP ViT-H/14","2023/07/25",56.9,"N/A"],[196,"Emu2_chat",37.0,"Llama-33B","EVA-02-CLIP-E-plus","2024/01/17",56.4,"N/A"],[197,"LLaVA-InternLM2-7B (QLoRA)",8.1,"InternLM2-7B","CLIP ViT-L/14","2024/01/17",56.2,"N/A"],[198,"InternLM-XComposer2-1.8B",2.0,"InternLM2-1.8B","CLIP ViT-L/14","2024/06/09",55.7,"N/A"],[199,"Mantis-8B-siglip-llama3",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/08/08",55.5,"N/A"],[200,"Parrot-7B",8.0,"Qwen2-7B","CLIP ViT-L/14","2024/08/22",55.3,"N/A"],[201,"Kosmos2",1.7,"","","2024/10/19",54.7,"N/A"],[202,"SmolVLM-Instruct",2.3,"SmolLM2-1.7B","SigLIP-400M","2025/01/27",53.9,"N/A"],[203,"InternLM-XComposer",8.0,"InternLM-7B","EVA-G","2023/09/26",53.8,"N/A"],[204,"Moondream1",1.9,"SigLIP-400M","Phi-1.5","2024/09/26",53.6,"N/A"],[205,"SmolVLM-Synthetic",2.3,"SmolLM2-1.7B","SigLIP-400M","2025/01/27",52.8,"N/A"],[206,"SmolVLM-Instruct-DPO",2.3,"SmolLM2-1.7B","SigLIP-400M","2025/01/27",52.7,"N/A"],[207,"InternVL2-1B",1.0,"Qwen2-0.5B","InternViT-300M","2024/07/11",52.3,"N/A"],[208,"Yi-VL-6B",6.6,"Yi-6B","CLIP ViT-H/14","2024/01/25",51.9,"N/A"],[209,"MiniCPM-V",3.0,"MiniCPM-2.4B","SigLIP-400M","2024/02/07",51.3,"N/A"],[210,"DeepSeek-VL-1.3B",2.0,"DeekSeek-1B","SAM-B
SigLIP-L","2024/03/21",51.1,"N/A"],[211,"Qwen2-VL-2B",2.0,"Qwen2-1.5B","QwenViT","2024/09/12",50.5,"N/A"],[212,"MMAlaya",7.8,"Alaya-7B-Chat","EVA-G","2024/01/29",50.2,"N/A"],[213,"SmolVLM2-500M",0.51,"SmolLM2-360M","ViT-93M","2025/03/13",50.0,"N/A"],[214,"Emu3_chat",8.49,"","","2025/01/26",49.2,"N/A"],[215,"IDEFICS2-8B",8.0,"Mistral-7B","SigLIP-400M","2024/04/26",49.1,"N/A"],[216,"ShareCaptioner",8.0,"InternLM-7B","EVA-G","2024/01/03",47.4,"N/A"],[217,"Mantis-8B-Fuyu",8.0,"Fuyu-8B","","2024/09/07",46.8,"N/A"],[218,"MiniGPT-4-v1-7B",8.0,"Vicuna-7B","EVA-G","2023/04/20",45.1,"N/A"],[219,"IDEFICS-9B-Instruct",9.0,"Llama-7B","CLIP ViT-H/14","2023/07/25",45.0,"N/A"],[220,"H2OVL-800M",0.83,"H2O-DANUBE3-500M","InternViT-300M","2024/10/31",44.8,"N/A"],[221,"Monkey",9.8,"Qwen-7B","ViT-BigHuge","2024/01/11",43.3,"N/A"],[222,"SmolVLM2-256M",0.26,"SmolLM2-135M","ViT-93M","2025/03/13",43.2,"N/A"],[223,"SmolVLM-500M",0.51,"SmolLM2-360M","ViT-93M","2025/01/27",43.1,"N/A"],[224,"XinYuan-VL-2B-Instruct",2.0,"Qwen2-1.5B","QwenViT","2024/09/27",42.1,"N/A"],[225,"SmolVLM-256M",0.26,"SmolLM2-135M","ViT-93M","2025/01/27",39.7,"N/A"],[226,"VisualGLM",8.0,"ChatGLM 6B","EVA-CLIP","2023/05/17",37.3,"N/A"],[227,"PandaGPT-13B",14.0,"Vicuna-13B","ImageBind ViT-H/14","2023/05/25",37.1,"N/A"],[228,"PaliGemma-3B-mix-448",3.0,"Gemma-2B","SigLIP-400M","2024/05/17",36.9,"N/A"],[229,"OpenFlamingo v2",9.0,"MPT 7B","CLIP ViT-L/14","2023/06/28",34.2,"N/A"],[230,"Molmo-7B-D",8.0,"Qwen2-7B","CLIP ViT-L/14","2024/10/12",33.6,"N/A"],[231,"Chameleon-30B",30.0,"","","2024/07/29",33.3,"N/A"],[232,"MiniGPT-4-v2",8.0,"Llama-2-13B","EVA-G","2023/10/27",28.8,"N/A"],[233,"Chameleon-7B",7.0,"","","2024/07/29",26.6,"N/A"],[234,"Qwen-VL",9.6,"Qwen-7B","ViT-G/16","2023/08/24",12.9,"N/A"]],"metadata":null},"headers":["1","2","3"],"row_count":[1,"dynamic"],"col_count":[3,"dynamic"],"datatype":["number","html","number","html","html","str","number","number"],"type":"pandas","latex_delimiters":[{"left":"$$","right":"$$","display":true}],"show_label":true,"height":500,"min_width":160,"interactive":false,"visible":true,"elem_classes":[],"wrap":true,"line_breaks":true,"column_widths":[],"name":"dataframe","_selectable":false},"skip_api":false,"component_class_id":"6a51bb3357f2e94c40fb8d4fbe06aa8e","key":null,"api_info":{"properties":{"headers":{"items":{"type":"string"},"title":"Headers","type":"array"},"data":{"items":{"items":{},"type":"array"},"title":"Data","type":"array"},"metadata":{"anyOf":[{"additionalProperties":{"anyOf":[{"items":{},"type":"array"},{"type":"null"}]},"type":"object"},{"type":"null"}],"default":null,"title":"Metadata"}},"required":["headers","data"],"title":"DataframeData","type":"object"},"example_inputs":{"headers":["a","b"],"data":[["foo","bar"]]}},{"id":153,"type":"textbox","props":{"value":"LLaVABench","lines":1,"max_lines":20,"label":"LLaVABench","show_label":true,"container":true,"min_width":160,"visible":false,"autofocus":false,"autoscroll":true,"elem_classes":[],"type":"text","rtl":false,"show_copy_button":false,"name":"textbox","_selectable":false},"skip_api":false,"component_class_id":"d0491bb0fbd427bdb2a4549c4d1ac869","key":null,"api_info":{"type":"string"},"example_inputs":"Hello!!"},{"id":154,"type":"form","props":{"scale":0,"min_width":0,"name":"form"},"skip_api":true,"component_class_id":"43cda85c6ff7a5dd8f83d29496b014ee","key":null},{"id":155,"type":"form","props":{"scale":0,"min_width":0,"name":"form"},"skip_api":true,"component_class_id":"43cda85c6ff7a5dd8f83d29496b014ee","key":null},{"id":156,"type":"tabitem","props":{"label":"📊 AI2D Leaderboard","visible":true,"interactive":true,"id":14,"elem_id":"AI2D","name":"tab"},"skip_api":true,"component_class_id":"18f46968e2b273dc5dbda0fe78433d7e","key":null},{"id":157,"type":"checkboxgroup","props":{"choices":[["Overall","Overall"],["atomStructure","atomStructure"],["eclipses","eclipses"],["faultsEarthquakes","faultsEarthquakes"],["foodChainsWebs","foodChainsWebs"],["lifeCycles","lifeCycles"],["moonPhaseEquinox","moonPhaseEquinox"],["partsOfA","partsOfA"],["partsOfTheEarth","partsOfTheEarth"],["photosynthesisRespiration","photosynthesisRespiration"],["rockCycle","rockCycle"],["rockStrata","rockStrata"],["solarSystem","solarSystem"],["typesOf","typesOf"],["volcano","volcano"],["waterCNPCycle","waterCNPCycle"]],"value":["Overall"],"type":"value","label":"AI2D CheckBoxes","show_label":true,"container":true,"min_width":160,"interactive":true,"visible":true,"elem_classes":[],"name":"checkboxgroup","_selectable":false},"skip_api":false,"component_class_id":"0635a5d3bf87369f1c2c1c69f8a3d0cc","key":null,"api_info":{"items":{"enum":["Overall","atomStructure","eclipses","faultsEarthquakes","foodChainsWebs","lifeCycles","moonPhaseEquinox","partsOfA","partsOfTheEarth","photosynthesisRespiration","rockCycle","rockStrata","solarSystem","typesOf","volcano","waterCNPCycle"],"type":"string"},"title":"Checkbox Group","type":"array"},"example_inputs":["Overall"]},{"id":158,"type":"row","props":{"variant":"default","visible":true,"equal_height":true,"show_progress":false,"name":"row"},"skip_api":true,"component_class_id":"b5cf3d15e2293fb5ccc071d7b8d69f64","key":null},{"id":159,"type":"textbox","props":{"value":"Input the Model Name (fuzzy, case insensitive)","lines":1,"max_lines":20,"label":"Model Name","show_label":true,"container":true,"min_width":160,"interactive":true,"visible":true,"autofocus":false,"autoscroll":true,"elem_classes":[],"type":"text","rtl":false,"show_copy_button":false,"name":"textbox","_selectable":false},"skip_api":false,"component_class_id":"d0491bb0fbd427bdb2a4549c4d1ac869","key":null,"api_info":{"type":"string"},"example_inputs":"Hello!!"},{"id":160,"type":"checkboxgroup","props":{"choices":[["<4B","<4B"],["4B-10B","4B-10B"],["10B-20B","10B-20B"],["20B-40B","20B-40B"],[">40B",">40B"],["Unknown","Unknown"]],"value":["<4B","4B-10B","10B-20B","20B-40B",">40B","Unknown"],"type":"value","label":"Model Size","show_label":true,"container":true,"min_width":160,"interactive":true,"visible":true,"elem_classes":[],"name":"checkboxgroup","_selectable":false},"skip_api":false,"component_class_id":"0635a5d3bf87369f1c2c1c69f8a3d0cc","key":null,"api_info":{"items":{"enum":["<4B","4B-10B","10B-20B","20B-40B",">40B","Unknown"],"type":"string"},"title":"Checkbox Group","type":"array"},"example_inputs":["<4B"]},{"id":161,"type":"checkboxgroup","props":{"choices":[["API","API"],["OpenSource","OpenSource"]],"value":["API","OpenSource"],"type":"value","label":"Model Type","show_label":true,"container":true,"min_width":160,"interactive":true,"visible":true,"elem_classes":[],"name":"checkboxgroup","_selectable":false},"skip_api":false,"component_class_id":"0635a5d3bf87369f1c2c1c69f8a3d0cc","key":null,"api_info":{"items":{"enum":["API","OpenSource"],"type":"string"},"title":"Checkbox Group","type":"array"},"example_inputs":["API"]},{"id":162,"type":"form","props":{"scale":3,"min_width":480,"name":"form"},"skip_api":true,"component_class_id":"43cda85c6ff7a5dd8f83d29496b014ee","key":null},{"id":163,"type":"dataframe","props":{"value":{"headers":["Rank","Method","Param (B)","Language Model","Vision Model","Eval Date","Overall"],"data":[[1,"HunYuan-Standard-Vision",null,"","","2025/01/15",93.2],[2,"Taiyi",null,"","","2024/12/11",90.8],[3,"SenseNova-V6-5-Pro",null,"","","2025/09/03",90.2],[4,"CongRong-v2.0",null,"","","2025/05/20",90.0],[5,"InternVL3-78B",78.4,"Qwen2.5-72B","InternViT-6B-v2.5","2025/04/14",89.8],[6,"GPT-5-20250807",null,"","","2025/08/14",89.5],[7,"Gemini-2.5-Pro",null,"","","2025/04/07",89.5],[8,"SenseNova-V6-Pro",null,"","","2025/05/05",89.2],[9,"InternVL2.5-78B-MPO",78.0,"Qwen-2.5-72B","InternViT-6B-v2.5","2024/12/29",89.2],[10,"Step-1o",null,"","","2025/01/13",89.1],[11,"InternVL2.5-78B",78.0,"Qwen-2.5-72B","InternViT-6B-v2.5","2024/12/10",89.1],[12,"MUG-U-7B",7.0,"","","2025/03/19",88.9],[13,"InternVL3-38B",38.4,"Qwen2.5-32B","InternViT-6B-v2.5","2025/04/14",88.7],[14,"Qwen2.5-VL-72B",73.4,"Qwen2.5-72B","QwenViT","2025/02/02",88.5],[15,"TeleMM",null,"","","2024/12/31",88.5],[16,"Qwen2-VL-72B",73.4,"Qwen2-72B","QwenViT","2024/10/28",88.3],[17,"JT-VL-Chat-V3.0",null,"","","2025/08/04",88.3],[18,"Ovis2-34B",34.9,"Qwen2.5-32B","AIMv2-1B","2025/02/18",88.3],[19,"Qwen-VL-Max-0809",72.0,"Qwen2-72B","QwenViT","2024/09/12",88.1],[20,"InternVL2.5-38B-MPO",38.0,"Qwen-2.5-32B","InternViT-6B-v2.5","2024/12/28",87.9],[21,"SenseNova",null,"","","2024/12/12",87.8],[22,"InternVL2-Llama3-76B",76.0,"Llama-3-70B-Instruct","InternViT-6B","2024/07/19",87.6],[23,"InternVL2.5-38B",38.0,"Qwen-2.5-32B","InternViT-6B-v2.5","2024/12/10",87.6],[24,"SAIL-VL-1.6-8B",8.33,"Qwen2.5-7B","AIMv2 Huge","2025/04/24",87.5],[25,"SAIL-VL-1.5-8B",7.95,"Qwen2.5-7B","InternViT-300B","2025/04/23",87.5],[26,"Step-1.5V",null,"Step-1.5","stepencoder","2024/10/11",87.5],[27,"GPT-4.5",null,"","","2025/03/26",87.2],[28,"BailingMM-Pro-0120",81.0,"Bailing-80B","SigLIP-400M","2025/01/25",87.2],[29,"InternVL2-40B",40.0,"Nous-Hermes-2-Yi-34B","InternViT-6B","2024/07/11",86.8],[30,"GLM-4v-Plus-20250111",null,"","","2025/01/25",86.7],[31,"GPT-5-mini-20250807",null,"","","2025/08/14",86.7],[32,"Ovis1.6-Gemma2-27B",28.9,"Gemma2-27B","SigLIP-400M","2024/11/29",86.6],[33,"Ovis2-8B",8.94,"Qwen2.5-7B","AIMv2 Huge","2025/02/18",86.6],[34,"Ovis2-16B",16.2,"Qwen2.5-14B","AIMv2 Huge","2025/02/18",86.3],[35,"ChatGPT-4o-latest",null,"","","2025/04/07",86.3],[36,"LLaVA-OneVision-72B",73.0,"Qwen2-72B","SigLIP-400M","2024/09/19",86.2],[37,"InternVL2.5-26B-MPO",26.0,"InternLM2.5-20B","InternViT-6B-v2.5","2024/12/28",86.2],[38,"R-4B",4.82,"Qwen3-4B","SigLip-400M","2025/08/11",86.2],[39,"InternVL2.5-26B",26.0,"InternLM2.5-20B","InternViT-6B-v2.5","2024/12/10",86.2],[40,"BlueLM-2.6-3B",3.0,"","","2025/09/17",86.1],[41,"MiniCPM-o-2.6",8.67,"Qwen2.5-7B","SigLIP-400M","2025/01/21",86.1],[42,"Ola-7b",8.88,"Qwen2.5-7B","Oryx-ViT","2025/02/05",86.1],[43,"InternVL3-14B",15.1,"Qwen2.5-14B","InternViT-300M-v2.5","2025/04/14",86.0],[44,"BailingMM-Lite-1203",21.0,"Bailing-20B","SigLIP-400M","2024/12/08",86.0],[45,"GPT-4.1-20250414",null,"","","2025/04/16",85.9],[46,"VARCO-VISION-2.0-14B",15.2,"Qwen3-14B","SigLIP-400M","2025/08/04",85.7],[47,"Ovis2-4B",4.62,"Qwen2.5-3B","AIMv2 Huge","2025/02/18",85.7],[48,"Ovis-U1-3B",3.64,"Qwen3-1.7B","aimv2-large-path14-448","2025/07/20",85.6],[49,"LLaVA-OneVision-72B (SI)",73.0,"Qwen2-72B","SigLIP-400M","2024/09/19",85.5],[50,"Qwen2.5-VL-32B",33.5,"Qwen2.5-32B","QwenViT","2025/07/02",85.4],[51,"BlueLM-V-3B",3.0,"BlueLM-3B","SigLIP-400M","2024/10/30",85.3],[52,"InternVL3-9B",9.14,"InternLM3-8B","InternViT-300M-v2.5","2025/04/14",85.2],[53,"GLM-4v-Plus",null,"","","2024/12/11",85.1],[54,"InternVL3-8B",7.94,"Qwen2.5-7B","InternViT-300M-v2.5","2025/04/14",85.1],[55,"RBDash-v1.5",79.0,"Qwen2-72B","CLIP ViT-L/14
InternViT-6B","2024/11/17",85.0],[56,"GPT-4o (1120, detail-high)",null,"","","2024/12/02",84.9],[57,"Gemini-2.0-Pro",null,"","","2025/02/27",84.8],[58,"GPT-4o (0806, detail-high)",null,"","","2024/08/08",84.7],[59,"InternVL2.5-8B",8.0,"InternLM2.5-7B","InternViT-300M-v2.5","2024/12/10",84.6],[60,"GPT-4o (0513, detail-high)",null,"","","2024/05/31",84.6],[61,"Kimi-VL-A3B-Instruct",16.4,"Moonlight-16B-A3B","MoonViT","2025/04/14",84.5],[62,"InternVL2.5-8B-MPO",8.0,"InternLM2.5-7B","InternViT-300M-v2.5","2024/12/28",84.5],[63,"InternVL2-26B",26.0,"InternLM2-20B","InternViT-6B","2024/07/11",84.5],[64,"Ovis1.5-Gemma2-9B",11.4,"Gemma2-9B-It","SigLIP-400M","2024/08/04",84.5],[65,"Gemini-1.5-Flash-002",null,"","","2024/12/02",84.4],[66,"Ovis1.6-Gemma2-9B",10.2,"Gemma2-9B-It","SigLIP-400M","2024/09/19",84.4],[67,"Qwen2.5-VL-7B",8.29,"Qwen2.5-7B","QwenViT","2025/02/02",84.3],[68,"Ristretto-3B",3.84,"Qwen2.5-3B","SigLIP-400M","2025/04/01",84.2],[69,"WeThink-Qwen2.5VL-7B",8.29,"Qwen2.5-7B","QwenViT","2025/05/26",84.0],[70,"VARCO-VISION-14B",15.2,"Qwen2.5-14B","SigLIP-400M","2025/01/02",83.9],[71,"DeepSeek-VL2",27.5,"DeepSeekMoE-27B","SigLIP-400M","2025/01/01",83.8],[72,"SAIL-VL-1.5-2B",2.47,"Qwen2.5-1.5B","AIMv2 Huge","2025/04/23",83.7],[73,"InternVL2-8B",8.0,"InternLM2.5-7B","InternViT-300M","2024/07/11",83.6],[74,"bailingMM-mini",17.0,"bailing-mini","bailingMM-encoder-1B
InternViT-6B","2024/10/24",83.5],[75,"Molmo-72B",73.3,"Qwen2-72B","CLIP ViT-L/14","2024/10/28",83.4],[76,"InternVL2-8B-MPO-CoT",8.0,"InternLM2.5-7B","InternViT-300M","2024/11/25",83.4],[77,"InternVL2-8B-MPO",8.0,"InternLM2.5-7B","InternViT-300M","2024/11/25",83.4],[78,"Gemini-1.5-Pro-002",null,"","","2024/12/02",83.3],[79,"Kimi-VL-A3B-Thinking-2506",16.4,"Moonlight-16B-A3B","MoonViT","2025/07/02",83.1],[80,"Gemini-2.0-Flash",null,"","","2025/01/02",83.1],[81,"BlueLM-2.5-3B",2.9,"BlueLM-base-3B","Siglip2-So400M","2025/07/16",83.1],[82,"Phi-4-MultiModal",5.57,"Phi-4-Mini","SigLIP-400M","2025/03/13",83.0],[83,"valley2_dpo",8.88,"Qwen2.5-7B","SigLIP-400M","2025/05/30",83.0],[84,"Qwen2-VL-7B",8.0,"Qwen2-7B","QwenViT","2024/09/12",83.0],[85,"Qwen-VL-Plus-0809",null,"","","2024/09/17",82.9],[86,"LLaVA-OneVision-7B (SI)",8.0,"Qwen2-7B","SigLIP-400M","2024/09/17",82.8],[87,"valley2",8.88,"Qwen2.5-7B","SigLIP-400M","2025/05/30",82.8],[88,"MiMo-VL-7B",8.31,"Mimo-7B","Qwen2.5-ViT","2025/07/02",82.8],[89,"Ovis2-2B",2.46,"Qwen2.5-1.5B","AIMv2 Large","2025/02/18",82.7],[90,"Aria",25.3,"Aria-MoE","SigLIP-400M","2024/12/05",82.7],[91,"Valley-Eagle",8.9,"Qwen2.5-7B","Qwen-ViT
SigLIP-400M","2024/12/29",82.5],[92,"Claude3.7-Sonnet",null,"","","2025/02/27",82.5],[93,"Ovis1.5-Llama3-8B",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/07/29",82.5],[94,"LLaVA-OneVision-7B",8.0,"Qwen2-7B","SigLIP-400M","2024/09/16",82.4],[95,"CongRong",null,"","","2024/06/26",82.4],[96,"abab7-preview",null,"","","2024/12/11",82.3],[97,"MiniCPM-V-2.6",8.0,"Qwen2-7B","SigLIP-400M","2024/08/08",82.1],[98,"moonshot-v1-8k",null,"","","2025/03/03",81.8],[99,"DeepSeek-VL2-Small",16.1,"DeepSeekMoE-16B","SigLIP-400M","2025/01/01",81.7],[100,"InternLM-XComposer2.5",8.0,"InternLM2-7B","CLIP ViT-L/14","2024/07/11",81.6],[101,"InternVL2.5-4B-MPO",4.0,"Qwen-2.5-3B","InternViT-300M-v2.5","2024/12/28",81.5],[102,"InternVL2.5-4B",4.0,"Qwen-2.5-3B","InternViT-300M-v2.5","2024/12/10",81.4],[103,"GPT-5-nano-20250807",null,"","","2025/08/14",81.4],[104,"Gemma3-27B",27.4,"Gemma3-27B","SigLIP-400M","2025/03/19",81.4],[105,"Qwen2.5-VL-3B",3.75,"Qwen2.5-3B","QwenViT","2025/02/02",81.4],[106,"POINTS1.5-Qwen2.5-7B",8.3,"Qwen-2.5-7B","NaViT","2024/12/06",81.4],[107,"Step-1.5V-mini",null,"","","2024/12/11",81.3],[108,"QTuneVL1.5-3B",3.75,"Qwen2.5-3B","QwenViT","2025/08/11",81.2],[109,"POINTS-Qwen2.5-7B",8.3,"Qwen-2.5-7B","CLIP ViT-L/14","2024/10/19",81.2],[110,"Claude3.5-Sonnet-20241022",null,"","","2024/11/06",81.2],[111,"grok-2-vision-1212",null,"","","2025/03/03",81.2],[112,"InternLM-XComposer2",7.0,"InternLM2-7B","CLIP ViT-L/14","2024/01/26",81.2],[113,"InternLM-XComposer2-4KHD",7.0,"InternLM2-7B","CLIP ViT-L/14","2024/06/09",81.0],[114,"Molmo-7B-D",8.0,"Qwen2-7B","CLIP ViT-L/14","2024/10/12",81.0],[115,"Long-VITA-16K",14.0,"Qwen2.5-14B","InternViT-300M","2025/06/13",80.9],[116,"Eagle-X5-34B-Chat",36.8,"Yi-34B","Clip-448
ConvNeXT-1024
SAM-1024
DET-1024
Pix2Struct-1024","2024/11/29",80.8],[117,"MMAlaya2",26.0,"InternLM2-20B","InternViT-6B","2024/08/27",80.8],[118,"InternVL-Chat-V1.5",26.0,"InternLM2-20B","InternViT-6B","2024/04/17",80.6],[119,"Claude3.5-Sonnet",null,"","","2024/06/24",80.2],[120,"NVLM-D-72B",79.4,"Qwen2-72B","InternViT-6B","2024/10/19",80.1],[121,"Cambrian-34B",34.0,"Nous-Hermes-2-Yi-34B","CLIP ViT-L/14","2024/07/18",79.5],[122,"Ross-Qwen2-7B",8.2,"Qwen2-7B","CLIP ViT-L/14","2025/01/17",79.4],[123,"VITA-1.5",8.3,"Qwen2-7B","InternViT-300M","2025/01/01",79.2],[124,"Gemini-1.5-Pro",null,"","","2024/06/10",79.1],[125,"InternVL2-4B",4.0,"Phi-3","InternViT-300M","2024/07/11",79.0],[126,"Pixtral-12B",13.0,"Nemo-12B","ViT-400M","2024/09/16",79.0],[127,"LLaVA-Next-Yi-34B",34.8,"Yi-34B","CLIP ViT-L/14","2024/03/25",78.9],[128,"POINTS-Yi-1.5-9B",9.5,"Yi-1.5-9B","CLIP ViT-L/14","2024/10/11",78.8],[129,"LLaVA-CoT",11.0,"","","2025/01/05",78.7],[130,"InternVL3-2B",2.09,"Qwen2.5-1.5B","InternViT-300M-v2.5","2025/04/14",78.6],[131,"GPT-4v (0409, detail-high)",null,"","","2024/05/15",78.6],[132,"QTuneVL1.5-2B",2.09,"Qwen2.5-1.5B","InternViT-300M-v2.5","2025/08/11",78.6],[133,"granite-vision-3.2-2b",2.98,"granite-3.1-2b-instruct","SigLip","2025/06/20",78.6],[134,"Gemini-1.5-Flash",null,"","","2024/09/16",78.5],[135,"MiniCPM-Llama3-V2.5",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/05/27",78.4],[136,"Phi-3-Vision",4.2,"Phi-3","CLIP ViT-L/14","2024/05/31",78.4],[137,"Yi-Vision",null,"","","2024/08/03",78.2],[138,"Gemma3-12B",12.2,"Gemma3-12B","SigLIP-400M","2025/03/19",78.1],[139,"Falcon2-VLM-11B",11.4,"Falcon2-11B","CLIP ViT-L/14","2024/10/30",77.9],[140,"WeMM",7.0,"InternLM2-7B","SigLIP-400M","2024/06/09",77.9],[141,"GPT-4o-mini (0718, detail-high)",null,"","","2024/07/20",77.8],[142,"VILA1.5-40B",40.0,"Yi-34B","InternViT-6B","2024/08/25",77.8],[143,"OmChat-v2.0-13B",13.0,"Qwen2-7B","InternViT-6B","2024/08/22",77.8],[144,"Phi-3.5-Vision",4.0,"Phi-3.5","CLIP ViT-L/14","2024/08/28",77.8],[145,"Ovis1.6-Llama3.2-3B",4.1,"Llama-3.2-3B","SigLIP-400M","2024/10/24",77.8],[146,"granite-vision-3.1-2b-preview",2.98,"granite-3.1-2b-instruct","SigLip","2025/06/20",77.7],[147,"Kimi-VL-A3B-Thinking",16.4,"Moonlight-16B-A3B","MoonViT","2025/04/23",77.5],[148,"SAIL-VL-2B",2.1,"Qwen2.5-1.5B","InternViT-300M","2024/12/25",77.4],[149,"GPT-4o (0513, detail-low)",null,"","","2024/05/15",77.4],[150,"Llama-3.2-11B-Vision-Instruct",11.0,"Llama-3.1-8B","","2024/10/07",77.3],[151,"Eagle-X5-13B",15.0,"Vicuna-v1.5-13B","Clip-448
ConvNeXT-1024
SAM-1024
DET-1024
Pix2Struct-1024","2024/09/26",77.2],[152,"Mini-InternVL-Chat-4B-V1.5",4.0,"Phi-3","InternViT-300M","2024/06/10",77.0],[153,"granite-vision-3.3-2b",2.98,"granite-3.1-2b-instruct","SigLIP2-400M","2025/06/20",76.6],[154,"Idefics3-8B-Llama3",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/08/27",76.5],[155,"Ovis2-1B",1.27,"Qwen2.5-0.5B","AIMv2 Large","2025/02/18",76.4],[156,"GPT-4v (0409, detail-low)",null,"","","2024/05/15",76.1],[157,"GLM-4v",null,"","","2024/05/20",76.1],[158,"GPT-4.1-mini-20250414",null,"","","2025/04/16",76.0],[159,"GPT-4v (1106, detail-low)",null,"","","2023/12/23",75.9],[160,"Qwen-VL-Max",null,"QwenLM","","2024/02/02",75.7],[161,"Molmo-7B-O",8.0,"Qwen2-7B","CLIP ViT-L/14","2024/10/20",75.7],[162,"RekaFlash",null,"","","2024/05/07",75.6],[163,"LLaVA-Next-Qwen-32B",33.0,"Qwen-1.5-32B","SigLIP-400M","2024/08/08",75.5],[164,"VARCO-VISION-2.0-1.7B",2.12,"Qwen3-1.7B","SigLIP-400M","2025/08/04",75.2],[165,"QTuneVL1-2B",2.21,"InternLM2.5-1.8B","InternViT-300M-v2.5","2025/05/05",75.2],[166,"Aquila-VL-2B",2.2,"Qwen-2.5-1.5B","SigLIP-400M","2024/10/24",75.1],[167,"InternVL2.5-2B-MPO",2.0,"InternLM2.5-1.8B","InternViT-300M-v2.5","2024/12/28",75.1],[168,"InternVL2.5-2B",2.0,"InternLM2.5-1.8B","InternViT-300M-v2.5","2024/12/10",74.9],[169,"MiniMonkey",2.2,"InternLM2-1.8B","InternViT-300M","2024/09/26",74.8],[170,"Qwen2-VL-2B",2.0,"Qwen2-1.5B","QwenViT","2024/09/12",74.7],[171,"DeepSeek-VL2-Tiny",3.4,"DeepSeekMoE-3B","SigLIP-400M","2025/01/01",74.6],[172,"Cambrian-8B",8.0,"Vicuna-v1.5-7B","CLIP ViT-L/14","2024/07/11",74.6],[173,"Flash-VL-2B-Dynamic-ISS",2.53,"Qwen-2.5-1.5B-Instruct","SigLIP2-400M-512","2025/05/30",74.4],[174,"XGen-MM-Instruct-Interleave-v1.5",4.4,"Phi-3","SigLIP-400M","2024/09/06",74.2],[175,"XinYuan-VL-2B-Instruct",2.0,"Qwen2-1.5B","QwenViT","2024/09/27",74.2],[176,"InternVL2-2B",2.0,"InternLM2-1.8B","InternViT-300M","2024/07/11",74.1],[177,"LLaVA-Next-Interleave-7B",8.0,"Qwen-1.5-7B","SigLIP-400M","2024/08/08",73.8],[178,"Cambrian-13B",13.0,"Vicuna-v1.5-13B","CLIP ViT-L/14","2024/07/29",73.6],[179,"Eagle-X5-7B",9.0,"Vicuna-v1.5-7B","Clip-448
ConvNeXT-1024
SAM-1024
DET-1024
Pix2Struct-1024","2024/09/26",73.6],[180,"CogVLM2-19B-Chat",19.0,"Llama-3-8B-Instruct","EVA2-CLIP-E","2024/05/31",73.4],[181,"Gemini-1.0-Pro",null,"","","2023/12/23",72.9],[182,"LLaVA-Next-Interleave-7B-DPO",8.0,"Qwen-1.5-7B","SigLIP-400M","2024/07/29",72.9],[183,"VITA",47.0,"Mixtral-8x7B","InternViT-300M","2025/01/20",72.8],[184,"LLaVA-Next-Llama3",8.0,"Llama-3-8B-Instruct","CLIP ViT-L/14","2024/07/29",72.8],[185,"Llama-3-MixSense-v1.1",8.0,"Llama-3-8B-Instruct","Florence-2-Large-FT","2024/08/21",72.4],[186,"IDEFICS2-8B",8.0,"Mistral-7B","SigLIP-400M","2024/04/26",72.3],[187,"LLaVA-Next-Vicuna-13B",13.4,"Vicuna-v1.5-13B","CLIP ViT-L/14","2024/03/25",72.2],[188,"XGen-MM-Instruct-DPO-v1.5",4.4,"Phi-3","SigLIP-400M","2024/09/06",72.0],[189,"360VL-70B",70.0,"Llama-3-70B-Instruct","CLIP ViT-L/14","2024/05/25",71.9],[190,"Emu3_chat",8.49,"","","2025/01/26",71.5],[191,"GPT-4v (1106, detail-high)",null,"","","2024/04/22",71.4],[192,"GLM-4v-9B",9.0,"GLM-4-9B","EVA-02-5B","2024/06/14",71.2],[193,"InternLM-XComposer2-1.8B",2.0,"InternLM2-1.8B","CLIP ViT-L/14","2024/06/09",71.1],[194,"MolmoE-1B",7.2,"OLMoE-1B-7B-0924","CLIP ViT-L/14","2024/10/21",71.0],[195,"H2OVL-2B",2.2,"H2O-DANUBE2-1.8B","InternViT-300M","2024/10/31",70.9],[196,"Gemma3-4B",4.3,"Gemma3-4B","SigLIP-400M","2025/03/19",70.7],[197,"Claude3-Opus",null,"","","2024/03/28",70.6],[198,"XVERSE-V-13B",13.0,"XVERSE-13B","CLIP ViT-L/14","2024/05/10",70.6],[199,"Claude3-Sonnet",null,"","","2024/03/28",69.9],[200,"VILA1.5-13B",13.0,"Vicuna-v1.5-13B","SigLIP-400M","2024/08/25",69.9],[201,"LLaVA-LLaMA-3-8B",8.0,"Llama-3-8B-Instruct","CLIP ViT-L/14","2024/05/07",69.9],[202,"SmolVLM2",2.25,"SmolLM2-1.7M","SigLIP-400M","2025/03/13",69.7],[203,"Mini-InternVL-Chat-2B-V1.5",2.0,"InternLM2-1.8B","InternViT-300M","2024/06/10",69.7],[204,"InternVL3-1B",0.94,"Qwen2.5-0.5B","InternViT-300M-v2.5","2025/04/14",69.7],[205,"Llama-3.2-90B-Vision-Instruct",88.6,"Llama-3.1-70B","","2024/10/19",69.5],[206,"Bunny-Llama3-8B",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/07/18",69.4],[207,"Vintern-3B-beta",3.7,"Qwen-2.5-3B","InternViT-300M","2024/10/24",69.1],[208,"InternVL2.5-1B",1.0,"Qwen-2.5-0.5B","InternViT-300M-v2.5","2024/12/10",69.0],[209,"LLaVA-Next-Mistral-7B",7.6,"Mistral-7B","CLIP ViT-L/14","2024/03/25",69.0],[210,"Monkey-Chat",9.8,"Qwen-7B","ViT-BigHuge","2024/01/16",68.5],[211,"InternVL2.5-1B-MPO",1.0,"Qwen-2.5-0.5B","InternViT-300M-v2.5","2024/12/28",68.5],[212,"Slime-8B",8.0,"Llama-3-8B-Instruct","CLIP ViT-L/14","2024/09/14",68.5],[213,"PaliGemma-3B-mix-448",3.0,"Gemma-2B","SigLIP-400M","2024/05/17",68.3],[214,"Janus-Pro-7B",7.42,"DeepSeek-7B","SigLIP-400M","2025/02/02",68.1],[215,"GPT-4.1-nano-20250414",null,"","","2025/04/16",68.0],[216,"RekaEdge",null,"","","2024/05/31",67.4],[217,"Mantis-8B-Idefics2",8.0,"Mistral-7B","SigLIP-400M","2024/08/08",67.3],[218,"LLaVA-Next-Vicuna-7B",7.1,"Vicuna-v1.5-7B","CLIP ViT-L/14","2024/03/25",67.0],[219,"HawkVL-2B",2.44,"Qwen2.5-1.5B","QwenViT","2025/06/16",66.6],[220,"Slime-13B",13.0,"Vicuna-v1.5-13B","CLIP ViT-L/14","2024/09/14",66.0],[221,"Yi-VL-34B",34.6,"Yi-34B","CLIP ViT-H/14","2024/01/25",65.9],[222,"Qwen-VL-Plus",null,"QwenLM","","2024/01/10",65.7],[223,"Claude3-Haiku",null,"","","2024/03/28",65.6],[224,"LLaVA-InternLM2-20B (QLoRA)",20.2,"InternLM2-20B","CLIP ViT-L/14","2024/01/17",65.4],[225,"DeepSeek-VL-7B",7.3,"DeekSeek-7B","SAM-B
SigLIP-L","2024/03/21",65.3],[226,"SmolVLM-Instruct",2.3,"SmolLM2-1.7B","SigLIP-400M","2025/01/27",64.2],[227,"TransCore-M",13.4,"PCITransGPT-13B","CLIP ViT-L/14","2024/04/16",64.1],[228,"InternVL2-1B",1.0,"Qwen2-0.5B","InternViT-300M","2024/07/11",63.8],[229,"LLaVA-InternLM2-7B (QLoRA)",8.1,"InternLM2-7B","CLIP ViT-L/14","2024/01/17",63.6],[230,"OmniLMM-12B",12.0,"Zephyr-7B-β","EVA-02-5B","2024/02/07",63.3],[231,"CogVLM-17B-Chat",17.0,"Vicuna-v1.5-7B","EVA2-CLIP-E","2024/01/03",63.3],[232,"Qwen-VL-Chat",9.6,"Qwen-7B","ViT-G/16","2023/08/24",63.0],[233,"MiniCPM-V-2",2.8,"MiniCPM-2.4B","SigLIP-400M","2024/04/15",62.9],[234,"Monkey",9.8,"Qwen-7B","ViT-BigHuge","2024/01/11",62.5],[235,"SmolVLM-Instruct-DPO",2.3,"SmolLM2-1.7B","SigLIP-400M","2025/01/27",62.2],[236,"Slime-7B",7.0,"Vicuna-v1.5-7B","CLIP ViT-L/14","2024/09/14",61.9],[237,"ShareGPT4V-13B",13.4,"Vicuna-v1.5-13B","CLIP ViT-L/14","2023/12/08",61.4],[238,"LLaVA-v1.5-13B (QLoRA)",13.4,"Vicuna-v1.5-13B","CLIP ViT-L/14","2023/12/28",61.3],[239,"LLaVA-v1.5-13B",13.4,"Vicuna-v1.5-13B","CLIP ViT-L/14","2023/10/05",61.1],[240,"Parrot-7B",8.0,"Qwen2-7B","CLIP ViT-L/14","2024/08/22",60.9],[241,"Mantis-8B-siglip-llama3",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/08/08",60.4],[242,"Yi-VL-6B",6.6,"Yi-6B","CLIP ViT-H/14","2024/01/25",59.8],[243,"LLaVA-OneVision-0.5B",1.0,"Qwen2-0.5B","SigLIP-400M","2024/09/16",59.4],[244,"SmolVLM-500M",0.51,"SmolLM2-360M","ViT-93M","2025/01/27",59.2],[245,"Moondream2",1.9,"SigLIP-400M","Phi-1.5","2024/10/20",58.8],[246,"Llama-3-VILA1.5-8B",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/08/25",58.8],[247,"LLaVA-InternLM-7B (QLoRA)",7.6,"InternLM-7B","CLIP ViT-L/14","2023/12/28",58.0],[248,"ShareGPT4V-7B",7.2,"Vicuna-v1.5-7B","CLIP ViT-L/14","2023/12/08",58.0],[249,"VILA1.5-3B",3.0,"Sheared-LLaMA-2.7B","SigLIP-400M","2024/08/25",57.9],[250,"Qwen-VL",9.6,"Qwen-7B","ViT-G/16","2023/08/24",57.7],[251,"SmolVLM2-500M",0.51,"SmolLM2-360M","ViT-93M","2025/03/13",57.3],[252,"InternLM-XComposer",8.0,"InternLM-7B","EVA-G","2023/09/26",56.9],[253,"ShareCaptioner",8.0,"InternLM-7B","EVA-G","2024/01/03",56.7],[254,"Mantis-8B-clip-llama3",8.0,"Llama-3-8B-Instruct","CLIP ViT-L/14","2024/08/08",56.6],[255,"Vintern-1B-v2",3.7,"Qwen2-0.5B","InternViT-300M","2024/11/16",56.5],[256,"AKI-4B",4.33,"Phi-3.5","SigLIP-400M","2025/03/25",56.5],[257,"MiniCPM-V",3.0,"MiniCPM-2.4B","SigLIP-400M","2024/02/07",56.3],[258,"LLaVA-v1.5-7B (QLoRA)",7.2,"Vicuna-v1.5-7B","CLIP ViT-L/14","2023/12/28",55.9],[259,"mPLUG-Owl2",8.2,"Llama-2-7B","CLIP ViT-L/14","2023/11/10",55.7],[260,"LLaVA-v1.5-7B",7.2,"Vicuna-v1.5-7B","CLIP ViT-L/14","2023/10/05",55.5],[261,"IDEFICS-80B-Instruct",80.0,"Llama-65B","CLIP ViT-H/14","2023/07/25",54.8],[262,"Chameleon-30B",30.0,"","","2024/07/29",53.7],[263,"LLaVA-OneVision-0.5B (SI)",1.0,"Qwen2-0.5B","SigLIP-400M","2024/09/17",53.5],[264,"H2OVL-800M",0.83,"H2O-DANUBE3-500M","InternViT-300M","2024/10/31",53.5],[265,"Janus-1.3B",2.1,"DeepSeek-1B","SigLIP-400M","2024/10/24",52.8],[266,"abab6.5s",null,"","","2024/12/11",52.0],[267,"DeepSeek-VL-1.3B",2.0,"DeekSeek-1B","SAM-B
SigLIP-L","2024/03/21",51.5],[268,"SmolVLM-Synthetic",2.3,"SmolLM2-1.7B","SigLIP-400M","2025/01/27",50.8],[269,"PandaGPT-13B",14.0,"Vicuna-13B","ImageBind ViT-H/14","2023/05/25",50.3],[270,"Emu2_chat",37.0,"Llama-33B","EVA-02-CLIP-E-plus","2024/01/17",49.7],[271,"Moondream1",1.9,"SigLIP-400M","Phi-1.5","2024/09/26",49.1],[272,"LLaVA-v1-7B",7.2,"Llama-7B","CLIP ViT-L/14","2023/04/17",48.3],[273,"Mantis-8B-Fuyu",8.0,"Fuyu-8B","","2024/09/07",46.8],[274,"SmolVLM-256M",0.26,"SmolLM2-135M","ViT-93M","2025/01/27",46.4],[275,"Chameleon-7B",7.0,"","","2024/07/29",46.0],[276,"MMAlaya",7.8,"Alaya-7B-Chat","EVA-G","2024/01/29",42.3],[277,"IDEFICS-9B-Instruct",9.0,"Llama-7B","CLIP ViT-H/14","2023/07/25",42.2],[278,"VisualGLM",8.0,"ChatGLM 6B","EVA-CLIP","2023/05/17",41.2],[279,"InstructBLIP-7B",8.0,"Vicuna-7B","EVA-G","2023/05/11",40.6],[280,"SmolVLM2-256M",0.26,"SmolLM2-135M","ViT-93M","2025/03/13",39.2],[281,"OpenFlamingo v2",9.0,"MPT 7B","CLIP ViT-L/14","2023/06/28",31.7],[282,"MiniGPT-4-v2",8.0,"Llama-2-13B","EVA-G","2023/10/27",30.5],[283,"MiniGPT-4-v1-7B",8.0,"Vicuna-7B","EVA-G","2023/04/20",28.4],[284,"Kosmos2",1.7,"","","2024/10/19",25.6]],"metadata":null},"headers":["1","2","3"],"row_count":[1,"dynamic"],"col_count":[3,"dynamic"],"datatype":["number","html","number","html","html","str","number"],"type":"pandas","latex_delimiters":[{"left":"$$","right":"$$","display":true}],"show_label":true,"height":500,"min_width":160,"interactive":false,"visible":true,"elem_classes":[],"wrap":true,"line_breaks":true,"column_widths":[],"name":"dataframe","_selectable":false},"skip_api":false,"component_class_id":"6a51bb3357f2e94c40fb8d4fbe06aa8e","key":null,"api_info":{"properties":{"headers":{"items":{"type":"string"},"title":"Headers","type":"array"},"data":{"items":{"items":{},"type":"array"},"title":"Data","type":"array"},"metadata":{"anyOf":[{"additionalProperties":{"anyOf":[{"items":{},"type":"array"},{"type":"null"}]},"type":"object"},{"type":"null"}],"default":null,"title":"Metadata"}},"required":["headers","data"],"title":"DataframeData","type":"object"},"example_inputs":{"headers":["a","b"],"data":[["foo","bar"]]}},{"id":164,"type":"textbox","props":{"value":"AI2D","lines":1,"max_lines":20,"label":"AI2D","show_label":true,"container":true,"min_width":160,"visible":false,"autofocus":false,"autoscroll":true,"elem_classes":[],"type":"text","rtl":false,"show_copy_button":false,"name":"textbox","_selectable":false},"skip_api":false,"component_class_id":"d0491bb0fbd427bdb2a4549c4d1ac869","key":null,"api_info":{"type":"string"},"example_inputs":"Hello!!"},{"id":165,"type":"form","props":{"scale":0,"min_width":0,"name":"form"},"skip_api":true,"component_class_id":"43cda85c6ff7a5dd8f83d29496b014ee","key":null},{"id":166,"type":"form","props":{"scale":0,"min_width":0,"name":"form"},"skip_api":true,"component_class_id":"43cda85c6ff7a5dd8f83d29496b014ee","key":null},{"id":167,"type":"tabitem","props":{"label":"📊 COCO_VAL Leaderboard","visible":true,"interactive":true,"id":15,"elem_id":"COCO_VAL","name":"tab"},"skip_api":true,"component_class_id":"18f46968e2b273dc5dbda0fe78433d7e","key":null},{"id":168,"type":"markdown","props":{"value":"## COCO Caption Results\n\n- By default, we evaluate COCO Caption Validation set (5000 samples), and report the following metrics: BLEU-1, BLEU-4, CIDEr, ROUGE-L (default sorted by CIDEr).\n- We use the following prompt to evaluate all VLMs: `Please describe this image in general. Directly provide the description, do not include prefix like \"This image depicts\". `\n- **No specific prompt is adopted for all VLMs.**","show_label":true,"rtl":false,"latex_delimiters":[{"left":"$$","right":"$$","display":true}],"visible":true,"elem_classes":[],"sanitize_html":true,"line_breaks":false,"header_links":false,"show_copy_button":false,"name":"markdown","_selectable":false},"skip_api":false,"component_class_id":"0f35515b9a3362b42bb6721c836157a0","key":null,"api_info":{"type":"string"},"example_inputs":"# Hello!"},{"id":169,"type":"checkboxgroup","props":{"choices":[["BLEU-1","BLEU-1"],["BLEU-4","BLEU-4"],["ROUGE-L","ROUGE-L"],["CIDEr","CIDEr"]],"value":["BLEU-1","BLEU-4","ROUGE-L","CIDEr"],"type":"value","label":"COCO_VAL CheckBoxes","show_label":true,"container":true,"min_width":160,"interactive":true,"visible":true,"elem_classes":[],"name":"checkboxgroup","_selectable":false},"skip_api":false,"component_class_id":"0635a5d3bf87369f1c2c1c69f8a3d0cc","key":null,"api_info":{"items":{"enum":["BLEU-1","BLEU-4","ROUGE-L","CIDEr"],"type":"string"},"title":"Checkbox Group","type":"array"},"example_inputs":["BLEU-1"]},{"id":170,"type":"row","props":{"variant":"default","visible":true,"equal_height":true,"show_progress":false,"name":"row"},"skip_api":true,"component_class_id":"b5cf3d15e2293fb5ccc071d7b8d69f64","key":null},{"id":171,"type":"textbox","props":{"value":"Input the Model Name (fuzzy, case insensitive)","lines":1,"max_lines":20,"label":"Model Name","show_label":true,"container":true,"min_width":160,"interactive":true,"visible":true,"autofocus":false,"autoscroll":true,"elem_classes":[],"type":"text","rtl":false,"show_copy_button":false,"name":"textbox","_selectable":false},"skip_api":false,"component_class_id":"d0491bb0fbd427bdb2a4549c4d1ac869","key":null,"api_info":{"type":"string"},"example_inputs":"Hello!!"},{"id":172,"type":"checkboxgroup","props":{"choices":[["<4B","<4B"],["4B-10B","4B-10B"],["10B-20B","10B-20B"],["20B-40B","20B-40B"],[">40B",">40B"],["Unknown","Unknown"]],"value":["<4B","4B-10B","10B-20B","20B-40B",">40B","Unknown"],"type":"value","label":"Model Size","show_label":true,"container":true,"min_width":160,"interactive":true,"visible":true,"elem_classes":[],"name":"checkboxgroup","_selectable":false},"skip_api":false,"component_class_id":"0635a5d3bf87369f1c2c1c69f8a3d0cc","key":null,"api_info":{"items":{"enum":["<4B","4B-10B","10B-20B","20B-40B",">40B","Unknown"],"type":"string"},"title":"Checkbox Group","type":"array"},"example_inputs":["<4B"]},{"id":173,"type":"checkboxgroup","props":{"choices":[["API","API"],["OpenSource","OpenSource"]],"value":["API","OpenSource"],"type":"value","label":"Model Type","show_label":true,"container":true,"min_width":160,"interactive":true,"visible":true,"elem_classes":[],"name":"checkboxgroup","_selectable":false},"skip_api":false,"component_class_id":"0635a5d3bf87369f1c2c1c69f8a3d0cc","key":null,"api_info":{"items":{"enum":["API","OpenSource"],"type":"string"},"title":"Checkbox Group","type":"array"},"example_inputs":["API"]},{"id":174,"type":"form","props":{"scale":3,"min_width":480,"name":"form"},"skip_api":true,"component_class_id":"43cda85c6ff7a5dd8f83d29496b014ee","key":null},{"id":175,"type":"dataframe","props":{"value":{"headers":["Rank","Method","Param (B)","Language Model","Vision Model","Eval Date","BLEU-1","BLEU-4","ROUGE-L","CIDEr"],"data":[[1,"Emu2_chat",37.0,"Llama-33B","EVA-02-CLIP-E-plus","2024/01/17",78.2,38.7,56.9,109.2],[2,"Qwen-VL-Chat",9.6,"Qwen-7B","ViT-G/16","2023/08/24",75.8,34.0,54.9,98.9],[3,"Yi-VL-34B",34.6,"Yi-34B","CLIP ViT-H/14","2024/01/25",68.4,31.5,55.2,98.5],[4,"VARCO-VISION-14B",15.2,"Qwen2.5-14B","SigLIP-400M","2025/01/02",73.6,31.3,49.1,95.1],[5,"IDEFICS-80B-Instruct",80.0,"Llama-65B","CLIP ViT-H/14","2023/07/25",76.1,32.5,54.1,94.9],[6,"IDEFICS-9B-Instruct",9.0,"Llama-7B","CLIP ViT-H/14","2023/07/25",72.7,29.4,53.4,90.4],[7,"granite-vision-3.2-2b",2.98,"granite-3.1-2b-instruct","SigLip","2025/06/20",72.5,29.2,53.3,87.7],[8,"360VL-70B",70.0,"Llama-3-70B-Instruct","CLIP ViT-L/14","2024/05/25",71.0,28.1,53.0,86.6],[9,"PaliGemma-3B-mix-448",3.0,"Gemma-2B","SigLIP-400M","2024/05/17",58.9,23.8,45.8,80.6],[10,"granite-vision-3.3-2b",2.98,"granite-3.1-2b-instruct","SigLIP2-400M","2025/06/20",45.8,15.9,50.5,78.5],[11,"Yi-VL-6B",6.6,"Yi-6B","CLIP ViT-H/14","2024/01/25",27.5,9.0,47.1,77.6],[12,"Eagle-X5-34B-Chat",36.8,"Yi-34B","Clip-448
ConvNeXT-1024
SAM-1024
DET-1024
Pix2Struct-1024","2024/11/29",64.0,24.6,50.3,75.9],[13,"Moondream1",1.9,"SigLIP-400M","Phi-1.5","2024/09/26",62.2,21.0,47.7,70.0],[14,"Qwen-VL-Plus",null,"QwenLM","","2024/01/10",47.0,14.6,44.5,64.2],[15,"MiniCPM-V",3.0,"MiniCPM-2.4B","SigLIP-400M","2024/02/07",61.8,19.6,46.1,63.3],[16,"Monkey",9.8,"Qwen-7B","ViT-BigHuge","2024/01/11",42.3,17.7,38.8,62.8],[17,"Parrot-7B",8.0,"Qwen2-7B","CLIP ViT-L/14","2024/08/22",43.5,14.0,45.8,60.8],[18,"InstructBLIP-7B",8.0,"Vicuna-7B","EVA-G","2023/05/11",56.8,20.9,39.9,58.1],[19,"AKI-4B",4.33,"Phi-3.5","SigLIP-400M","2025/03/25",42.8,13.2,40.4,57.3],[20,"XVERSE-V-13B",13.0,"XVERSE-13B","CLIP ViT-L/14","2024/05/10",44.6,14.1,40.4,45.3],[21,"LLaVA-v1.5-7B (QLoRA)",7.2,"Vicuna-v1.5-7B","CLIP ViT-L/14","2023/12/28",25.0,7.2,36.6,43.2],[22,"Eagle-X5-7B",9.0,"Vicuna-v1.5-7B","Clip-448
ConvNeXT-1024
SAM-1024
DET-1024
Pix2Struct-1024","2024/09/26",49.6,15.4,43.9,41.6],[23,"Qwen-VL",9.6,"Qwen-7B","ViT-G/16","2023/08/24",11.6,3.5,30.0,41.1],[24,"InternLM-XComposer",8.0,"InternLM-7B","EVA-G","2023/09/26",38.3,12.4,37.9,41.0],[25,"XGen-MM-Instruct-DPO-v1.5",4.4,"Phi-3","SigLIP-400M","2024/09/06",30.6,8.2,37.8,38.0],[26,"mPLUG-Owl2",8.2,"Llama-2-7B","CLIP ViT-L/14","2023/11/10",25.8,7.1,33.6,35.0],[27,"LLaVA-Next-Qwen-32B",33.0,"Qwen-1.5-32B","SigLIP-400M","2024/08/08",20.8,5.2,31.3,34.4],[28,"TransCore-M",13.4,"PCITransGPT-13B","CLIP ViT-L/14","2024/04/16",17.8,4.3,32.2,33.5],[29,"MiniCPM-V-2",2.8,"MiniCPM-2.4B","SigLIP-400M","2024/04/15",40.7,11.6,35.9,26.4],[30,"DeepSeek-VL-7B",7.3,"DeekSeek-7B","SAM-B
SigLIP-L","2024/03/21",28.1,7.0,33.2,26.3],[31,"Eagle-X5-13B",15.0,"Vicuna-v1.5-13B","Clip-448
ConvNeXT-1024
SAM-1024
DET-1024
Pix2Struct-1024","2024/09/26",37.4,10.5,36.6,22.0],[32,"Aria",25.3,"Aria-MoE","SigLIP-400M","2024/12/05",9.5,3.0,18.7,21.6],[33,"DeepSeek-VL-1.3B",2.0,"DeekSeek-1B","SAM-B
SigLIP-L","2024/03/21",19.1,4.4,27.7,20.8],[34,"LLaVA-v1.5-13B (QLoRA)",13.4,"Vicuna-v1.5-13B","CLIP ViT-L/14","2023/12/28",19.6,5.3,25.8,17.8],[35,"SmolVLM2-256M",0.26,"SmolLM2-135M","ViT-93M","2025/03/13",7.1,1.6,27.5,17.1],[36,"VITA-1.5",8.3,"Qwen2-7B","InternViT-300M","2025/01/01",31.0,7.4,31.6,16.5],[37,"Monkey-Chat",9.8,"Qwen-7B","ViT-BigHuge","2024/01/16",37.8,5.9,25.6,15.6],[38,"OpenFlamingo v2",9.0,"MPT 7B","CLIP ViT-L/14","2023/06/28",6.4,1.3,15.8,14.9],[39,"Kosmos2",1.7,"","","2024/10/19",28.4,7.1,30.0,14.5],[40,"OmniLMM-12B",12.0,"Zephyr-7B-β","EVA-02-5B","2024/02/07",29.8,7.2,28.4,12.1],[41,"Gemini-1.0-Pro",null,"","","2023/12/23",33.2,8.4,31.2,9.7],[42,"LLaVA-Next-Vicuna-13B",13.4,"Vicuna-v1.5-13B","CLIP ViT-L/14","2024/03/25",14.4,3.1,18.2,8.8],[43,"ShareGPT4V-13B",13.4,"Vicuna-v1.5-13B","CLIP ViT-L/14","2023/12/08",12.4,2.6,19.0,8.6],[44,"Step-1.5V-mini",null,"","","2024/12/11",28.1,6.3,27.8,8.5],[45,"InternVL2-26B",26.0,"InternLM2-20B","InternViT-6B","2024/07/11",27.1,6.4,28.4,7.6],[46,"MiniMonkey",2.2,"InternLM2-1.8B","InternViT-300M","2024/09/26",24.5,5.1,26.5,6.8],[47,"Phi-3.5-Vision",4.0,"Phi-3.5","CLIP ViT-L/14","2024/08/28",23.3,5.0,25.0,6.7],[48,"MMAlaya",7.8,"Alaya-7B-Chat","EVA-G","2024/01/29",31.2,8.0,30.8,6.4],[49,"Step-1o",null,"","","2025/01/13",28.5,6.4,28.5,6.4],[50,"VILA1.5-3B",3.0,"Sheared-LLaMA-2.7B","SigLIP-400M","2024/08/25",25.4,6.6,29.5,6.1],[51,"InternLM-XComposer2-4KHD",7.0,"InternLM2-7B","CLIP ViT-L/14","2024/06/09",20.2,4.9,17.7,6.0],[52,"IDEFICS2-8B",8.0,"Mistral-7B","SigLIP-400M","2024/04/26",21.3,2.9,21.6,5.9],[53,"OmChat-v2.0-13B",13.0,"Qwen2-7B","InternViT-6B","2024/08/22",14.8,2.3,22.0,5.9],[54,"LLaVA-v1-7B",7.2,"Llama-7B","CLIP ViT-L/14","2023/04/17",27.0,6.7,26.4,5.5],[55,"LLaVA-OneVision-72B",73.0,"Qwen2-72B","SigLIP-400M","2024/09/19",16.5,3.5,21.0,5.1],[56,"LLaVA-Next-Llama3",8.0,"Llama-3-8B-Instruct","CLIP ViT-L/14","2024/07/29",17.7,3.9,22.4,4.9],[57,"Llama-3-MixSense-v1.1",8.0,"Llama-3-8B-Instruct","Florence-2-Large-FT","2024/08/21",19.4,4.1,22.5,4.8],[58,"H2OVL-2B",2.2,"H2O-DANUBE2-1.8B","InternViT-300M","2024/10/31",9.2,1.8,13.8,4.5],[59,"Step-1.5V",null,"Step-1.5","stepencoder","2024/10/11",24.5,5.3,25.2,4.5],[60,"HunYuan-Standard-Vision",null,"","","2025/01/15",18.1,3.6,19.9,4.4],[61,"Qwen-VL-Max",null,"QwenLM","","2024/02/02",12.3,2.1,16.7,4.3],[62,"Phi-4-MultiModal",5.57,"Phi-4-Mini","SigLIP-400M","2025/03/13",22.9,5.6,24.5,3.3],[63,"Bunny-Llama3-8B",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/07/18",24.8,5.9,25.6,3.2],[64,"Ovis1.5-Gemma2-9B",11.4,"Gemma2-9B-It","SigLIP-400M","2024/08/04",17.0,3.5,20.6,3.2],[65,"Idefics3-8B-Llama3",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/08/27",7.6,1.2,17.2,3.1],[66,"Janus-1.3B",2.1,"DeepSeek-1B","SigLIP-400M","2024/10/24",12.8,2.6,15.0,2.3],[67,"Chameleon-7B",7.0,"","","2024/07/29",12.9,2.3,15.7,2.1],[68,"InternVL3-14B",15.1,"Qwen2.5-14B","InternViT-300M-v2.5","2025/04/14",28.8,6.4,27.6,2.1],[69,"InternVL3-2B",2.09,"Qwen2.5-1.5B","InternViT-300M-v2.5","2025/04/14",27.9,6.1,27.3,2.0],[70,"BlueLM-V-3B",3.0,"BlueLM-3B","SigLIP-400M","2024/10/30",11.7,2.0,12.7,2.0],[71,"BailingMM-Lite-1203",21.0,"Bailing-20B","SigLIP-400M","2024/12/08",29.3,6.9,27.0,1.9],[72,"InternVL3-8B",7.94,"Qwen2.5-7B","InternViT-300M-v2.5","2025/04/14",26.5,5.7,26.0,1.7],[73,"InternVL3-9B",9.14,"InternLM3-8B","InternViT-300M-v2.5","2025/04/14",23.6,4.9,23.9,1.6],[74,"InternVL2-8B-MPO",8.0,"InternLM2.5-7B","InternViT-300M","2024/11/25",25.7,5.3,25.5,1.4],[75,"InternVL3-1B",0.94,"Qwen2.5-0.5B","InternViT-300M-v2.5","2025/04/14",23.7,4.9,23.9,1.3],[76,"InternVL2-40B",40.0,"Nous-Hermes-2-Yi-34B","InternViT-6B","2024/07/11",19.8,4.0,21.2,1.3],[77,"InternLM-XComposer2-1.8B",2.0,"InternLM2-1.8B","CLIP ViT-L/14","2024/06/09",27.1,6.5,25.5,1.3],[78,"InternVL2.5-78B-MPO",78.0,"Qwen-2.5-72B","InternViT-6B-v2.5","2024/12/29",28.9,6.4,27.3,1.3],[79,"InternVL2.5-38B-MPO",38.0,"Qwen-2.5-32B","InternViT-6B-v2.5","2024/12/28",27.8,6.3,26.7,1.1],[80,"InternVL2.5-26B-MPO",26.0,"InternLM2.5-20B","InternViT-6B-v2.5","2024/12/28",27.4,6.1,26.3,1.1],[81,"Ovis2-1B",1.27,"Qwen2.5-0.5B","AIMv2 Large","2025/02/18",17.5,3.3,18.0,1.0],[82,"XGen-MM-Instruct-Interleave-v1.5",4.4,"Phi-3","SigLIP-400M","2024/09/06",12.9,2.5,14.2,0.9],[83,"InternVL3-78B",78.4,"Qwen2.5-72B","InternViT-6B-v2.5","2025/04/14",27.7,6.1,26.3,0.9],[84,"MiniGPT-4-v1-7B",8.0,"Vicuna-7B","EVA-G","2023/04/20",19.6,4.3,17.5,0.8],[85,"InternVL2.5-4B-MPO",4.0,"Qwen-2.5-3B","InternViT-300M-v2.5","2024/12/28",24.9,5.2,24.6,0.8],[86,"BailingMM-Pro-0120",81.0,"Bailing-80B","SigLIP-400M","2025/01/25",20.1,4.2,22.3,0.8],[87,"InternVL3-38B",38.4,"Qwen2.5-32B","InternViT-6B-v2.5","2025/04/14",25.1,5.4,24.7,0.8],[88,"InternVL2.5-8B-MPO",8.0,"InternLM2.5-7B","InternViT-300M-v2.5","2024/12/28",23.8,5.0,24.2,0.7],[89,"MMAlaya2",26.0,"InternLM2-20B","InternViT-6B","2024/08/27",17.4,3.4,17.7,0.6],[90,"InternLM-XComposer2.5",8.0,"InternLM2-7B","CLIP ViT-L/14","2024/07/11",10.1,2.1,2.4,0.6],[91,"GLM-4v-Plus-20250111",null,"","","2025/01/25",24.4,5.2,23.7,0.6],[92,"WeMM",7.0,"InternLM2-7B","SigLIP-400M","2024/06/09",15.5,2.8,17.4,0.5],[93,"InternVL2-4B",4.0,"Phi-3","InternViT-300M","2024/07/11",18.5,3.6,19.6,0.4],[94,"GPT-4.1-nano-20250414",null,"","","2025/04/16",22.6,4.4,22.5,0.4],[95,"LLaVA-v1.5-13B",13.4,"Vicuna-v1.5-13B","CLIP ViT-L/14","2023/10/05",20.7,5.1,21.4,0.4],[96,"SmolVLM-256M",0.26,"SmolLM2-135M","ViT-93M","2025/01/27",4.5,0.8,5.8,0.3],[97,"abab6.5s",null,"","","2024/12/11",20.0,3.1,19.3,0.3],[98,"InternVL2-8B",8.0,"InternLM2.5-7B","InternViT-300M","2024/07/11",16.7,3.2,17.8,0.3],[99,"Ovis1.5-Llama3-8B",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/07/29",16.0,3.1,16.9,0.3],[100,"Slime-7B",7.0,"Vicuna-v1.5-7B","CLIP ViT-L/14","2024/09/14",10.8,1.8,12.6,0.2],[101,"CongRong",null,"","","2024/06/26",15.1,2.8,15.9,0.2],[102,"VisualGLM",8.0,"ChatGLM 6B","EVA-CLIP","2023/05/17",28.6,5.4,23.6,0.2],[103,"XinYuan-VL-2B-Instruct",2.0,"Qwen2-1.5B","QwenViT","2024/09/27",6.1,1.1,8.2,0.2],[104,"Kimi-VL-A3B-Instruct",16.4,"Moonlight-16B-A3B","MoonViT","2025/04/14",12.6,2.4,15.3,0.2],[105,"Cambrian-34B",34.0,"Nous-Hermes-2-Yi-34B","CLIP ViT-L/14","2024/07/18",13.9,2.5,14.3,0.1],[106,"Slime-13B",13.0,"Vicuna-v1.5-13B","CLIP ViT-L/14","2024/09/14",8.9,1.3,10.1,0.1],[107,"Gemini-1.5-Flash",null,"","","2024/09/16",18.4,4.3,22.0,0.1],[108,"CogVLM-17B-Chat",17.0,"Vicuna-v1.5-7B","EVA2-CLIP-E","2024/01/03",21.3,3.6,20.0,0.1],[109,"MiniGPT-4-v2",8.0,"Llama-2-13B","EVA-G","2023/10/27",12.6,1.4,13.3,0.1],[110,"PandaGPT-13B",14.0,"Vicuna-13B","ImageBind ViT-H/14","2023/05/25",19.9,4.6,19.3,0.1],[111,"LLaVA-InternLM-7B (QLoRA)",7.6,"InternLM-7B","CLIP ViT-L/14","2023/12/28",17.3,4.0,17.2,0.1],[112,"LLaVA-Next-Mistral-7B",7.6,"Mistral-7B","CLIP ViT-L/14","2024/03/25",14.5,2.9,14.8,0.1],[113,"CogVLM2-19B-Chat",19.0,"Llama-3-8B-Instruct","EVA2-CLIP-E","2024/05/31",15.3,2.2,15.6,0.1],[114,"Vintern-3B-beta",3.7,"Qwen-2.5-3B","InternViT-300M","2024/10/24",9.4,1.4,11.1,0.1],[115,"InternLM-XComposer2",7.0,"InternLM2-7B","CLIP ViT-L/14","2024/01/26",20.9,4.7,20.0,0.1],[116,"InternVL2.5-2B-MPO",2.0,"InternLM2.5-1.8B","InternViT-300M-v2.5","2024/12/28",18.9,3.4,19.0,0.1],[117,"moonshot-v1-8k",null,"","","2025/03/03",10.8,1.8,6.0,0.1],[118,"Gemma3-4B",4.3,"Gemma3-4B","SigLIP-400M","2025/03/19",18.4,2.9,17.7,0.1],[119,"GPT-4.1-mini-20250414",null,"","","2025/04/16",23.6,4.7,23.1,0.1],[120,"grok-2-vision-1212",null,"","","2025/03/03",23.4,4.7,22.7,0.1],[121,"Ross-Qwen2-7B",8.2,"Qwen2-7B","CLIP ViT-L/14","2025/01/17",4.2,0.7,4.5,0.1],[122,"H2OVL-800M",0.83,"H2O-DANUBE3-500M","InternViT-300M","2024/10/31",17.4,3.5,18.4,0.1],[123,"Gemma3-12B",12.2,"Gemma3-12B","SigLIP-400M","2025/03/19",21.4,3.8,21.1,0.0],[124,"Ovis2-8B",8.94,"Qwen2.5-7B","AIMv2 Huge","2025/02/18",14.2,2.4,14.1,0.0],[125,"Ovis2-4B",4.62,"Qwen2.5-3B","AIMv2 Huge","2025/02/18",14.2,2.5,14.0,0.0],[126,"Ovis2-2B",2.46,"Qwen2.5-1.5B","AIMv2 Large","2025/02/18",17.7,3.4,17.2,0.0],[127,"MUG-U-7B",7.0,"","","2025/03/19",16.3,3.3,16.2,0.0],[128,"GPT-4.1-20250414",null,"","","2025/04/16",21.0,3.9,20.4,0.0],[129,"Gemma3-27B",27.4,"Gemma3-27B","SigLIP-400M","2025/03/19",19.0,3.2,18.5,0.0],[130,"SmolVLM-Instruct",2.3,"SmolLM2-1.7B","SigLIP-400M","2025/01/27",5.0,1.0,6.7,0.0],[131,"InternVL2-8B-MPO-CoT",8.0,"InternLM2.5-7B","InternViT-300M","2024/11/25",15.1,3.8,17.4,0.0],[132,"SAIL-VL-2B",2.1,"Qwen2.5-1.5B","InternViT-300M","2024/12/25",14.5,3.0,15.6,0.0],[133,"abab7-preview",null,"","","2024/12/11",19.1,3.2,18.9,0.0],[134,"InternVL2.5-1B-MPO",1.0,"Qwen-2.5-0.5B","InternViT-300M-v2.5","2024/12/28",18.3,3.4,18.4,0.0],[135,"GLM-4v-Plus",null,"","","2024/12/11",18.3,3.5,17.3,0.0],[136,"Janus-Pro-7B",7.42,"DeepSeek-7B","SigLIP-400M","2025/02/02",19.2,3.5,18.1,0.0],[137,"Ovis2-16B",16.2,"Qwen2.5-14B","AIMv2 Huge","2025/02/18",15.3,2.8,15.8,0.0],[138,"Qwen2.5-VL-3B",3.75,"Qwen2.5-3B","QwenViT","2025/02/02",15.4,2.7,15.8,0.0],[139,"Qwen2.5-VL-7B",8.29,"Qwen2.5-7B","QwenViT","2025/02/02",15.0,2.6,14.5,0.0],[140,"SmolVLM2-500M",0.51,"SmolLM2-360M","ViT-93M","2025/03/13",5.3,1.0,6.2,0.0],[141,"Qwen2.5-VL-72B",73.4,"Qwen2.5-72B","QwenViT","2025/02/02",19.5,3.7,19.2,0.0],[142,"Claude3.7-Sonnet",null,"","","2025/02/27",15.2,2.2,14.4,0.0],[143,"SmolVLM2",2.25,"SmolLM2-1.7M","SigLIP-400M","2025/03/13",7.7,1.3,8.8,0.0],[144,"Ovis2-34B",34.9,"Qwen2.5-32B","AIMv2-1B","2025/02/18",15.7,2.9,15.7,0.0],[145,"MiniCPM-o-2.6",8.67,"Qwen2.5-7B","SigLIP-400M","2025/01/21",13.5,2.5,13.9,0.0],[146,"SmolVLM-500M",0.51,"SmolLM2-360M","ViT-93M","2025/01/27",4.3,0.7,4.8,0.0],[147,"Emu3_chat",8.49,"","","2025/01/26",6.1,1.1,7.4,0.0],[148,"Llama-3.2-90B-Vision-Instruct",88.6,"Llama-3.1-70B","","2024/10/19",12.1,2.4,12.4,0.0],[149,"NVLM-D-72B",79.4,"Qwen2-72B","InternViT-6B","2024/10/19",5.8,1.0,6.4,0.0],[150,"Molmo-7B-O",8.0,"Qwen2-7B","CLIP ViT-L/14","2024/10/20",14.8,2.4,14.4,0.0],[151,"MolmoE-1B",7.2,"OLMoE-1B-7B-0924","CLIP ViT-L/14","2024/10/21",12.4,2.0,12.5,0.0],[152,"Ovis1.6-Llama3.2-3B",4.1,"Llama-3.2-3B","SigLIP-400M","2024/10/24",14.0,2.2,13.9,0.0],[153,"Falcon2-VLM-11B",11.4,"Falcon2-11B","CLIP ViT-L/14","2024/10/30",14.0,2.9,14.7,0.0],[154,"Qwen2-VL-72B",73.4,"Qwen2-72B","QwenViT","2024/10/28",18.5,3.6,17.8,0.0],[155,"Aquila-VL-2B",2.2,"Qwen-2.5-1.5B","SigLIP-400M","2024/10/24",10.5,1.6,11.0,0.0],[156,"Qwen-VL-Max-0809",72.0,"Qwen2-72B","QwenViT","2024/09/12",18.4,3.6,17.7,0.0],[157,"Taiyi",null,"","","2024/12/11",13.9,2.1,14.1,0.0],[158,"POINTS1.5-Qwen2.5-7B",8.3,"Qwen-2.5-7B","NaViT","2024/12/06",10.6,1.6,10.8,0.0],[159,"Ovis1.6-Gemma2-27B",28.9,"Gemma2-27B","SigLIP-400M","2024/11/29",14.5,2.3,14.3,0.0],[160,"SmolVLM-Synthetic",2.3,"SmolLM2-1.7B","SigLIP-400M","2025/01/27",15.6,3.4,18.3,0.0],[161,"SmolVLM-Instruct-DPO",2.3,"SmolLM2-1.7B","SigLIP-400M","2025/01/27",5.3,1.0,7.1,0.0],[162,"Cambrian-13B",13.0,"Vicuna-v1.5-13B","CLIP ViT-L/14","2024/07/29",10.6,1.4,11.0,0.0],[163,"Llama-3.2-11B-Vision-Instruct",11.0,"Llama-3.1-8B","","2024/10/07",10.6,2.4,11.5,0.0],[164,"LLaVA-OneVision-7B",8.0,"Qwen2-7B","SigLIP-400M","2024/09/16",8.5,1.4,9.3,0.0],[165,"LLaVA-OneVision-0.5B (SI)",1.0,"Qwen2-0.5B","SigLIP-400M","2024/09/17",9.3,1.5,9.6,0.0],[166,"LLaVA-OneVision-7B (SI)",8.0,"Qwen2-7B","SigLIP-400M","2024/09/17",13.9,2.6,14.5,0.0],[167,"Qwen-VL-Plus-0809",null,"","","2024/09/17",15.0,2.7,15.0,0.0],[168,"Ovis1.6-Gemma2-9B",10.2,"Gemma2-9B-It","SigLIP-400M","2024/09/19",14.6,2.3,14.3,0.0],[169,"Molmo-7B-D",8.0,"Qwen2-7B","CLIP ViT-L/14","2024/10/12",12.1,1.9,12.1,0.0],[170,"POINTS-Yi-1.5-9B",9.5,"Yi-1.5-9B","CLIP ViT-L/14","2024/10/11",11.4,1.8,11.6,0.0],[171,"POINTS-Qwen2.5-7B",8.3,"Qwen-2.5-7B","CLIP ViT-L/14","2024/10/19",10.9,1.7,11.5,0.0],[172,"Qwen2-VL-2B",2.0,"Qwen2-1.5B","QwenViT","2024/09/12",14.6,2.7,15.7,0.0],[173,"Mantis-8B-Fuyu",8.0,"Fuyu-8B","","2024/09/07",18.5,3.7,18.2,0.0],[174,"Slime-8B",8.0,"Llama-3-8B-Instruct","CLIP ViT-L/14","2024/09/14",7.8,1.2,8.7,0.0],[175,"Pixtral-12B",13.0,"Nemo-12B","ViT-400M","2024/09/16",17.8,3.3,17.3,0.0],[176,"LLaVA-OneVision-0.5B",1.0,"Qwen2-0.5B","SigLIP-400M","2024/09/16",11.2,1.7,11.5,0.0],[177,"Qwen2-VL-7B",8.0,"Qwen2-7B","QwenViT","2024/09/12",14.6,2.6,14.6,0.0],[178,"VILA1.5-40B",40.0,"Yi-34B","InternViT-6B","2024/08/25",9.5,1.2,10.0,0.0],[179,"VILA1.5-13B",13.0,"Vicuna-v1.5-13B","SigLIP-400M","2024/08/25",10.6,1.7,11.6,0.0],[180,"InternVL2-2B",2.0,"InternLM2-1.8B","InternViT-300M","2024/07/11",13.6,2.3,15.0,0.0],[181,"Cambrian-8B",8.0,"Vicuna-v1.5-7B","CLIP ViT-L/14","2024/07/11",12.0,1.9,12.2,0.0],[182,"GPT-4o-mini (0718, detail-high)",null,"","","2024/07/20",21.2,3.9,20.3,0.0],[183,"InternVL2-Llama3-76B",76.0,"Llama-3-70B-Instruct","InternViT-6B","2024/07/19",15.2,2.8,16.8,0.0],[184,"LLaVA-Next-Interleave-7B-DPO",8.0,"Qwen-1.5-7B","SigLIP-400M","2024/07/29",11.2,1.8,11.6,0.0],[185,"Chameleon-30B",30.0,"","","2024/07/29",11.6,2.0,12.0,0.0],[186,"Yi-Vision",null,"","","2024/08/03",12.7,2.0,13.1,0.0],[187,"Llama-3-VILA1.5-8B",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/08/25",11.9,2.1,13.0,0.0],[188,"MiniCPM-V-2.6",8.0,"Qwen2-7B","SigLIP-400M","2024/08/08",10.8,1.6,11.0,0.0],[189,"GPT-4o (0806, detail-high)",null,"","","2024/08/08",24.2,5.1,23.2,0.0],[190,"Mantis-8B-siglip-llama3",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/08/08",18.2,3.9,17.5,0.0],[191,"Mantis-8B-Idefics2",8.0,"Mistral-7B","SigLIP-400M","2024/08/08",17.2,3.8,16.9,0.0],[192,"Mantis-8B-clip-llama3",8.0,"Llama-3-8B-Instruct","CLIP ViT-L/14","2024/08/08",18.4,3.8,17.7,0.0],[193,"LLaVA-Next-Interleave-7B",8.0,"Qwen-1.5-7B","SigLIP-400M","2024/08/08",14.3,2.6,14.4,0.0],[194,"Claude3.5-Sonnet",null,"","","2024/06/24",15.5,2.2,15.0,0.0],[195,"GLM-4v-9B",9.0,"GLM-4-9B","EVA-02-5B","2024/06/14",13.2,2.1,13.6,0.0],[196,"ShareCaptioner",8.0,"InternLM-7B","EVA-G","2024/01/03",8.8,1.0,9.2,0.0],[197,"LLaVA-v1.5-7B",7.2,"Vicuna-v1.5-7B","CLIP ViT-L/14","2023/10/05",19.8,4.7,20.0,0.0],[198,"ShareGPT4V-7B",7.2,"Vicuna-v1.5-7B","CLIP ViT-L/14","2023/12/08",9.6,1.4,10.5,0.0],[199,"Mini-InternVL-Chat-4B-V1.5",4.0,"Phi-3","InternViT-300M","2024/06/10",14.7,2.8,15.0,0.0],[200,"InternVL2-1B",1.0,"Qwen2-0.5B","InternViT-300M","2024/07/11",11.2,1.9,12.7,0.0],[201,"Mini-InternVL-Chat-2B-V1.5",2.0,"InternLM2-1.8B","InternViT-300M","2024/06/10",15.5,3.1,16.2,0.0],[202,"LLaVA-LLaMA-3-8B",8.0,"Llama-3-8B-Instruct","CLIP ViT-L/14","2024/05/07",9.1,1.2,9.8,0.0],[203,"LLaVA-Next-Vicuna-7B",7.1,"Vicuna-v1.5-7B","CLIP ViT-L/14","2024/03/25",12.8,2.4,13.5,0.0],[204,"Phi-3-Vision",4.2,"Phi-3","CLIP ViT-L/14","2024/05/31",15.8,2.9,16.1,0.0],[205,"LLaVA-InternLM2-7B (QLoRA)",8.1,"InternLM2-7B","CLIP ViT-L/14","2024/01/17",18.6,4.3,18.0,0.0],[206,"LLaVA-InternLM2-20B (QLoRA)",20.2,"InternLM2-20B","CLIP ViT-L/14","2024/01/17",17.9,4.0,17.3,0.0],[207,"GPT-4v (1106, detail-low)",null,"","","2023/12/23",18.0,3.3,18.1,0.0],[208,"MiniCPM-Llama3-V2.5",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/05/27",11.1,1.4,11.2,0.0],[209,"LLaVA-Next-Yi-34B",34.8,"Yi-34B","CLIP ViT-L/14","2024/03/25",12.8,2.4,13.1,0.0],[210,"GLM-4v",null,"","","2024/05/20",13.8,1.9,13.3,0.0],[211,"InternVL-Chat-V1.5",26.0,"InternLM2-20B","InternViT-6B","2024/04/17",15.9,3.0,15.8,0.0]],"metadata":null},"headers":["1","2","3"],"row_count":[1,"dynamic"],"col_count":[3,"dynamic"],"datatype":["number","html","number","html","html","str","number","number","number","number"],"type":"pandas","latex_delimiters":[{"left":"$$","right":"$$","display":true}],"show_label":true,"height":500,"min_width":160,"interactive":false,"visible":true,"elem_classes":[],"wrap":true,"line_breaks":true,"column_widths":[],"name":"dataframe","_selectable":false},"skip_api":false,"component_class_id":"6a51bb3357f2e94c40fb8d4fbe06aa8e","key":null,"api_info":{"properties":{"headers":{"items":{"type":"string"},"title":"Headers","type":"array"},"data":{"items":{"items":{},"type":"array"},"title":"Data","type":"array"},"metadata":{"anyOf":[{"additionalProperties":{"anyOf":[{"items":{},"type":"array"},{"type":"null"}]},"type":"object"},{"type":"null"}],"default":null,"title":"Metadata"}},"required":["headers","data"],"title":"DataframeData","type":"object"},"example_inputs":{"headers":["a","b"],"data":[["foo","bar"]]}},{"id":176,"type":"textbox","props":{"value":"COCO_VAL","lines":1,"max_lines":20,"label":"COCO_VAL","show_label":true,"container":true,"min_width":160,"visible":false,"autofocus":false,"autoscroll":true,"elem_classes":[],"type":"text","rtl":false,"show_copy_button":false,"name":"textbox","_selectable":false},"skip_api":false,"component_class_id":"d0491bb0fbd427bdb2a4549c4d1ac869","key":null,"api_info":{"type":"string"},"example_inputs":"Hello!!"},{"id":177,"type":"form","props":{"scale":0,"min_width":0,"name":"form"},"skip_api":true,"component_class_id":"43cda85c6ff7a5dd8f83d29496b014ee","key":null},{"id":178,"type":"form","props":{"scale":0,"min_width":0,"name":"form"},"skip_api":true,"component_class_id":"43cda85c6ff7a5dd8f83d29496b014ee","key":null},{"id":179,"type":"tabitem","props":{"label":"📊 ScienceQA_VAL Leaderboard","visible":true,"interactive":true,"id":16,"elem_id":"ScienceQA_VAL","name":"tab"},"skip_api":true,"component_class_id":"18f46968e2b273dc5dbda0fe78433d7e","key":null},{"id":180,"type":"markdown","props":{"value":"## ScienceQA Evaluation Results\n\n- We benchmark the **image** subset of ScienceQA validation and test set, and report the Top-1 accuracy. \n- During evaluation, we use `GPT-3.5-Turbo-0613` as the choice extractor for all VLMs if the choice can not be extracted via heuristic matching. **Zero-shot** inference is adopted. ","show_label":true,"rtl":false,"latex_delimiters":[{"left":"$$","right":"$$","display":true}],"visible":true,"elem_classes":[],"sanitize_html":true,"line_breaks":false,"header_links":false,"show_copy_button":false,"name":"markdown","_selectable":false},"skip_api":false,"component_class_id":"0f35515b9a3362b42bb6721c836157a0","key":null,"api_info":{"type":"string"},"example_inputs":"# Hello!"},{"id":181,"type":"checkboxgroup","props":{"choices":[["Overall","Overall"],["Adaptations","Adaptations"],["Adaptations and natural selection","Adaptations and natural selection"],["Age of Exploration","Age of Exploration"],["Ancient Egypt and Kush","Ancient Egypt and Kush"],["Ancient Mesopotamia","Ancient Mesopotamia"],["Animals","Animals"],["Astronomy","Astronomy"],["Atoms and molecules","Atoms and molecules"],["Basic economic principles","Basic economic principles"],["Chemical reactions","Chemical reactions"],["Cities","Cities"],["Classification","Classification"],["Classification and scientific names","Classification and scientific names"],["Climate change","Climate change"],["Colonial America","Colonial America"],["Context clues","Context clues"],["Descriptive details","Descriptive details"],["Designing experiments","Designing experiments"],["Domain-specific vocabulary","Domain-specific vocabulary"],["Early 19th century American history","Early 19th century American history"],["Early Americas","Early Americas"],["Earth events","Earth events"],["Ecological interactions","Ecological interactions"],["Ecosystems","Ecosystems"],["Engineering practices","Engineering practices"],["English colonies in North America","English colonies in North America"],["Force and motion","Force and motion"],["Fossils","Fossils"],["Genes to traits","Genes to traits"],["Geography","Geography"],["Government","Government"],["Independent reading comprehension","Independent reading comprehension"],["Informational texts: level 1","Informational texts: level 1"],["Magnets","Magnets"],["Maps","Maps"],["Materials","Materials"],["Medieval Asia","Medieval Asia"],["Natural resources and human impacts","Natural resources and human impacts"],["Oceania: geography","Oceania: geography"],["Oceans and continents","Oceans and continents"],["Oceans and continents\t","Oceans and continents\t"],["Particle motion and energy","Particle motion and energy"],["Persuasive strategies","Persuasive strategies"],["Physical Geography","Physical Geography"],["Plant reproduction","Plant reproduction"],["Plants","Plants"],["Plate tectonics","Plate tectonics"],["Read-alone texts","Read-alone texts"],["Rocks and minerals","Rocks and minerals"],["Rome and the Byzantine Empire","Rome and the Byzantine Empire"],["Scientific names","Scientific names"],["Solutions","Solutions"],["State capitals","State capitals"],["States","States"],["States of matter","States of matter"],["The American Revolution","The American Revolution"],["The Americas: geography","The Americas: geography"],["The Antebellum period","The Antebellum period"],["The Civil War and Reconstruction","The Civil War and Reconstruction"],["The Silk Road","The Silk Road"],["Thermal energy","Thermal energy"],["Velocity, acceleration, and forces","Velocity, acceleration, and forces"],["Visual elements","Visual elements"],["Water cycle","Water cycle"],["Weather and climate","Weather and climate"],["World religions","World religions"]],"value":["Overall"],"type":"value","label":"ScienceQA_VAL CheckBoxes","show_label":true,"container":true,"min_width":160,"interactive":true,"visible":true,"elem_classes":[],"name":"checkboxgroup","_selectable":false},"skip_api":false,"component_class_id":"0635a5d3bf87369f1c2c1c69f8a3d0cc","key":null,"api_info":{"items":{"enum":["Overall","Adaptations","Adaptations and natural selection","Age of Exploration","Ancient Egypt and Kush","Ancient Mesopotamia","Animals","Astronomy","Atoms and molecules","Basic economic principles","Chemical reactions","Cities","Classification","Classification and scientific names","Climate change","Colonial America","Context clues","Descriptive details","Designing experiments","Domain-specific vocabulary","Early 19th century American history","Early Americas","Earth events","Ecological interactions","Ecosystems","Engineering practices","English colonies in North America","Force and motion","Fossils","Genes to traits","Geography","Government","Independent reading comprehension","Informational texts: level 1","Magnets","Maps","Materials","Medieval Asia","Natural resources and human impacts","Oceania: geography","Oceans and continents","Oceans and continents\t","Particle motion and energy","Persuasive strategies","Physical Geography","Plant reproduction","Plants","Plate tectonics","Read-alone texts","Rocks and minerals","Rome and the Byzantine Empire","Scientific names","Solutions","State capitals","States","States of matter","The American Revolution","The Americas: geography","The Antebellum period","The Civil War and Reconstruction","The Silk Road","Thermal energy","Velocity, acceleration, and forces","Visual elements","Water cycle","Weather and climate","World religions"],"type":"string"},"title":"Checkbox Group","type":"array"},"example_inputs":["Overall"]},{"id":182,"type":"row","props":{"variant":"default","visible":true,"equal_height":true,"show_progress":false,"name":"row"},"skip_api":true,"component_class_id":"b5cf3d15e2293fb5ccc071d7b8d69f64","key":null},{"id":183,"type":"textbox","props":{"value":"Input the Model Name (fuzzy, case insensitive)","lines":1,"max_lines":20,"label":"Model Name","show_label":true,"container":true,"min_width":160,"interactive":true,"visible":true,"autofocus":false,"autoscroll":true,"elem_classes":[],"type":"text","rtl":false,"show_copy_button":false,"name":"textbox","_selectable":false},"skip_api":false,"component_class_id":"d0491bb0fbd427bdb2a4549c4d1ac869","key":null,"api_info":{"type":"string"},"example_inputs":"Hello!!"},{"id":184,"type":"checkboxgroup","props":{"choices":[["<4B","<4B"],["4B-10B","4B-10B"],["10B-20B","10B-20B"],["20B-40B","20B-40B"],[">40B",">40B"],["Unknown","Unknown"]],"value":["<4B","4B-10B","10B-20B","20B-40B",">40B","Unknown"],"type":"value","label":"Model Size","show_label":true,"container":true,"min_width":160,"interactive":true,"visible":true,"elem_classes":[],"name":"checkboxgroup","_selectable":false},"skip_api":false,"component_class_id":"0635a5d3bf87369f1c2c1c69f8a3d0cc","key":null,"api_info":{"items":{"enum":["<4B","4B-10B","10B-20B","20B-40B",">40B","Unknown"],"type":"string"},"title":"Checkbox Group","type":"array"},"example_inputs":["<4B"]},{"id":185,"type":"checkboxgroup","props":{"choices":[["API","API"],["OpenSource","OpenSource"]],"value":["API","OpenSource"],"type":"value","label":"Model Type","show_label":true,"container":true,"min_width":160,"interactive":true,"visible":true,"elem_classes":[],"name":"checkboxgroup","_selectable":false},"skip_api":false,"component_class_id":"0635a5d3bf87369f1c2c1c69f8a3d0cc","key":null,"api_info":{"items":{"enum":["API","OpenSource"],"type":"string"},"title":"Checkbox Group","type":"array"},"example_inputs":["API"]},{"id":186,"type":"form","props":{"scale":3,"min_width":480,"name":"form"},"skip_api":true,"component_class_id":"43cda85c6ff7a5dd8f83d29496b014ee","key":null},{"id":187,"type":"dataframe","props":{"value":{"headers":["Rank","Method","Param (B)","Language Model","Vision Model","Eval Date","Overall"],"data":[[1,"InternVL3-38B",38.4,"Qwen2.5-32B","InternViT-6B-v2.5","2025/04/14",99.2],[2,"InternVL2.5-78B-MPO",78.0,"Qwen-2.5-72B","InternViT-6B-v2.5","2024/12/29",99.0],[3,"GLM-4v-9B",9.0,"GLM-4-9B","EVA-02-5B","2024/06/14",98.7],[4,"InternVL2.5-38B-MPO",38.0,"Qwen-2.5-32B","InternViT-6B-v2.5","2024/12/28",98.6],[5,"GLM-4v",null,"","","2024/05/20",98.6],[6,"Taiyi",null,"","","2024/12/11",98.6],[7,"VARCO-VISION-14B",15.2,"Qwen2.5-14B","SigLIP-400M","2025/01/02",98.5],[8,"InternVL3-78B",78.4,"Qwen2.5-72B","InternViT-6B-v2.5","2025/04/14",98.5],[9,"InternVL3-14B",15.1,"Qwen2.5-14B","InternViT-300M-v2.5","2025/04/14",98.4],[10,"InternVL2.5-26B-MPO",26.0,"InternLM2.5-20B","InternViT-6B-v2.5","2024/12/28",98.3],[11,"MUG-U-7B",7.0,"","","2025/03/19",98.2],[12,"InternVL2-Llama3-76B",76.0,"Llama-3-70B-Instruct","InternViT-6B","2024/07/19",98.2],[13,"MiniCPM-o-2.6",8.67,"Qwen2.5-7B","SigLIP-400M","2025/01/21",98.1],[14,"GLM-4v-Plus-20250111",null,"","","2025/01/25",97.9],[15,"InternVL2-26B",26.0,"InternLM2-20B","InternViT-6B","2024/07/11",97.9],[16,"BailingMM-Pro-0120",81.0,"Bailing-80B","SigLIP-400M","2025/01/25",97.9],[17,"InternVL3-8B",7.94,"Qwen2.5-7B","InternViT-300M-v2.5","2025/04/14",97.9],[18,"InternVL2.5-8B-MPO",8.0,"InternLM2.5-7B","InternViT-300M-v2.5","2024/12/28",97.9],[19,"InternVL2-40B",40.0,"Nous-Hermes-2-Yi-34B","InternViT-6B","2024/07/11",97.8],[20,"BailingMM-Lite-1203",21.0,"Bailing-20B","SigLIP-400M","2024/12/08",97.7],[21,"InternVL2-8B-MPO",8.0,"InternLM2.5-7B","InternViT-300M","2024/11/25",97.6],[22,"InternVL3-9B",9.14,"InternLM3-8B","InternViT-300M-v2.5","2025/04/14",97.5],[23,"InternVL2-8B",8.0,"InternLM2.5-7B","InternViT-300M","2024/07/11",97.4],[24,"InternVL2.5-4B-MPO",4.0,"Qwen-2.5-3B","InternViT-300M-v2.5","2024/12/28",97.4],[25,"Aria",25.3,"Aria-MoE","SigLIP-400M","2024/12/05",97.2],[26,"abab7-preview",null,"","","2024/12/11",96.9],[27,"GLM-4v-Plus",null,"","","2024/12/11",96.8],[28,"InternLM-XComposer2",7.0,"InternLM2-7B","CLIP ViT-L/14","2024/01/26",96.5],[29,"Ovis2-34B",34.9,"Qwen2.5-32B","AIMv2-1B","2025/02/18",96.4],[30,"InternLM-XComposer2-4KHD",7.0,"InternLM2-7B","CLIP ViT-L/14","2024/06/09",96.3],[31,"Phi-4-MultiModal",5.57,"Phi-4-Mini","SigLIP-400M","2025/03/13",96.3],[32,"InternLM-XComposer2.5",8.0,"InternLM2-7B","CLIP ViT-L/14","2024/07/11",96.1],[33,"InternVL2-4B",4.0,"Phi-3","InternViT-300M","2024/07/11",96.0],[34,"MiniCPM-V-2.6",8.0,"Qwen2-7B","SigLIP-400M","2024/08/08",96.0],[35,"SAIL-VL-2B",2.1,"Qwen2.5-1.5B","InternViT-300M","2024/12/25",95.7],[36,"Step-1o",null,"","","2025/01/13",95.6],[37,"HunYuan-Standard-Vision",null,"","","2025/01/15",95.5],[38,"VITA-1.5",8.3,"Qwen2-7B","InternViT-300M","2025/01/01",95.5],[39,"POINTS1.5-Qwen2.5-7B",8.3,"Qwen-2.5-7B","NaViT","2024/12/06",95.4],[40,"CongRong",null,"","","2024/06/26",95.3],[41,"Kimi-VL-A3B-Instruct",16.4,"Moonlight-16B-A3B","MoonViT","2025/04/14",95.3],[42,"InternVL2.5-2B-MPO",2.0,"InternLM2.5-1.8B","InternViT-300M-v2.5","2024/12/28",95.2],[43,"POINTS-Qwen2.5-7B",8.3,"Qwen-2.5-7B","CLIP ViT-L/14","2024/10/19",95.2],[44,"InternVL3-2B",2.09,"Qwen2.5-1.5B","InternViT-300M-v2.5","2025/04/14",95.1],[45,"Ovis2-8B",8.94,"Qwen2.5-7B","AIMv2 Huge","2025/02/18",95.1],[46,"LLaVA-OneVision-7B",8.0,"Qwen2-7B","SigLIP-400M","2024/09/16",95.1],[47,"Ovis2-16B",16.2,"Qwen2.5-14B","AIMv2 Huge","2025/02/18",95.0],[48,"Ross-Qwen2-7B",8.2,"Qwen2-7B","CLIP ViT-L/14","2025/01/17",95.0],[49,"BlueLM-V-3B",3.0,"BlueLM-3B","SigLIP-400M","2024/10/30",94.8],[50,"POINTS-Yi-1.5-9B",9.5,"Yi-1.5-9B","CLIP ViT-L/14","2024/10/11",94.6],[51,"Ovis2-4B",4.62,"Qwen2.5-3B","AIMv2 Huge","2025/02/18",94.5],[52,"Step-1.5V",null,"Step-1.5","stepencoder","2024/10/11",94.4],[53,"InternVL2-2B",2.0,"InternLM2-1.8B","InternViT-300M","2024/07/11",94.3],[54,"Ovis1.6-Gemma2-27B",28.9,"Gemma2-27B","SigLIP-400M","2024/11/29",94.2],[55,"MiniMonkey",2.2,"InternLM2-1.8B","InternViT-300M","2024/09/26",93.7],[56,"Aquila-VL-2B",2.2,"Qwen-2.5-1.5B","SigLIP-400M","2024/10/24",93.7],[57,"InternVL-Chat-V1.5",26.0,"InternLM2-20B","InternViT-6B","2024/04/17",93.7],[58,"Ovis1.6-Gemma2-9B",10.2,"Gemma2-9B-It","SigLIP-400M","2024/09/19",93.6],[59,"Ovis1.5-Gemma2-9B",11.4,"Gemma2-9B-It","SigLIP-400M","2024/08/04",93.5],[60,"MMAlaya2",26.0,"InternLM2-20B","InternViT-6B","2024/08/27",93.4],[61,"InternVL2.5-1B-MPO",1.0,"Qwen-2.5-0.5B","InternViT-300M-v2.5","2024/12/28",93.3],[62,"PaliGemma-3B-mix-448",3.0,"Gemma-2B","SigLIP-400M","2024/05/17",93.3],[63,"granite-vision-3.2-2b",2.98,"granite-3.1-2b-instruct","SigLip","2025/06/20",93.1],[64,"NVLM-D-72B",79.4,"Qwen2-72B","InternViT-6B","2024/10/19",93.1],[65,"GPT-4.1-20250414",null,"","","2025/04/16",92.6],[66,"Mini-InternVL-Chat-4B-V1.5",4.0,"Phi-3","InternViT-300M","2024/06/10",92.1],[67,"InternLM-XComposer2-1.8B",2.0,"InternLM2-1.8B","CLIP ViT-L/14","2024/06/09",91.9],[68,"Qwen-VL-Max-0809",72.0,"Qwen2-72B","QwenViT","2024/09/12",91.8],[69,"Qwen2-VL-72B",73.4,"Qwen2-72B","QwenViT","2024/10/28",91.6],[70,"Qwen2.5-VL-72B",73.4,"Qwen2.5-72B","QwenViT","2025/02/02",91.3],[71,"InternVL2-8B-MPO-CoT",8.0,"InternLM2.5-7B","InternViT-300M","2024/11/25",91.2],[72,"RBDash-v1.5",79.0,"Qwen2-72B","CLIP ViT-L/14
InternViT-6B","2024/11/17",90.9],[73,"Claude3.7-Sonnet",null,"","","2025/02/27",90.9],[74,"H2OVL-2B",2.2,"H2O-DANUBE2-1.8B","InternViT-300M","2024/10/31",90.6],[75,"Idefics3-8B-Llama3",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/08/27",90.5],[76,"grok-2-vision-1212",null,"","","2025/03/03",90.3],[77,"Phi-3.5-Vision",4.0,"Phi-3.5","CLIP ViT-L/14","2024/08/28",90.3],[78,"Phi-3-Vision",4.2,"Phi-3","CLIP ViT-L/14","2024/05/31",90.2],[79,"Ovis2-2B",2.46,"Qwen2.5-1.5B","AIMv2 Large","2025/02/18",90.1],[80,"GPT-4o (0806, detail-high)",null,"","","2024/08/08",90.1],[81,"granite-vision-3.3-2b",2.98,"granite-3.1-2b-instruct","SigLIP2-400M","2025/06/20",89.9],[82,"OmChat-v2.0-13B",13.0,"Qwen2-7B","InternViT-6B","2024/08/22",89.8],[83,"LLaVA-OneVision-72B",73.0,"Qwen2-72B","SigLIP-400M","2024/09/19",89.7],[84,"GPT-4o (0513, detail-high)",null,"","","2024/05/31",89.7],[85,"InternVL3-1B",0.94,"Qwen2.5-0.5B","InternViT-300M-v2.5","2025/04/14",89.6],[86,"GPT-4o (0513, detail-low)",null,"","","2024/05/15",89.4],[87,"Claude3.5-Sonnet",null,"","","2024/06/24",89.3],[88,"Ovis1.5-Llama3-8B",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/07/29",89.3],[89,"360VL-70B",70.0,"Llama-3-70B-Instruct","CLIP ViT-L/14","2024/05/25",88.9],[90,"Qwen2.5-VL-7B",8.29,"Qwen2.5-7B","QwenViT","2025/02/02",88.9],[91,"Molmo-7B-O",8.0,"Qwen2-7B","CLIP ViT-L/14","2024/10/20",88.8],[92,"Eagle-X5-34B-Chat",36.8,"Yi-34B","Clip-448
ConvNeXT-1024
SAM-1024
DET-1024
Pix2Struct-1024","2024/11/29",88.7],[93,"MiniCPM-Llama3-V2.5",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/05/27",88.4],[94,"CogVLM2-19B-Chat",19.0,"Llama-3-8B-Instruct","EVA2-CLIP-E","2024/05/31",88.4],[95,"SmolVLM2",2.25,"SmolLM2-1.7M","SigLIP-400M","2025/03/13",88.4],[96,"InternLM-XComposer",8.0,"InternLM-7B","EVA-G","2023/09/26",88.0],[97,"Emu3_chat",8.49,"","","2025/01/26",87.8],[98,"LLaVA-OneVision-7B (SI)",8.0,"Qwen2-7B","SigLIP-400M","2024/09/17",87.6],[99,"Gemma3-27B",27.4,"Gemma3-27B","SigLIP-400M","2025/03/19",87.1],[100,"MolmoE-1B",7.2,"OLMoE-1B-7B-0924","CLIP ViT-L/14","2024/10/21",86.9],[101,"InternVL2-1B",1.0,"Qwen2-0.5B","InternViT-300M","2024/07/11",86.8],[102,"XinYuan-VL-2B-Instruct",2.0,"Qwen2-1.5B","QwenViT","2024/09/27",86.7],[103,"Pixtral-12B",13.0,"Nemo-12B","ViT-400M","2024/09/16",86.6],[104,"XVERSE-V-13B",13.0,"XVERSE-13B","CLIP ViT-L/14","2024/05/10",86.6],[105,"Yi-Vision",null,"","","2024/08/03",86.5],[106,"IDEFICS2-8B",8.0,"Mistral-7B","SigLIP-400M","2024/04/26",86.5],[107,"Ovis1.6-Llama3.2-3B",4.1,"Llama-3.2-3B","SigLIP-400M","2024/10/24",86.3],[108,"AKI-4B",4.33,"Phi-3.5","SigLIP-400M","2025/03/25",86.3],[109,"Gemini-1.5-Pro",null,"","","2024/06/10",85.9],[110,"XGen-MM-Instruct-Interleave-v1.5",4.4,"Phi-3","SigLIP-400M","2024/09/06",85.7],[111,"GPT-4o-mini (0718, detail-high)",null,"","","2024/07/20",85.6],[112,"RekaFlash",null,"","","2024/05/07",85.4],[113,"Cambrian-34B",34.0,"Nous-Hermes-2-Yi-34B","CLIP ViT-L/14","2024/07/18",85.3],[114,"Gemma3-12B",12.2,"Gemma3-12B","SigLIP-400M","2025/03/19",85.2],[115,"Qwen2-VL-7B",8.0,"Qwen2-7B","QwenViT","2024/09/12",84.6],[116,"GPT-4v (1106, detail-low)",null,"","","2023/12/23",84.6],[117,"GPT-4v (0409, detail-high)",null,"","","2024/05/15",84.5],[118,"Qwen-VL-Plus-0809",null,"","","2024/09/17",84.4],[119,"Step-1.5V-mini",null,"","","2024/12/11",84.4],[120,"VILA1.5-40B",40.0,"Yi-34B","InternViT-6B","2024/08/25",83.9],[121,"Llama-3.2-90B-Vision-Instruct",88.6,"Llama-3.1-70B","","2024/10/19",83.5],[122,"Gemini-1.5-Flash",null,"","","2024/09/16",82.9],[123,"Llama-3-MixSense-v1.1",8.0,"Llama-3-8B-Instruct","Florence-2-Large-FT","2024/08/21",82.7],[124,"XGen-MM-Instruct-DPO-v1.5",4.4,"Phi-3","SigLIP-400M","2024/09/06",81.9],[125,"Mini-InternVL-Chat-2B-V1.5",2.0,"InternLM2-1.8B","InternViT-300M","2024/06/10",81.9],[126,"GPT-4.1-mini-20250414",null,"","","2025/04/16",81.7],[127,"ShareCaptioner",8.0,"InternLM-7B","EVA-G","2024/01/03",81.0],[128,"Llama-3.2-11B-Vision-Instruct",11.0,"Llama-3.1-8B","","2024/10/07",80.9],[129,"Monkey-Chat",9.8,"Qwen-7B","ViT-BigHuge","2024/01/16",80.8],[130,"Janus-Pro-7B",7.42,"DeepSeek-7B","SigLIP-400M","2025/02/02",80.7],[131,"Cambrian-8B",8.0,"Vicuna-v1.5-7B","CLIP ViT-L/14","2024/07/11",80.5],[132,"WeMM",7.0,"InternLM2-7B","SigLIP-400M","2024/06/09",80.5],[133,"Gemini-1.0-Pro",null,"","","2023/12/23",80.1],[134,"Qwen-VL-Max",null,"QwenLM","","2024/02/02",79.8],[135,"Ovis2-1B",1.27,"Qwen2.5-0.5B","AIMv2 Large","2025/02/18",79.7],[136,"SmolVLM-Instruct",2.3,"SmolLM2-1.7B","SigLIP-400M","2025/01/27",79.6],[137,"Qwen2.5-VL-3B",3.75,"Qwen2.5-3B","QwenViT","2025/02/02",79.3],[138,"Slime-8B",8.0,"Llama-3-8B-Instruct","CLIP ViT-L/14","2024/09/14",78.8],[139,"LLaVA-Next-Yi-34B",34.8,"Yi-34B","CLIP ViT-L/14","2024/03/25",78.8],[140,"Bunny-Llama3-8B",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/07/18",78.6],[141,"OmniLMM-12B",12.0,"Zephyr-7B-β","EVA-02-5B","2024/02/07",78.5],[142,"SmolVLM-Instruct-DPO",2.3,"SmolLM2-1.7B","SigLIP-400M","2025/01/27",78.5],[143,"VILA1.5-13B",13.0,"Vicuna-v1.5-13B","SigLIP-400M","2024/08/25",77.7],[144,"Mantis-8B-Idefics2",8.0,"Mistral-7B","SigLIP-400M","2024/08/08",77.4],[145,"GPT-4.1-nano-20250414",null,"","","2025/04/16",76.8],[146,"LLaVA-Next-Qwen-32B",33.0,"Qwen-1.5-32B","SigLIP-400M","2024/08/08",76.8],[147,"SmolVLM-500M",0.51,"SmolLM2-360M","ViT-93M","2025/01/27",76.5],[148,"Cambrian-13B",13.0,"Vicuna-v1.5-13B","CLIP ViT-L/14","2024/07/29",76.4],[149,"MiniCPM-V-2",2.8,"MiniCPM-2.4B","SigLIP-400M","2024/04/15",76.3],[150,"DeepSeek-VL-7B",7.3,"DeekSeek-7B","SAM-B
SigLIP-L","2024/03/21",76.0],[151,"Gemma3-4B",4.3,"Gemma3-4B","SigLIP-400M","2025/03/19",76.0],[152,"TransCore-M",13.4,"PCITransGPT-13B","CLIP ViT-L/14","2024/04/16",74.4],[153,"MiniCPM-V",3.0,"MiniCPM-2.4B","SigLIP-400M","2024/02/07",74.4],[154,"Qwen2-VL-2B",2.0,"Qwen2-1.5B","QwenViT","2024/09/12",74.3],[155,"Slime-7B",7.0,"Vicuna-v1.5-7B","CLIP ViT-L/14","2024/09/14",73.8],[156,"LLaVA-Next-Llama3",8.0,"Llama-3-8B-Instruct","CLIP ViT-L/14","2024/07/29",73.7],[157,"Falcon2-VLM-11B",11.4,"Falcon2-11B","CLIP ViT-L/14","2024/10/30",73.7],[158,"Vintern-3B-beta",3.7,"Qwen-2.5-3B","InternViT-300M","2024/10/24",73.6],[159,"Yi-VL-34B",34.6,"Yi-34B","CLIP ViT-H/14","2024/01/25",73.6],[160,"SmolVLM2-500M",0.51,"SmolLM2-360M","ViT-93M","2025/03/13",73.5],[161,"Slime-13B",13.0,"Vicuna-v1.5-13B","CLIP ViT-L/14","2024/09/14",73.4],[162,"Mantis-8B-siglip-llama3",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/08/08",73.0],[163,"LLaVA-InternLM2-20B (QLoRA)",20.2,"InternLM2-20B","CLIP ViT-L/14","2024/01/17",72.7],[164,"SmolVLM-256M",0.26,"SmolLM2-135M","ViT-93M","2025/01/27",72.1],[165,"LLaVA-LLaMA-3-8B",8.0,"Llama-3-8B-Instruct","CLIP ViT-L/14","2024/05/07",72.1],[166,"Janus-1.3B",2.1,"DeepSeek-1B","SigLIP-400M","2024/10/24",71.9],[167,"Eagle-X5-7B",9.0,"Vicuna-v1.5-7B","Clip-448
ConvNeXT-1024
SAM-1024
DET-1024
Pix2Struct-1024","2024/09/26",71.8],[168,"Llama-3-VILA1.5-8B",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/08/25",71.7],[169,"Yi-VL-6B",6.6,"Yi-6B","CLIP ViT-H/14","2024/01/25",71.7],[170,"Qwen-VL-Plus",null,"QwenLM","","2024/01/10",71.6],[171,"LLaVA-Next-Vicuna-13B",13.4,"Vicuna-v1.5-13B","CLIP ViT-L/14","2024/03/25",71.4],[172,"RekaEdge",null,"","","2024/05/31",71.0],[173,"LLaVA-InternLM2-7B (QLoRA)",8.1,"InternLM2-7B","CLIP ViT-L/14","2024/01/17",70.9],[174,"ShareGPT4V-13B",13.4,"Vicuna-v1.5-13B","CLIP ViT-L/14","2023/12/08",70.7],[175,"Eagle-X5-13B",15.0,"Vicuna-v1.5-13B","Clip-448
ConvNeXT-1024
SAM-1024
DET-1024
Pix2Struct-1024","2024/09/26",70.6],[176,"Parrot-7B",8.0,"Qwen2-7B","CLIP ViT-L/14","2024/08/22",70.2],[177,"Mantis-8B-clip-llama3",8.0,"Llama-3-8B-Instruct","CLIP ViT-L/14","2024/08/08",69.9],[178,"LLaVA-Next-Mistral-7B",7.6,"Mistral-7B","CLIP ViT-L/14","2024/03/25",69.5],[179,"mPLUG-Owl2",8.2,"Llama-2-7B","CLIP ViT-L/14","2023/11/10",69.5],[180,"LLaVA-v1.5-13B",13.4,"Vicuna-v1.5-13B","CLIP ViT-L/14","2023/10/05",69.5],[181,"LLaVA-Next-Interleave-7B-DPO",8.0,"Qwen-1.5-7B","SigLIP-400M","2024/07/29",69.0],[182,"LLaVA-v1.5-13B (QLoRA)",13.4,"Vicuna-v1.5-13B","CLIP ViT-L/14","2023/12/28",68.9],[183,"LLaVA-v1.5-7B (QLoRA)",7.2,"Vicuna-v1.5-7B","CLIP ViT-L/14","2023/12/28",68.8],[184,"LLaVA-Next-Vicuna-7B",7.1,"Vicuna-v1.5-7B","CLIP ViT-L/14","2024/03/25",68.5],[185,"Monkey",9.8,"Qwen-7B","ViT-BigHuge","2024/01/11",68.2],[186,"ShareGPT4V-7B",7.2,"Vicuna-v1.5-7B","CLIP ViT-L/14","2023/12/08",68.2],[187,"LLaVA-Next-Interleave-7B",8.0,"Qwen-1.5-7B","SigLIP-400M","2024/08/08",68.2],[188,"H2OVL-800M",0.83,"H2O-DANUBE3-500M","InternViT-300M","2024/10/31",66.9],[189,"LLaVA-v1.5-7B",7.2,"Vicuna-v1.5-7B","CLIP ViT-L/14","2023/10/05",66.6],[190,"CogVLM-17B-Chat",17.0,"Vicuna-v1.5-7B","EVA2-CLIP-E","2024/01/03",65.6],[191,"Qwen-VL-Chat",9.6,"Qwen-7B","ViT-G/16","2023/08/24",65.5],[192,"Emu2_chat",37.0,"Llama-33B","EVA-02-CLIP-E-plus","2024/01/17",65.3],[193,"LLaVA-InternLM-7B (QLoRA)",7.6,"InternLM-7B","CLIP ViT-L/14","2023/12/28",65.3],[194,"LLaVA-OneVision-0.5B",1.0,"Qwen2-0.5B","SigLIP-400M","2024/09/16",64.6],[195,"DeepSeek-VL-1.3B",2.0,"DeekSeek-1B","SAM-B
SigLIP-L","2024/03/21",64.2],[196,"VILA1.5-3B",3.0,"Sheared-LLaMA-2.7B","SigLIP-400M","2024/08/25",63.9],[197,"LLaVA-OneVision-0.5B (SI)",1.0,"Qwen2-0.5B","SigLIP-400M","2024/09/17",63.8],[198,"SmolVLM-Synthetic",2.3,"SmolLM2-1.7B","SigLIP-400M","2025/01/27",62.5],[199,"LLaVA-v1-7B",7.2,"Llama-7B","CLIP ViT-L/14","2023/04/17",61.9],[200,"PandaGPT-13B",14.0,"Vicuna-13B","ImageBind ViT-H/14","2023/05/25",60.9],[201,"abab6.5s",null,"","","2024/12/11",60.8],[202,"IDEFICS-80B-Instruct",80.0,"Llama-65B","CLIP ViT-H/14","2023/07/25",59.9],[203,"Moondream1",1.9,"SigLIP-400M","Phi-1.5","2024/09/26",59.2],[204,"MMAlaya",7.8,"Alaya-7B-Chat","EVA-G","2024/01/29",57.7],[205,"Qwen-VL",9.6,"Qwen-7B","ViT-G/16","2023/08/24",57.7],[206,"Chameleon-30B",30.0,"","","2024/07/29",57.6],[207,"SmolVLM2-256M",0.26,"SmolLM2-135M","ViT-93M","2025/03/13",56.3],[208,"Molmo-7B-D",8.0,"Qwen2-7B","CLIP ViT-L/14","2024/10/12",55.6],[209,"InstructBLIP-7B",8.0,"Vicuna-7B","EVA-G","2023/05/11",54.7],[210,"Mantis-8B-Fuyu",8.0,"Fuyu-8B","","2024/09/07",54.5],[211,"MiniGPT-4-v2",8.0,"Llama-2-13B","EVA-G","2023/10/27",54.1],[212,"VisualGLM",8.0,"ChatGLM 6B","EVA-CLIP","2023/05/17",53.4],[213,"IDEFICS-9B-Instruct",9.0,"Llama-7B","CLIP ViT-H/14","2023/07/25",51.6],[214,"OpenFlamingo v2",9.0,"MPT 7B","CLIP ViT-L/14","2023/06/28",45.7],[215,"Chameleon-7B",7.0,"","","2024/07/29",44.6],[216,"MiniGPT-4-v1-7B",8.0,"Vicuna-7B","EVA-G","2023/04/20",39.0],[217,"Kosmos2",1.7,"","","2024/10/19",33.1],[218,"moonshot-v1-8k",null,"","","2025/03/03",1.3]],"metadata":null},"headers":["1","2","3"],"row_count":[1,"dynamic"],"col_count":[3,"dynamic"],"datatype":["number","html","number","html","html","str","number"],"type":"pandas","latex_delimiters":[{"left":"$$","right":"$$","display":true}],"show_label":true,"height":500,"min_width":160,"interactive":false,"visible":true,"elem_classes":[],"wrap":true,"line_breaks":true,"column_widths":[],"name":"dataframe","_selectable":false},"skip_api":false,"component_class_id":"6a51bb3357f2e94c40fb8d4fbe06aa8e","key":null,"api_info":{"properties":{"headers":{"items":{"type":"string"},"title":"Headers","type":"array"},"data":{"items":{"items":{},"type":"array"},"title":"Data","type":"array"},"metadata":{"anyOf":[{"additionalProperties":{"anyOf":[{"items":{},"type":"array"},{"type":"null"}]},"type":"object"},{"type":"null"}],"default":null,"title":"Metadata"}},"required":["headers","data"],"title":"DataframeData","type":"object"},"example_inputs":{"headers":["a","b"],"data":[["foo","bar"]]}},{"id":188,"type":"textbox","props":{"value":"ScienceQA_VAL","lines":1,"max_lines":20,"label":"ScienceQA_VAL","show_label":true,"container":true,"min_width":160,"visible":false,"autofocus":false,"autoscroll":true,"elem_classes":[],"type":"text","rtl":false,"show_copy_button":false,"name":"textbox","_selectable":false},"skip_api":false,"component_class_id":"d0491bb0fbd427bdb2a4549c4d1ac869","key":null,"api_info":{"type":"string"},"example_inputs":"Hello!!"},{"id":189,"type":"form","props":{"scale":0,"min_width":0,"name":"form"},"skip_api":true,"component_class_id":"43cda85c6ff7a5dd8f83d29496b014ee","key":null},{"id":190,"type":"form","props":{"scale":0,"min_width":0,"name":"form"},"skip_api":true,"component_class_id":"43cda85c6ff7a5dd8f83d29496b014ee","key":null},{"id":191,"type":"tabitem","props":{"label":"📊 ScienceQA_TEST Leaderboard","visible":true,"interactive":true,"id":17,"elem_id":"ScienceQA_TEST","name":"tab"},"skip_api":true,"component_class_id":"18f46968e2b273dc5dbda0fe78433d7e","key":null},{"id":192,"type":"markdown","props":{"value":"## ScienceQA Evaluation Results\n\n- We benchmark the **image** subset of ScienceQA validation and test set, and report the Top-1 accuracy. \n- During evaluation, we use `GPT-3.5-Turbo-0613` as the choice extractor for all VLMs if the choice can not be extracted via heuristic matching. **Zero-shot** inference is adopted. ","show_label":true,"rtl":false,"latex_delimiters":[{"left":"$$","right":"$$","display":true}],"visible":true,"elem_classes":[],"sanitize_html":true,"line_breaks":false,"header_links":false,"show_copy_button":false,"name":"markdown","_selectable":false},"skip_api":false,"component_class_id":"0f35515b9a3362b42bb6721c836157a0","key":null,"api_info":{"type":"string"},"example_inputs":"# Hello!"},{"id":193,"type":"checkboxgroup","props":{"choices":[["Overall","Overall"],["Adaptations","Adaptations"],["Ancient Egypt and Kush","Ancient Egypt and Kush"],["Ancient Mesopotamia","Ancient Mesopotamia"],["Animals","Animals"],["Astronomy","Astronomy"],["Atoms and molecules","Atoms and molecules"],["Basic economic principles","Basic economic principles"],["Cells","Cells"],["Chemical reactions","Chemical reactions"],["Cities","Cities"],["Classification","Classification"],["Classification and scientific names","Classification and scientific names"],["Climate change","Climate change"],["Colonial America","Colonial America"],["Context clues","Context clues"],["Descriptive details","Descriptive details"],["Designing experiments","Designing experiments"],["Domain-specific vocabulary","Domain-specific vocabulary"],["Early 19th century American history","Early 19th century American history"],["Earth events","Earth events"],["Ecological interactions","Ecological interactions"],["Ecosystems","Ecosystems"],["Engineering practices","Engineering practices"],["English colonies in North America","English colonies in North America"],["Force and motion","Force and motion"],["Fossils","Fossils"],["Genes to traits","Genes to traits"],["Geography","Geography"],["Government","Government"],["Greece","Greece"],["Independent reading comprehension","Independent reading comprehension"],["Informational texts: level 1","Informational texts: level 1"],["Kinetic and potential energy","Kinetic and potential energy"],["Magnets","Magnets"],["Maps","Maps"],["Materials","Materials"],["Medieval Asia","Medieval Asia"],["Oceania: geography","Oceania: geography"],["Oceans and continents","Oceans and continents"],["Oceans and continents\t","Oceans and continents\t"],["Particle motion and energy","Particle motion and energy"],["Persuasive strategies","Persuasive strategies"],["Photosynthesis","Photosynthesis"],["Physical Geography","Physical Geography"],["Plant reproduction","Plant reproduction"],["Plants","Plants"],["Plate tectonics","Plate tectonics"],["Read-alone texts","Read-alone texts"],["Rocks and minerals","Rocks and minerals"],["Scientific names","Scientific names"],["Solutions","Solutions"],["State capitals","State capitals"],["States","States"],["States of matter","States of matter"],["The American Revolution","The American Revolution"],["The Americas: geography","The Americas: geography"],["The Antebellum period","The Antebellum period"],["The Civil War and Reconstruction","The Civil War and Reconstruction"],["Thermal energy","Thermal energy"],["Topographic maps","Topographic maps"],["Velocity, acceleration, and forces","Velocity, acceleration, and forces"],["Visual elements","Visual elements"],["Water cycle","Water cycle"],["Weather and climate","Weather and climate"],["World religions","World religions"]],"value":["Overall"],"type":"value","label":"ScienceQA_TEST CheckBoxes","show_label":true,"container":true,"min_width":160,"interactive":true,"visible":true,"elem_classes":[],"name":"checkboxgroup","_selectable":false},"skip_api":false,"component_class_id":"0635a5d3bf87369f1c2c1c69f8a3d0cc","key":null,"api_info":{"items":{"enum":["Overall","Adaptations","Ancient Egypt and Kush","Ancient Mesopotamia","Animals","Astronomy","Atoms and molecules","Basic economic principles","Cells","Chemical reactions","Cities","Classification","Classification and scientific names","Climate change","Colonial America","Context clues","Descriptive details","Designing experiments","Domain-specific vocabulary","Early 19th century American history","Earth events","Ecological interactions","Ecosystems","Engineering practices","English colonies in North America","Force and motion","Fossils","Genes to traits","Geography","Government","Greece","Independent reading comprehension","Informational texts: level 1","Kinetic and potential energy","Magnets","Maps","Materials","Medieval Asia","Oceania: geography","Oceans and continents","Oceans and continents\t","Particle motion and energy","Persuasive strategies","Photosynthesis","Physical Geography","Plant reproduction","Plants","Plate tectonics","Read-alone texts","Rocks and minerals","Scientific names","Solutions","State capitals","States","States of matter","The American Revolution","The Americas: geography","The Antebellum period","The Civil War and Reconstruction","Thermal energy","Topographic maps","Velocity, acceleration, and forces","Visual elements","Water cycle","Weather and climate","World religions"],"type":"string"},"title":"Checkbox Group","type":"array"},"example_inputs":["Overall"]},{"id":194,"type":"row","props":{"variant":"default","visible":true,"equal_height":true,"show_progress":false,"name":"row"},"skip_api":true,"component_class_id":"b5cf3d15e2293fb5ccc071d7b8d69f64","key":null},{"id":195,"type":"textbox","props":{"value":"Input the Model Name (fuzzy, case insensitive)","lines":1,"max_lines":20,"label":"Model Name","show_label":true,"container":true,"min_width":160,"interactive":true,"visible":true,"autofocus":false,"autoscroll":true,"elem_classes":[],"type":"text","rtl":false,"show_copy_button":false,"name":"textbox","_selectable":false},"skip_api":false,"component_class_id":"d0491bb0fbd427bdb2a4549c4d1ac869","key":null,"api_info":{"type":"string"},"example_inputs":"Hello!!"},{"id":196,"type":"checkboxgroup","props":{"choices":[["<4B","<4B"],["4B-10B","4B-10B"],["10B-20B","10B-20B"],["20B-40B","20B-40B"],[">40B",">40B"],["Unknown","Unknown"]],"value":["<4B","4B-10B","10B-20B","20B-40B",">40B","Unknown"],"type":"value","label":"Model Size","show_label":true,"container":true,"min_width":160,"interactive":true,"visible":true,"elem_classes":[],"name":"checkboxgroup","_selectable":false},"skip_api":false,"component_class_id":"0635a5d3bf87369f1c2c1c69f8a3d0cc","key":null,"api_info":{"items":{"enum":["<4B","4B-10B","10B-20B","20B-40B",">40B","Unknown"],"type":"string"},"title":"Checkbox Group","type":"array"},"example_inputs":["<4B"]},{"id":197,"type":"checkboxgroup","props":{"choices":[["API","API"],["OpenSource","OpenSource"]],"value":["API","OpenSource"],"type":"value","label":"Model Type","show_label":true,"container":true,"min_width":160,"interactive":true,"visible":true,"elem_classes":[],"name":"checkboxgroup","_selectable":false},"skip_api":false,"component_class_id":"0635a5d3bf87369f1c2c1c69f8a3d0cc","key":null,"api_info":{"items":{"enum":["API","OpenSource"],"type":"string"},"title":"Checkbox Group","type":"array"},"example_inputs":["API"]},{"id":198,"type":"form","props":{"scale":3,"min_width":480,"name":"form"},"skip_api":true,"component_class_id":"43cda85c6ff7a5dd8f83d29496b014ee","key":null},{"id":199,"type":"dataframe","props":{"value":{"headers":["Rank","Method","Param (B)","Language Model","Vision Model","Eval Date","Overall"],"data":[[1,"InternVL2.5-78B-MPO",78.0,"Qwen-2.5-72B","InternViT-6B-v2.5","2024/12/29",99.5],[2,"InternVL3-38B",38.4,"Qwen2.5-32B","InternViT-6B-v2.5","2025/04/14",99.3],[3,"InternVL2.5-38B-MPO",38.0,"Qwen-2.5-32B","InternViT-6B-v2.5","2024/12/28",99.1],[4,"Taiyi",null,"","","2024/12/11",98.9],[5,"MiniCPM-o-2.6",8.67,"Qwen2.5-7B","SigLIP-400M","2025/01/21",98.8],[6,"MUG-U-7B",7.0,"","","2025/03/19",98.8],[7,"InternVL2-Llama3-76B",76.0,"Llama-3-70B-Instruct","InternViT-6B","2024/07/19",98.8],[8,"InternVL3-78B",78.4,"Qwen2.5-72B","InternViT-6B-v2.5","2025/04/14",98.7],[9,"InternVL2.5-26B-MPO",26.0,"InternLM2.5-20B","InternViT-6B-v2.5","2024/12/28",98.7],[10,"InternVL3-14B",15.1,"Qwen2.5-14B","InternViT-300M-v2.5","2025/04/14",98.6],[11,"InternVL2-40B",40.0,"Nous-Hermes-2-Yi-34B","InternViT-6B","2024/07/11",98.5],[12,"VARCO-VISION-14B",15.2,"Qwen2.5-14B","SigLIP-400M","2025/01/02",98.5],[13,"InternVL2.5-8B-MPO",8.0,"InternLM2.5-7B","InternViT-300M-v2.5","2024/12/28",98.4],[14,"BailingMM-Pro-0120",81.0,"Bailing-80B","SigLIP-400M","2025/01/25",98.2],[15,"InternVL3-9B",9.14,"InternLM3-8B","InternViT-300M-v2.5","2025/04/14",98.1],[16,"InternVL3-8B",7.94,"Qwen2.5-7B","InternViT-300M-v2.5","2025/04/14",97.9],[17,"Aria",25.3,"Aria-MoE","SigLIP-400M","2024/12/05",97.7],[18,"InternVL2.5-4B-MPO",4.0,"Qwen-2.5-3B","InternViT-300M-v2.5","2024/12/28",97.6],[19,"GLM-4v",null,"","","2024/05/20",97.4],[20,"InternVL2-26B",26.0,"InternLM2-20B","InternViT-6B","2024/07/11",97.4],[21,"Phi-4-MultiModal",5.57,"Phi-4-Mini","SigLIP-400M","2025/03/13",97.3],[22,"InternVL2-8B-MPO",8.0,"InternLM2.5-7B","InternViT-300M","2024/11/25",97.3],[23,"GLM-4v-Plus-20250111",null,"","","2025/01/25",97.2],[24,"GLM-4v-Plus",null,"","","2024/12/11",97.1],[25,"InternVL2-8B",8.0,"InternLM2.5-7B","InternViT-300M","2024/07/11",97.1],[26,"BailingMM-Lite-1203",21.0,"Bailing-20B","SigLIP-400M","2024/12/08",96.9],[27,"MiniCPM-V-2.6",8.0,"Qwen2-7B","SigLIP-400M","2024/08/08",96.7],[28,"InternLM-XComposer2",7.0,"InternLM2-7B","CLIP ViT-L/14","2024/01/26",96.7],[29,"GLM-4v-9B",9.0,"GLM-4-9B","EVA-02-5B","2024/06/14",96.7],[30,"abab7-preview",null,"","","2024/12/11",96.7],[31,"InternLM-XComposer2.5",8.0,"InternLM2-7B","CLIP ViT-L/14","2024/07/11",96.6],[32,"HunYuan-Standard-Vision",null,"","","2025/01/15",96.4],[33,"InternLM-XComposer2-4KHD",7.0,"InternLM2-7B","CLIP ViT-L/14","2024/06/09",96.3],[34,"InternVL2-4B",4.0,"Phi-3","InternViT-300M","2024/07/11",96.3],[35,"InternVL2.5-2B-MPO",2.0,"InternLM2.5-1.8B","InternViT-300M-v2.5","2024/12/28",96.0],[36,"CongRong",null,"","","2024/06/26",95.9],[37,"VITA-1.5",8.3,"Qwen2-7B","InternViT-300M","2025/01/01",95.8],[38,"InternVL3-2B",2.09,"Qwen2.5-1.5B","InternViT-300M-v2.5","2025/04/14",95.8],[39,"Ovis2-34B",34.9,"Qwen2.5-32B","AIMv2-1B","2025/02/18",95.7],[40,"SAIL-VL-2B",2.1,"Qwen2.5-1.5B","InternViT-300M","2024/12/25",95.5],[41,"LLaVA-OneVision-7B",8.0,"Qwen2-7B","SigLIP-400M","2024/09/16",95.4],[42,"Step-1o",null,"","","2025/01/13",95.3],[43,"POINTS-Yi-1.5-9B",9.5,"Yi-1.5-9B","CLIP ViT-L/14","2024/10/11",95.3],[44,"Kimi-VL-A3B-Instruct",16.4,"Moonlight-16B-A3B","MoonViT","2025/04/14",95.3],[45,"Ross-Qwen2-7B",8.2,"Qwen2-7B","CLIP ViT-L/14","2025/01/17",95.2],[46,"Ovis2-16B",16.2,"Qwen2.5-14B","AIMv2 Huge","2025/02/18",95.2],[47,"Ovis2-8B",8.94,"Qwen2.5-7B","AIMv2 Huge","2025/02/18",95.1],[48,"Aquila-VL-2B",2.2,"Qwen-2.5-1.5B","SigLIP-400M","2024/10/24",95.1],[49,"POINTS1.5-Qwen2.5-7B",8.3,"Qwen-2.5-7B","NaViT","2024/12/06",95.0],[50,"POINTS-Qwen2.5-7B",8.3,"Qwen-2.5-7B","CLIP ViT-L/14","2024/10/19",94.8],[51,"Ovis1.6-Gemma2-27B",28.9,"Gemma2-27B","SigLIP-400M","2024/11/29",94.7],[52,"BlueLM-V-3B",3.0,"BlueLM-3B","SigLIP-400M","2024/10/30",94.5],[53,"PaliGemma-3B-mix-448",3.0,"Gemma-2B","SigLIP-400M","2024/05/17",94.3],[54,"Step-1.5V",null,"Step-1.5","stepencoder","2024/10/11",94.3],[55,"granite-vision-3.2-2b",2.98,"granite-3.1-2b-instruct","SigLip","2025/06/20",94.3],[56,"MMAlaya2",26.0,"InternLM2-20B","InternViT-6B","2024/08/27",94.1],[57,"InternVL2-2B",2.0,"InternLM2-1.8B","InternViT-300M","2024/07/11",94.1],[58,"Ovis2-4B",4.62,"Qwen2.5-3B","AIMv2 Huge","2025/02/18",94.0],[59,"MiniMonkey",2.2,"InternLM2-1.8B","InternViT-300M","2024/09/26",93.9],[60,"InternVL-Chat-V1.5",26.0,"InternLM2-20B","InternViT-6B","2024/04/17",93.9],[61,"Ovis1.5-Gemma2-9B",11.4,"Gemma2-9B-It","SigLIP-400M","2024/08/04",93.8],[62,"NVLM-D-72B",79.4,"Qwen2-72B","InternViT-6B","2024/10/19",93.7],[63,"Ovis1.6-Gemma2-9B",10.2,"Gemma2-9B-It","SigLIP-400M","2024/09/19",93.4],[64,"InternVL2.5-1B-MPO",1.0,"Qwen-2.5-0.5B","InternViT-300M-v2.5","2024/12/28",93.1],[65,"GPT-4.1-20250414",null,"","","2025/04/16",92.8],[66,"Mini-InternVL-Chat-4B-V1.5",4.0,"Phi-3","InternViT-300M","2024/06/10",92.6],[67,"InternLM-XComposer2-1.8B",2.0,"InternLM2-1.8B","CLIP ViT-L/14","2024/06/09",92.2],[68,"H2OVL-2B",2.2,"H2O-DANUBE2-1.8B","InternViT-300M","2024/10/31",92.1],[69,"InternVL3-1B",0.94,"Qwen2.5-0.5B","InternViT-300M-v2.5","2025/04/14",91.7],[70,"InternVL2-8B-MPO-CoT",8.0,"InternLM2.5-7B","InternViT-300M","2024/11/25",91.5],[71,"Qwen-VL-Max-0809",72.0,"Qwen2-72B","QwenViT","2024/09/12",91.4],[72,"Qwen2.5-VL-72B",73.4,"Qwen2.5-72B","QwenViT","2025/02/02",91.4],[73,"Idefics3-8B-Llama3",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/08/27",91.3],[74,"Qwen2-VL-72B",73.4,"Qwen2-72B","QwenViT","2024/10/28",91.2],[75,"Ovis2-2B",2.46,"Qwen2.5-1.5B","AIMv2 Large","2025/02/18",91.2],[76,"Claude3.7-Sonnet",null,"","","2025/02/27",90.9],[77,"granite-vision-3.3-2b",2.98,"granite-3.1-2b-instruct","SigLIP2-400M","2025/06/20",90.7],[78,"GPT-4o (0513, detail-high)",null,"","","2024/05/31",90.7],[79,"RBDash-v1.5",79.0,"Qwen2-72B","CLIP ViT-L/14
InternViT-6B","2024/11/17",90.6],[80,"grok-2-vision-1212",null,"","","2025/03/03",90.4],[81,"CogVLM2-19B-Chat",19.0,"Llama-3-8B-Instruct","EVA2-CLIP-E","2024/05/31",90.2],[82,"LLaVA-OneVision-72B",73.0,"Qwen2-72B","SigLIP-400M","2024/09/19",90.2],[83,"GPT-4o (0806, detail-high)",null,"","","2024/08/08",90.1],[84,"GPT-4o (0513, detail-low)",null,"","","2024/05/15",90.1],[85,"Phi-3-Vision",4.2,"Phi-3","CLIP ViT-L/14","2024/05/31",90.0],[86,"InternLM-XComposer",8.0,"InternLM-7B","EVA-G","2023/09/26",89.8],[87,"OmChat-v2.0-13B",13.0,"Qwen2-7B","InternViT-6B","2024/08/22",89.6],[88,"SmolVLM2",2.25,"SmolLM2-1.7M","SigLIP-400M","2025/03/13",89.6],[89,"MiniCPM-Llama3-V2.5",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/05/27",89.2],[90,"Qwen2.5-VL-7B",8.29,"Qwen2.5-7B","QwenViT","2025/02/02",89.0],[91,"Claude3.5-Sonnet",null,"","","2024/06/24",88.9],[92,"Phi-3.5-Vision",4.0,"Phi-3.5","CLIP ViT-L/14","2024/08/28",88.9],[93,"Molmo-7B-O",8.0,"Qwen2-7B","CLIP ViT-L/14","2024/10/20",88.8],[94,"Ovis1.5-Llama3-8B",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/07/29",88.8],[95,"IDEFICS2-8B",8.0,"Mistral-7B","SigLIP-400M","2024/04/26",88.7],[96,"Yi-Vision",null,"","","2024/08/03",88.5],[97,"XGen-MM-Instruct-Interleave-v1.5",4.4,"Phi-3","SigLIP-400M","2024/09/06",88.3],[98,"Eagle-X5-34B-Chat",36.8,"Yi-34B","Clip-448
ConvNeXT-1024
SAM-1024
DET-1024
Pix2Struct-1024","2024/11/29",88.1],[99,"Emu3_chat",8.49,"","","2025/01/26",87.9],[100,"InternVL2-1B",1.0,"Qwen2-0.5B","InternViT-300M","2024/07/11",87.9],[101,"Gemma3-27B",27.4,"Gemma3-27B","SigLIP-400M","2025/03/19",87.7],[102,"Ovis1.6-Llama3.2-3B",4.1,"Llama-3.2-3B","SigLIP-400M","2024/10/24",87.6],[103,"MolmoE-1B",7.2,"OLMoE-1B-7B-0924","CLIP ViT-L/14","2024/10/21",87.5],[104,"360VL-70B",70.0,"Llama-3-70B-Instruct","CLIP ViT-L/14","2024/05/25",87.4],[105,"AKI-4B",4.33,"Phi-3.5","SigLIP-400M","2025/03/25",87.3],[106,"Pixtral-12B",13.0,"Nemo-12B","ViT-400M","2024/09/16",87.2],[107,"Llama-3.2-90B-Vision-Instruct",88.6,"Llama-3.1-70B","","2024/10/19",87.1],[108,"XVERSE-V-13B",13.0,"XVERSE-13B","CLIP ViT-L/14","2024/05/10",86.8],[109,"XinYuan-VL-2B-Instruct",2.0,"Qwen2-1.5B","QwenViT","2024/09/27",86.7],[110,"LLaVA-OneVision-7B (SI)",8.0,"Qwen2-7B","SigLIP-400M","2024/09/17",86.6],[111,"Step-1.5V-mini",null,"","","2024/12/11",86.0],[112,"Qwen-VL-Plus-0809",null,"","","2024/09/17",85.8],[113,"Gemini-1.5-Pro",null,"","","2024/06/10",85.7],[114,"Cambrian-34B",34.0,"Nous-Hermes-2-Yi-34B","CLIP ViT-L/14","2024/07/18",85.6],[115,"RekaFlash",null,"","","2024/05/07",85.5],[116,"XGen-MM-Instruct-DPO-v1.5",4.4,"Phi-3","SigLIP-400M","2024/09/06",85.5],[117,"Qwen2-VL-7B",8.0,"Qwen2-7B","QwenViT","2024/09/12",85.5],[118,"VILA1.5-40B",40.0,"Yi-34B","InternViT-6B","2024/08/25",85.4],[119,"GPT-4o-mini (0718, detail-high)",null,"","","2024/07/20",85.4],[120,"GPT-4v (0409, detail-high)",null,"","","2024/05/15",84.8],[121,"Mini-InternVL-Chat-2B-V1.5",2.0,"InternLM2-1.8B","InternViT-300M","2024/06/10",84.8],[122,"GPT-4.1-mini-20250414",null,"","","2025/04/16",84.7],[123,"SmolVLM-Instruct",2.3,"SmolLM2-1.7B","SigLIP-400M","2025/01/27",84.5],[124,"Llama-3.2-11B-Vision-Instruct",11.0,"Llama-3.1-8B","","2024/10/07",83.9],[125,"Gemma3-12B",12.2,"Gemma3-12B","SigLIP-400M","2025/03/19",83.9],[126,"Gemini-1.5-Flash",null,"","","2024/09/16",83.3],[127,"WeMM",7.0,"InternLM2-7B","SigLIP-400M","2024/06/09",83.3],[128,"Janus-Pro-7B",7.42,"DeepSeek-7B","SigLIP-400M","2025/02/02",83.2],[129,"Llama-3-MixSense-v1.1",8.0,"Llama-3-8B-Instruct","Florence-2-Large-FT","2024/08/21",83.1],[130,"SmolVLM-Instruct-DPO",2.3,"SmolLM2-1.7B","SigLIP-400M","2025/01/27",82.9],[131,"Monkey-Chat",9.8,"Qwen-7B","ViT-BigHuge","2024/01/16",82.4],[132,"Ovis2-1B",1.27,"Qwen2.5-0.5B","AIMv2 Large","2025/02/18",82.3],[133,"ShareCaptioner",8.0,"InternLM-7B","EVA-G","2024/01/03",82.3],[134,"GPT-4v (1106, detail-low)",null,"","","2023/12/23",82.1],[135,"LLaVA-Next-Yi-34B",34.8,"Yi-34B","CLIP ViT-L/14","2024/03/25",82.0],[136,"Mantis-8B-Idefics2",8.0,"Mistral-7B","SigLIP-400M","2024/08/08",81.8],[137,"Gemini-1.0-Pro",null,"","","2023/12/23",81.4],[138,"Qwen2.5-VL-3B",3.75,"Qwen2.5-3B","QwenViT","2025/02/02",81.4],[139,"OmniLMM-12B",12.0,"Zephyr-7B-β","EVA-02-5B","2024/02/07",81.1],[140,"Cambrian-8B",8.0,"Vicuna-v1.5-7B","CLIP ViT-L/14","2024/07/11",81.0],[141,"DeepSeek-VL-7B",7.3,"DeekSeek-7B","SAM-B
SigLIP-L","2024/03/21",80.9],[142,"MiniCPM-V-2",2.8,"MiniCPM-2.4B","SigLIP-400M","2024/04/15",80.7],[143,"LLaVA-Next-Qwen-32B",33.0,"Qwen-1.5-32B","SigLIP-400M","2024/08/08",80.0],[144,"Qwen-VL-Max",null,"QwenLM","","2024/02/02",80.0],[145,"SmolVLM-500M",0.51,"SmolLM2-360M","ViT-93M","2025/01/27",80.0],[146,"Cambrian-13B",13.0,"Vicuna-v1.5-13B","CLIP ViT-L/14","2024/07/29",79.3],[147,"VILA1.5-13B",13.0,"Vicuna-v1.5-13B","SigLIP-400M","2024/08/25",79.1],[148,"Bunny-Llama3-8B",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/07/18",79.1],[149,"Qwen2-VL-2B",2.0,"Qwen2-1.5B","QwenViT","2024/09/12",78.7],[150,"Slime-8B",8.0,"Llama-3-8B-Instruct","CLIP ViT-L/14","2024/09/14",78.0],[151,"GPT-4.1-nano-20250414",null,"","","2025/04/16",77.5],[152,"Gemma3-4B",4.3,"Gemma3-4B","SigLIP-400M","2025/03/19",77.1],[153,"MiniCPM-V",3.0,"MiniCPM-2.4B","SigLIP-400M","2024/02/07",77.0],[154,"SmolVLM2-500M",0.51,"SmolLM2-360M","ViT-93M","2025/03/13",76.5],[155,"Yi-VL-34B",34.6,"Yi-34B","CLIP ViT-H/14","2024/01/25",75.5],[156,"Mantis-8B-siglip-llama3",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/08/08",75.5],[157,"Slime-7B",7.0,"Vicuna-v1.5-7B","CLIP ViT-L/14","2024/09/14",75.4],[158,"Slime-13B",13.0,"Vicuna-v1.5-13B","CLIP ViT-L/14","2024/09/14",75.3],[159,"Janus-1.3B",2.1,"DeepSeek-1B","SigLIP-400M","2024/10/24",75.1],[160,"Vintern-3B-beta",3.7,"Qwen-2.5-3B","InternViT-300M","2024/10/24",75.0],[161,"TransCore-M",13.4,"PCITransGPT-13B","CLIP ViT-L/14","2024/04/16",74.9],[162,"Falcon2-VLM-11B",11.4,"Falcon2-11B","CLIP ViT-L/14","2024/10/30",73.9],[163,"SmolVLM-256M",0.26,"SmolLM2-135M","ViT-93M","2025/01/27",73.8],[164,"LLaVA-InternLM2-20B (QLoRA)",20.2,"InternLM2-20B","CLIP ViT-L/14","2024/01/17",73.7],[165,"LLaVA-Next-Vicuna-13B",13.4,"Vicuna-v1.5-13B","CLIP ViT-L/14","2024/03/25",73.7],[166,"LLaVA-InternLM2-7B (QLoRA)",8.1,"InternLM2-7B","CLIP ViT-L/14","2024/01/17",73.7],[167,"Mantis-8B-clip-llama3",8.0,"Llama-3-8B-Instruct","CLIP ViT-L/14","2024/08/08",73.5],[168,"RekaEdge",null,"","","2024/05/31",73.5],[169,"Qwen-VL-Plus",null,"QwenLM","","2024/01/10",73.4],[170,"LLaVA-Next-Interleave-7B",8.0,"Qwen-1.5-7B","SigLIP-400M","2024/08/08",73.2],[171,"Llama-3-VILA1.5-8B",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/08/25",73.2],[172,"LLaVA-Next-Llama3",8.0,"Llama-3-8B-Instruct","CLIP ViT-L/14","2024/07/29",73.1],[173,"LLaVA-Next-Mistral-7B",7.6,"Mistral-7B","CLIP ViT-L/14","2024/03/25",73.0],[174,"ShareGPT4V-13B",13.4,"Vicuna-v1.5-13B","CLIP ViT-L/14","2023/12/08",72.6],[175,"LLaVA-v1.5-13B",13.4,"Vicuna-v1.5-13B","CLIP ViT-L/14","2023/10/05",72.6],[176,"Yi-VL-6B",6.6,"Yi-6B","CLIP ViT-H/14","2024/01/25",72.6],[177,"LLaVA-LLaMA-3-8B",8.0,"Llama-3-8B-Instruct","CLIP ViT-L/14","2024/05/07",72.2],[178,"Monkey",9.8,"Qwen-7B","ViT-BigHuge","2024/01/11",72.1],[179,"LLaVA-Next-Interleave-7B-DPO",8.0,"Qwen-1.5-7B","SigLIP-400M","2024/07/29",72.0],[180,"Eagle-X5-13B",15.0,"Vicuna-v1.5-13B","Clip-448
ConvNeXT-1024
SAM-1024
DET-1024
Pix2Struct-1024","2024/09/26",71.8],[181,"Eagle-X5-7B",9.0,"Vicuna-v1.5-7B","Clip-448
ConvNeXT-1024
SAM-1024
DET-1024
Pix2Struct-1024","2024/09/26",71.2],[182,"LLaVA-Next-Vicuna-7B",7.1,"Vicuna-v1.5-7B","CLIP ViT-L/14","2024/03/25",70.3],[183,"LLaVA-v1.5-13B (QLoRA)",13.4,"Vicuna-v1.5-13B","CLIP ViT-L/14","2023/12/28",70.3],[184,"Parrot-7B",8.0,"Qwen2-7B","CLIP ViT-L/14","2024/08/22",70.2],[185,"H2OVL-800M",0.83,"H2O-DANUBE3-500M","InternViT-300M","2024/10/31",69.8],[186,"ShareGPT4V-7B",7.2,"Vicuna-v1.5-7B","CLIP ViT-L/14","2023/12/08",69.5],[187,"mPLUG-Owl2",8.2,"Llama-2-7B","CLIP ViT-L/14","2023/11/10",69.5],[188,"VILA1.5-3B",3.0,"Sheared-LLaMA-2.7B","SigLIP-400M","2024/08/25",69.2],[189,"LLaVA-v1.5-7B",7.2,"Vicuna-v1.5-7B","CLIP ViT-L/14","2023/10/05",69.2],[190,"Qwen-VL-Chat",9.6,"Qwen-7B","ViT-G/16","2023/08/24",68.8],[191,"LLaVA-v1.5-7B (QLoRA)",7.2,"Vicuna-v1.5-7B","CLIP ViT-L/14","2023/12/28",68.7],[192,"DeepSeek-VL-1.3B",2.0,"DeekSeek-1B","SAM-B
SigLIP-L","2024/03/21",68.4],[193,"LLaVA-InternLM-7B (QLoRA)",7.6,"InternLM-7B","CLIP ViT-L/14","2023/12/28",68.4],[194,"Emu2_chat",37.0,"Llama-33B","EVA-02-CLIP-E-plus","2024/01/17",68.2],[195,"LLaVA-OneVision-0.5B",1.0,"Qwen2-0.5B","SigLIP-400M","2024/09/16",67.5],[196,"LLaVA-OneVision-0.5B (SI)",1.0,"Qwen2-0.5B","SigLIP-400M","2024/09/17",67.5],[197,"SmolVLM-Synthetic",2.3,"SmolLM2-1.7B","SigLIP-400M","2025/01/27",66.4],[198,"CogVLM-17B-Chat",17.0,"Vicuna-v1.5-7B","EVA2-CLIP-E","2024/01/03",66.2],[199,"PandaGPT-13B",14.0,"Vicuna-13B","ImageBind ViT-H/14","2023/05/25",63.2],[200,"Moondream1",1.9,"SigLIP-400M","Phi-1.5","2024/09/26",62.1],[201,"IDEFICS-80B-Instruct",80.0,"Llama-65B","CLIP ViT-H/14","2023/07/25",61.8],[202,"LLaVA-v1-7B",7.2,"Llama-7B","CLIP ViT-L/14","2023/04/17",61.8],[203,"abab6.5s",null,"","","2024/12/11",61.4],[204,"Qwen-VL",9.6,"Qwen-7B","ViT-G/16","2023/08/24",61.1],[205,"MMAlaya",7.8,"Alaya-7B-Chat","EVA-G","2024/01/29",60.9],[206,"SmolVLM2-256M",0.26,"SmolLM2-135M","ViT-93M","2025/03/13",58.8],[207,"Chameleon-30B",30.0,"","","2024/07/29",58.8],[208,"Molmo-7B-D",8.0,"Qwen2-7B","CLIP ViT-L/14","2024/10/12",58.1],[209,"Mantis-8B-Fuyu",8.0,"Fuyu-8B","","2024/09/07",56.8],[210,"VisualGLM",8.0,"ChatGLM 6B","EVA-CLIP","2023/05/17",56.1],[211,"MiniGPT-4-v2",8.0,"Llama-2-13B","EVA-G","2023/10/27",54.7],[212,"InstructBLIP-7B",8.0,"Vicuna-7B","EVA-G","2023/05/11",54.1],[213,"IDEFICS-9B-Instruct",9.0,"Llama-7B","CLIP ViT-H/14","2023/07/25",53.5],[214,"Chameleon-7B",7.0,"","","2024/07/29",46.8],[215,"OpenFlamingo v2",9.0,"MPT 7B","CLIP ViT-L/14","2023/06/28",44.8],[216,"MiniGPT-4-v1-7B",8.0,"Vicuna-7B","EVA-G","2023/04/20",39.6],[217,"Kosmos2",1.7,"","","2024/10/19",32.7],[218,"moonshot-v1-8k",null,"","","2025/03/03",1.2]],"metadata":null},"headers":["1","2","3"],"row_count":[1,"dynamic"],"col_count":[3,"dynamic"],"datatype":["number","html","number","html","html","str","number"],"type":"pandas","latex_delimiters":[{"left":"$$","right":"$$","display":true}],"show_label":true,"height":500,"min_width":160,"interactive":false,"visible":true,"elem_classes":[],"wrap":true,"line_breaks":true,"column_widths":[],"name":"dataframe","_selectable":false},"skip_api":false,"component_class_id":"6a51bb3357f2e94c40fb8d4fbe06aa8e","key":null,"api_info":{"properties":{"headers":{"items":{"type":"string"},"title":"Headers","type":"array"},"data":{"items":{"items":{},"type":"array"},"title":"Data","type":"array"},"metadata":{"anyOf":[{"additionalProperties":{"anyOf":[{"items":{},"type":"array"},{"type":"null"}]},"type":"object"},{"type":"null"}],"default":null,"title":"Metadata"}},"required":["headers","data"],"title":"DataframeData","type":"object"},"example_inputs":{"headers":["a","b"],"data":[["foo","bar"]]}},{"id":200,"type":"textbox","props":{"value":"ScienceQA_TEST","lines":1,"max_lines":20,"label":"ScienceQA_TEST","show_label":true,"container":true,"min_width":160,"visible":false,"autofocus":false,"autoscroll":true,"elem_classes":[],"type":"text","rtl":false,"show_copy_button":false,"name":"textbox","_selectable":false},"skip_api":false,"component_class_id":"d0491bb0fbd427bdb2a4549c4d1ac869","key":null,"api_info":{"type":"string"},"example_inputs":"Hello!!"},{"id":201,"type":"form","props":{"scale":0,"min_width":0,"name":"form"},"skip_api":true,"component_class_id":"43cda85c6ff7a5dd8f83d29496b014ee","key":null},{"id":202,"type":"form","props":{"scale":0,"min_width":0,"name":"form"},"skip_api":true,"component_class_id":"43cda85c6ff7a5dd8f83d29496b014ee","key":null},{"id":203,"type":"tabitem","props":{"label":"📊 OCRBench Leaderboard","visible":true,"interactive":true,"id":18,"elem_id":"OCRBench","name":"tab"},"skip_api":true,"component_class_id":"18f46968e2b273dc5dbda0fe78433d7e","key":null},{"id":204,"type":"markdown","props":{"value":"## OCRBench Evaluation Results\n\n- The evaluation of OCRBench is implemented by the official team: https://github.com/Yuliang-Liu/MultimodalOCR. \n- The performance of GPT4V might be underestimated: GPT4V rejects to answer 12 percent of the questions due to the policy of OpenAI. For those questions, the returned answer is \"Your input image may contain content that is not allowed by our safety system.\"","show_label":true,"rtl":false,"latex_delimiters":[{"left":"$$","right":"$$","display":true}],"visible":true,"elem_classes":[],"sanitize_html":true,"line_breaks":false,"header_links":false,"show_copy_button":false,"name":"markdown","_selectable":false},"skip_api":false,"component_class_id":"0f35515b9a3362b42bb6721c836157a0","key":null,"api_info":{"type":"string"},"example_inputs":"# Hello!"},{"id":205,"type":"checkboxgroup","props":{"choices":[["Final Score","Final Score"],["Text Recognition","Text Recognition"],["Scene Text-centric VQA","Scene Text-centric VQA"],["Doc-oriented VQA","Doc-oriented VQA"],["Key Information Extraction","Key Information Extraction"],["Handwritten Mathematical Expression Recognition","Handwritten Mathematical Expression Recognition"]],"value":["Final Score"],"type":"value","label":"OCRBench CheckBoxes","show_label":true,"container":true,"min_width":160,"interactive":true,"visible":true,"elem_classes":[],"name":"checkboxgroup","_selectable":false},"skip_api":false,"component_class_id":"0635a5d3bf87369f1c2c1c69f8a3d0cc","key":null,"api_info":{"items":{"enum":["Final Score","Text Recognition","Scene Text-centric VQA","Doc-oriented VQA","Key Information Extraction","Handwritten Mathematical Expression Recognition"],"type":"string"},"title":"Checkbox Group","type":"array"},"example_inputs":["Final Score"]},{"id":206,"type":"row","props":{"variant":"default","visible":true,"equal_height":true,"show_progress":false,"name":"row"},"skip_api":true,"component_class_id":"b5cf3d15e2293fb5ccc071d7b8d69f64","key":null},{"id":207,"type":"textbox","props":{"value":"Input the Model Name (fuzzy, case insensitive)","lines":1,"max_lines":20,"label":"Model Name","show_label":true,"container":true,"min_width":160,"interactive":true,"visible":true,"autofocus":false,"autoscroll":true,"elem_classes":[],"type":"text","rtl":false,"show_copy_button":false,"name":"textbox","_selectable":false},"skip_api":false,"component_class_id":"d0491bb0fbd427bdb2a4549c4d1ac869","key":null,"api_info":{"type":"string"},"example_inputs":"Hello!!"},{"id":208,"type":"checkboxgroup","props":{"choices":[["<4B","<4B"],["4B-10B","4B-10B"],["10B-20B","10B-20B"],["20B-40B","20B-40B"],[">40B",">40B"],["Unknown","Unknown"]],"value":["<4B","4B-10B","10B-20B","20B-40B",">40B","Unknown"],"type":"value","label":"Model Size","show_label":true,"container":true,"min_width":160,"interactive":true,"visible":true,"elem_classes":[],"name":"checkboxgroup","_selectable":false},"skip_api":false,"component_class_id":"0635a5d3bf87369f1c2c1c69f8a3d0cc","key":null,"api_info":{"items":{"enum":["<4B","4B-10B","10B-20B","20B-40B",">40B","Unknown"],"type":"string"},"title":"Checkbox Group","type":"array"},"example_inputs":["<4B"]},{"id":209,"type":"checkboxgroup","props":{"choices":[["API","API"],["OpenSource","OpenSource"]],"value":["API","OpenSource"],"type":"value","label":"Model Type","show_label":true,"container":true,"min_width":160,"interactive":true,"visible":true,"elem_classes":[],"name":"checkboxgroup","_selectable":false},"skip_api":false,"component_class_id":"0635a5d3bf87369f1c2c1c69f8a3d0cc","key":null,"api_info":{"items":{"enum":["API","OpenSource"],"type":"string"},"title":"Checkbox Group","type":"array"},"example_inputs":["API"]},{"id":210,"type":"form","props":{"scale":3,"min_width":480,"name":"form"},"skip_api":true,"component_class_id":"43cda85c6ff7a5dd8f83d29496b014ee","key":null},{"id":211,"type":"dataframe","props":{"value":{"headers":["Rank","Method","Param (B)","Language Model","Vision Model","Eval Date","Final Score"],"data":[[1,"JT-VL-Chat-V3.0",null,"","","2025/08/04",950],[2,"CongRong-v2.0",null,"","","2025/05/20",927],[3,"Step-1o",null,"","","2025/01/13",926],[4,"MUG-U-7B",7.0,"","","2025/03/19",911],[5,"Ovis2-4B",4.62,"Qwen2.5-3B","AIMv2 Huge","2025/02/18",911],[6,"InternVL2.5-78B-MPO",78.0,"Qwen-2.5-72B","InternViT-6B-v2.5","2024/12/29",909],[7,"InternVL3-78B",78.4,"Qwen2.5-72B","InternViT-6B-v2.5","2025/04/14",908],[8,"GLM-4v-Plus-20250111",null,"","","2025/01/25",908],[9,"SAIL-VL-1.6-8B",8.33,"Qwen2.5-7B","AIMv2 Huge","2025/04/24",905],[10,"InternVL2.5-26B-MPO",26.0,"InternLM2.5-20B","InternViT-6B-v2.5","2024/12/28",905],[11,"SenseNova-V6-Pro",null,"","","2025/05/05",895],[12,"BailingMM-Pro-0120",81.0,"Bailing-80B","SigLIP-400M","2025/01/25",894],[13,"SenseNova",null,"","","2024/12/12",894],[14,"InternVL2.5-38B-MPO",38.0,"Qwen-2.5-32B","InternViT-6B-v2.5","2024/12/28",894],[15,"Ovis2-34B",34.9,"Qwen2.5-32B","AIMv2-1B","2025/02/18",894],[16,"Ovis2-8B",8.94,"Qwen2.5-7B","AIMv2 Huge","2025/02/18",891],[17,"SAIL-VL-1.5-2B",2.47,"Qwen2.5-1.5B","AIMv2 Huge","2025/04/23",891],[18,"TeleMM",null,"","","2024/12/31",891],[19,"Ovis2-1B",1.27,"Qwen2.5-0.5B","AIMv2 Large","2025/02/18",890],[20,"WeThink-Qwen2.5VL-7B",8.29,"Qwen2.5-7B","QwenViT","2025/05/26",890],[21,"MiniCPM-o-2.6",8.67,"Qwen2.5-7B","SigLIP-400M","2025/01/21",889],[22,"SAIL-VL-1.5-8B",7.95,"Qwen2.5-7B","InternViT-300B","2025/04/23",889],[23,"Qwen2.5-VL-7B",8.29,"Qwen2.5-7B","QwenViT","2025/02/02",888],[24,"Qwen2-VL-72B",73.4,"Qwen2-72B","QwenViT","2024/10/28",888],[25,"InternVL3-38B",38.4,"Qwen2.5-32B","InternViT-6B-v2.5","2025/04/14",886],[26,"Step-1.5V",null,"Step-1.5","stepencoder","2024/10/11",886],[27,"SenseNova-V6-5-Pro",null,"","","2025/09/03",885],[28,"InternVL3-8B",7.94,"Qwen2.5-7B","InternViT-300M-v2.5","2025/04/14",884],[29,"Qwen2.5-VL-72B",73.4,"Qwen2.5-72B","QwenViT","2025/02/02",882],[30,"InternVL2.5-8B-MPO",8.0,"InternLM2.5-7B","InternViT-300M-v2.5","2024/12/28",882],[31,"Qwen-VL-Max-0809",72.0,"Qwen2-72B","QwenViT","2024/09/12",881],[32,"Ovis-U1-3B",3.64,"Qwen3-1.7B","aimv2-large-path14-448","2025/07/20",881],[33,"InternVL3-9B",9.14,"InternLM3-8B","InternViT-300M-v2.5","2025/04/14",881],[34,"BlueLM-2.6-3B",3.0,"","","2025/09/17",881],[35,"Ovis2-16B",16.2,"Qwen2.5-14B","AIMv2 Huge","2025/02/18",879],[36,"InternVL2.5-4B-MPO",4.0,"Qwen-2.5-3B","InternViT-300M-v2.5","2024/12/28",879],[37,"InternVL3-14B",15.1,"Qwen2.5-14B","InternViT-300M-v2.5","2025/04/14",877],[38,"Ovis2-2B",2.46,"Qwen2.5-1.5B","AIMv2 Large","2025/02/18",873],[39,"Kimi-VL-A3B-Instruct",16.4,"Moonlight-16B-A3B","MoonViT","2025/04/14",871],[40,"VARCO-VISION-2.0-14B",15.2,"Qwen3-14B","SigLIP-400M","2025/08/04",869],[41,"KoreaDeep-VLM-OCR-32B",32.0,"","","2026/02/13",864],[42,"Gemini-2.0-Pro",null,"","","2025/02/27",863],[43,"Gemini-2.5-Pro",null,"","","2025/04/07",862],[44,"HunYuan-Standard-Vision",null,"","","2025/01/15",861],[45,"QTuneVL1.5-2B",2.09,"Qwen2.5-1.5B","InternViT-300M-v2.5","2025/08/11",858],[46,"valley2_dpo",8.88,"Qwen2.5-7B","SigLIP-400M","2025/05/30",858],[47,"Qwen2.5-VL-32B",33.5,"Qwen2.5-32B","QwenViT","2025/07/02",856],[48,"Ovis1.6-Gemma2-27B",28.9,"Gemma2-27B","SigLIP-400M","2024/11/29",856],[49,"InternVL2.5-26B",26.0,"InternLM2.5-20B","InternViT-6B-v2.5","2024/12/10",854],[50,"InternVL2.5-78B",78.0,"Qwen-2.5-72B","InternViT-6B-v2.5","2024/12/10",853],[51,"MiniCPM-V-2.6",8.0,"Qwen2-7B","SigLIP-400M","2024/08/08",852],[52,"BailingMM-Lite-1203",21.0,"Bailing-20B","SigLIP-400M","2024/12/08",852],[53,"Gemini-2.0-Flash",null,"","","2025/01/02",851],[54,"NVLM-D-72B",79.4,"Qwen2-72B","InternViT-6B","2024/10/19",849],[55,"Ristretto-3B",3.84,"Qwen2.5-3B","SigLIP-400M","2025/04/01",847],[56,"valley2",8.88,"Qwen2.5-7B","SigLIP-400M","2025/05/30",845],[57,"GPT-4.5",null,"","","2025/03/26",845],[58,"Phi-4-MultiModal",5.57,"Phi-4-Mini","SigLIP-400M","2025/03/13",844],[59,"Flash-VL-2B-Dynamic-ISS",2.53,"Qwen-2.5-1.5B-Instruct","SigLIP2-400M-512","2025/05/30",844],[60,"Qwen2-VL-7B",8.0,"Qwen2-7B","QwenViT","2024/09/12",843],[61,"GLM-4v-Plus",null,"","","2024/12/11",843],[62,"InternVL2.5-1B-MPO",1.0,"Qwen-2.5-0.5B","InternViT-300M-v2.5","2024/12/28",843],[63,"Qwen-VL-Plus-0809",null,"","","2024/09/17",843],[64,"Valley-Eagle",8.9,"Qwen2.5-7B","Qwen-ViT
SigLIP-400M","2024/12/29",842],[65,"InternVL2-Llama3-76B",76.0,"Llama-3-70B-Instruct","InternViT-6B","2024/07/19",842],[66,"InternVL2.5-38B",38.0,"Qwen-2.5-32B","InternViT-6B-v2.5","2024/12/10",841],[67,"GPT-4.1-mini-20250414",null,"","","2025/04/16",840],[68,"QTuneVL1.5-3B",3.75,"Qwen2.5-3B","QwenViT","2025/08/11",839],[69,"BlueLM-2.5-3B",2.9,"BlueLM-base-3B","Siglip2-So400M","2025/07/16",838],[70,"InternVL2.5-2B-MPO",2.0,"InternLM2.5-1.8B","InternViT-300M-v2.5","2024/12/28",838],[71,"R-4B",4.82,"Qwen3-4B","SigLip-400M","2025/08/11",837],[72,"bailingMM-mini",17.0,"bailing-mini","bailingMM-encoder-1B
InternViT-6B","2024/10/24",835],[73,"GPT-4.1-20250414",null,"","","2025/04/16",834],[74,"InternVL2-40B",40.0,"Nous-Hermes-2-Yi-34B","InternViT-6B","2024/07/11",833],[75,"POINTS1.5-Qwen2.5-7B",8.3,"Qwen-2.5-7B","NaViT","2024/12/06",832],[76,"DeepSeek-VL2-Small",16.1,"DeepSeekMoE-16B","SigLIP-400M","2025/01/01",832],[77,"SAIL-VL-2B",2.1,"Qwen2.5-1.5B","InternViT-300M","2024/12/25",831],[78,"InternVL3-2B",2.09,"Qwen2.5-1.5B","InternViT-300M-v2.5","2025/04/14",831],[79,"Ovis1.6-Gemma2-9B",10.2,"Gemma2-9B-It","SigLIP-400M","2024/09/19",830],[80,"InternVL2-8B-MPO-CoT",8.0,"InternLM2.5-7B","InternViT-300M","2024/11/25",830],[81,"MiMo-VL-7B",8.31,"Mimo-7B","Qwen2.5-ViT","2025/07/02",829],[82,"BlueLM-V-3B",3.0,"BlueLM-3B","SigLIP-400M","2024/10/30",829],[83,"GPT-5-mini-20250807",null,"","","2025/08/14",828],[84,"Qwen2.5-VL-3B",3.75,"Qwen2.5-3B","QwenViT","2025/02/02",828],[85,"CongRong",null,"","","2024/06/26",827],[86,"Kimi-VL-A3B-Thinking",16.4,"Moonlight-16B-A3B","MoonViT","2025/04/23",825],[87,"InternVL2-26B",26.0,"InternLM2-20B","InternViT-6B","2024/07/11",825],[88,"Kimi-VL-A3B-Thinking-2506",16.4,"Moonlight-16B-A3B","MoonViT","2025/07/02",823],[89,"Ola-7b",8.88,"Qwen2.5-7B","Oryx-ViT","2025/02/05",822],[90,"ChatGPT-4o-latest",null,"","","2025/04/07",822],[91,"InternVL2.5-8B",8.0,"InternLM2.5-7B","InternViT-300M-v2.5","2024/12/10",821],[92,"granite-vision-3.3-2b",2.98,"granite-3.1-2b-instruct","SigLIP2-400M","2025/06/20",820],[93,"Taiyi",null,"","","2024/12/11",820],[94,"InternVL2.5-4B",4.0,"Qwen-2.5-3B","InternViT-300M-v2.5","2024/12/10",820],[95,"VARCO-VISION-14B",15.2,"Qwen2.5-14B","SigLIP-400M","2025/01/02",815],[96,"GPT-4o (0513, detail-high)",null,"","","2024/05/31",815],[97,"GLM-4v",null,"","","2024/05/20",814],[98,"DeepSeek-VL2",27.5,"DeepSeekMoE-27B","SigLIP-400M","2025/01/01",809],[99,"VARCO-VISION-2.0-1.7B",2.12,"Qwen3-1.7B","SigLIP-400M","2025/08/04",808],[100,"GPT-5-20250807",null,"","","2025/08/14",807],[101,"GPT-4o (1120, detail-high)",null,"","","2024/12/02",806],[102,"QTuneVL1-2B",2.21,"InternLM2.5-1.8B","InternViT-300M-v2.5","2025/05/05",806],[103,"GPT-4o (0806, detail-high)",null,"","","2024/08/08",805],[104,"DeepSeek-VL2-Tiny",3.4,"DeepSeekMoE-3B","SigLIP-400M","2025/01/01",805],[105,"MiniMonkey",2.2,"InternLM2-1.8B","InternViT-300M","2024/09/26",804],[106,"InternVL2.5-2B",2.0,"InternLM2.5-1.8B","InternViT-300M-v2.5","2024/12/10",802],[107,"Ovis1.6-Llama3.2-3B",4.1,"Llama-3.2-3B","SigLIP-400M","2024/10/24",801],[108,"Claude3.5-Sonnet-20241022",null,"","","2024/11/06",798],[109,"InternVL3-1B",0.94,"Qwen2.5-0.5B","InternViT-300M-v2.5","2025/04/14",798],[110,"Qwen2-VL-2B",2.0,"Qwen2-1.5B","QwenViT","2024/09/12",797],[111,"InternVL2-8B",8.0,"InternLM2.5-7B","InternViT-300M","2024/07/11",794],[112,"abab7-preview",null,"","","2024/12/11",794],[113,"granite-vision-3.2-2b",2.98,"granite-3.1-2b-instruct","SigLip","2025/06/20",790],[114,"moonshot-v1-8k",null,"","","2025/03/03",790],[115,"Claude3.5-Sonnet",null,"","","2024/06/24",788],[116,"GPT-4o-mini (0718, detail-high)",null,"","","2024/07/20",785],[117,"InternVL2-4B",4.0,"Phi-3","InternViT-300M","2024/07/11",784],[118,"Llama-3.2-90B-Vision-Instruct",88.6,"Llama-3.1-70B","","2024/10/19",783],[119,"granite-vision-3.1-2b-preview",2.98,"granite-3.1-2b-instruct","SigLip","2025/06/20",783],[120,"InternVL2-2B",2.0,"InternLM2-1.8B","InternViT-300M","2024/07/11",781],[121,"XinYuan-VL-2B-Instruct",2.0,"Qwen2-1.5B","QwenViT","2024/09/27",780],[122,"H2OVL-2B",2.2,"H2O-DANUBE2-1.8B","InternViT-300M","2024/10/31",778],[123,"GLM-4v-9B",9.0,"GLM-4-9B","EVA-02-5B","2024/06/14",776],[124,"InternVL2.5-1B",1.0,"Qwen-2.5-0.5B","InternViT-300M-v2.5","2024/12/10",774],[125,"Step-1.5V-mini",null,"","","2024/12/11",773],[126,"Aquila-VL-2B",2.2,"Qwen-2.5-1.5B","SigLIP-400M","2024/10/24",773],[127,"Gemini-1.5-Pro-002",null,"","","2024/12/02",770],[128,"InternVL2-8B-MPO",8.0,"InternLM2.5-7B","InternViT-300M","2024/11/25",769],[129,"HawkVL-2B",2.44,"Qwen2.5-1.5B","QwenViT","2025/06/16",763],[130,"LLaVA-OneVision-72B (SI)",73.0,"Qwen2-72B","SigLIP-400M","2024/09/19",763],[131,"Long-VITA-16K",14.0,"Qwen2.5-14B","InternViT-300M","2025/06/13",761],[132,"CogVLM2-19B-Chat",19.0,"Llama-3-8B-Instruct","EVA2-CLIP-E","2024/05/31",757],[133,"LLaVA-CoT",11.0,"","","2025/01/05",755],[134,"InternVL2-1B",1.0,"Qwen2-0.5B","InternViT-300M","2024/07/11",755],[135,"Gemini-1.5-Pro",null,"","","2024/06/10",754],[136,"H2OVL-800M",0.83,"H2O-DANUBE3-500M","InternViT-300M","2024/10/31",754],[137,"Llama-3.2-11B-Vision-Instruct",11.0,"Llama-3.1-8B","","2024/10/07",753],[138,"Gemini-1.5-Flash",null,"","","2024/09/16",753],[139,"Gemma3-27B",27.4,"Gemma3-27B","SigLIP-400M","2025/03/19",753],[140,"Ovis1.5-Gemma2-9B",11.4,"Gemma2-9B-It","SigLIP-400M","2024/08/04",752],[141,"GPT-5-nano-20250807",null,"","","2025/08/14",747],[142,"Ovis1.5-Llama3-8B",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/07/29",744],[143,"VITA-1.5",8.3,"Qwen2-7B","InternViT-300M","2025/01/01",741],[144,"LLaVA-OneVision-72B",73.0,"Qwen2-72B","SigLIP-400M","2024/09/19",741],[145,"GPT-4o (0513, detail-low)",null,"","","2024/05/15",735],[146,"Aria",25.3,"Aria-MoE","SigLIP-400M","2024/12/05",734],[147,"Gemini-1.5-Flash-002",null,"","","2024/12/02",733],[148,"OmChat-v2.0-13B",13.0,"Qwen2-7B","InternViT-6B","2024/08/22",728],[149,"MMAlaya2",26.0,"InternLM2-20B","InternViT-6B","2024/08/27",727],[150,"Qwen-VL-Plus",null,"QwenLM","","2024/01/10",726],[151,"SmolVLM2",2.25,"SmolLM2-1.7M","SigLIP-400M","2025/03/13",725],[152,"MiniCPM-Llama3-V2.5",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/05/27",725],[153,"InternVL-Chat-V1.5",26.0,"InternLM2-20B","InternViT-6B","2024/04/17",720],[154,"POINTS-Yi-1.5-9B",9.5,"Yi-1.5-9B","CLIP ViT-L/14","2024/10/11",719],[155,"POINTS-Qwen2.5-7B",8.3,"Qwen-2.5-7B","CLIP ViT-L/14","2024/10/19",717],[156,"GPT-4.1-nano-20250414",null,"","","2025/04/16",710],[157,"Gemma3-12B",12.2,"Gemma3-12B","SigLIP-400M","2025/03/19",702],[158,"Molmo-72B",73.3,"Qwen2-72B","CLIP ViT-L/14","2024/10/28",701],[159,"Yi-Vision",null,"","","2024/08/03",701],[160,"Claude3.7-Sonnet",null,"","","2025/02/27",701],[161,"LLaVA-OneVision-7B (SI)",8.0,"Qwen2-7B","SigLIP-400M","2024/09/17",697],[162,"Claude3-Opus",null,"","","2024/03/28",694],[163,"RekaFlash",null,"","","2024/05/07",692],[164,"InternLM-XComposer2.5",8.0,"InternLM2-7B","CLIP ViT-L/14","2024/07/11",686],[165,"Pixtral-12B",13.0,"Nemo-12B","ViT-400M","2024/09/16",685],[166,"Qwen-VL-Max",null,"QwenLM","","2024/02/02",684],[167,"VITA",47.0,"Mixtral-8x7B","InternViT-300M","2025/01/20",683],[168,"Gemini-1.0-Pro",null,"","","2023/12/23",680],[169,"GPT-4v (1106, detail-high)",null,"","","2024/04/22",678],[170,"InternLM-XComposer2-4KHD",7.0,"InternLM2-7B","CLIP ViT-L/14","2024/06/09",675],[171,"Emu3_chat",8.49,"","","2025/01/26",667],[172,"Gemma3-4B",4.3,"Gemma3-4B","SigLIP-400M","2025/03/19",660],[173,"Claude3-Haiku",null,"","","2024/03/28",658],[174,"RBDash-v1.5",79.0,"Qwen2-72B","CLIP ViT-L/14
InternViT-6B","2024/11/17",657],[175,"Molmo-7B-D",8.0,"Qwen2-7B","CLIP ViT-L/14","2024/10/12",656],[176,"GPT-4v (0409, detail-high)",null,"","","2024/05/15",656],[177,"SmolVLM-Instruct",2.3,"SmolLM2-1.7B","SigLIP-400M","2025/01/27",656],[178,"Mini-InternVL-Chat-2B-V1.5",2.0,"InternLM2-1.8B","InternViT-300M","2024/06/10",652],[179,"Claude3-Sonnet",null,"","","2024/03/28",646],[180,"Mini-InternVL-Chat-4B-V1.5",4.0,"Phi-3","InternViT-300M","2024/06/10",639],[181,"Phi-3-Vision",4.2,"Phi-3","CLIP ViT-L/14","2024/05/31",637],[182,"WeMM",7.0,"InternLM2-7B","SigLIP-400M","2024/06/09",628],[183,"Vintern-1B-v2",3.7,"Qwen2-0.5B","InternViT-300M","2024/11/16",627],[184,"IDEFICS2-8B",8.0,"Mistral-7B","SigLIP-400M","2024/04/26",626],[185,"LLaVA-OneVision-7B",8.0,"Qwen2-7B","SigLIP-400M","2024/09/16",622],[186,"abab6.5s",null,"","","2024/12/11",622],[187,"Vintern-3B-beta",3.7,"Qwen-2.5-3B","InternViT-300M","2024/10/24",618],[188,"Molmo-7B-O",8.0,"Qwen2-7B","CLIP ViT-L/14","2024/10/20",616],[189,"PaliGemma-3B-mix-448",3.0,"Gemma-2B","SigLIP-400M","2024/05/17",614],[190,"Cambrian-8B",8.0,"Vicuna-v1.5-7B","CLIP ViT-L/14","2024/07/11",614],[191,"Cambrian-13B",13.0,"Vicuna-v1.5-13B","CLIP ViT-L/14","2024/07/29",610],[192,"SmolVLM-500M",0.51,"SmolLM2-360M","ViT-93M","2025/01/27",609],[193,"SmolVLM2-500M",0.51,"SmolLM2-360M","ViT-93M","2025/03/13",609],[194,"MiniCPM-V-2",2.8,"MiniCPM-2.4B","SigLIP-400M","2024/04/15",605],[195,"Phi-3.5-Vision",4.0,"Phi-3.5","CLIP ViT-L/14","2024/08/28",599],[196,"Janus-Pro-7B",7.42,"DeepSeek-7B","SigLIP-400M","2025/02/02",595],[197,"Cambrian-34B",34.0,"Nous-Hermes-2-Yi-34B","CLIP ViT-L/14","2024/07/18",591],[198,"CogVLM-17B-Chat",17.0,"Vicuna-v1.5-7B","EVA2-CLIP-E","2024/01/03",590],[199,"Moondream2",1.9,"SigLIP-400M","Phi-1.5","2024/10/20",585],[200,"LLaVA-OneVision-0.5B",1.0,"Qwen2-0.5B","SigLIP-400M","2024/09/16",583],[201,"VILA1.5-40B",40.0,"Yi-34B","InternViT-6B","2024/08/25",581],[202,"Llama-3-MixSense-v1.1",8.0,"Llama-3-8B-Instruct","Florence-2-Large-FT","2024/08/21",577],[203,"LLaVA-Next-Yi-34B",34.8,"Yi-34B","CLIP ViT-L/14","2024/03/25",574],[204,"Eagle-X5-13B",15.0,"Vicuna-v1.5-13B","Clip-448
ConvNeXT-1024
SAM-1024
DET-1024
Pix2Struct-1024","2024/09/26",574],[205,"SmolVLM2-256M",0.26,"SmolLM2-135M","ViT-93M","2025/03/13",566],[206,"LLaVA-OneVision-0.5B (SI)",1.0,"Qwen2-0.5B","SigLIP-400M","2024/09/17",565],[207,"grok-2-vision-1212",null,"","","2025/03/03",555],[208,"Ross-Qwen2-7B",8.2,"Qwen2-7B","CLIP ViT-L/14","2025/01/17",553],[209,"XGen-MM-Instruct-Interleave-v1.5",4.4,"Phi-3","SigLIP-400M","2024/09/06",551],[210,"Eagle-X5-7B",9.0,"Vicuna-v1.5-7B","Clip-448
ConvNeXT-1024
SAM-1024
DET-1024
Pix2Struct-1024","2024/09/26",551],[211,"Idefics3-8B-Llama3",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/08/27",550],[212,"MolmoE-1B",7.2,"OLMoE-1B-7B-0924","CLIP ViT-L/14","2024/10/21",547],[213,"Mantis-8B-Idefics2",8.0,"Mistral-7B","SigLIP-400M","2024/08/08",542],[214,"XGen-MM-Instruct-DPO-v1.5",4.4,"Phi-3","SigLIP-400M","2024/09/06",541],[215,"LLaVA-Next-Vicuna-13B",13.4,"Vicuna-v1.5-13B","CLIP ViT-L/14","2024/03/25",537],[216,"Monkey-Chat",9.8,"Qwen-7B","ViT-BigHuge","2024/01/16",534],[217,"InternLM-XComposer2",7.0,"InternLM2-7B","CLIP ViT-L/14","2024/01/26",532],[218,"LLaVA-Next-Vicuna-7B",7.1,"Vicuna-v1.5-7B","CLIP ViT-L/14","2024/03/25",532],[219,"LLaVA-Next-Mistral-7B",7.6,"Mistral-7B","CLIP ViT-L/14","2024/03/25",531],[220,"LLaVA-Next-Llama3",8.0,"Llama-3-8B-Instruct","CLIP ViT-L/14","2024/07/29",531],[221,"SmolVLM-256M",0.26,"SmolLM2-135M","ViT-93M","2025/01/27",527],[222,"GPT-4v (0409, detail-low)",null,"","","2024/05/15",526],[223,"GPT-4v (1106, detail-low)",null,"","","2023/12/23",516],[224,"Monkey",9.8,"Qwen-7B","ViT-BigHuge","2024/01/11",514],[225,"RekaEdge",null,"","","2024/05/31",506],[226,"SmolVLM-Instruct-DPO",2.3,"SmolLM2-1.7B","SigLIP-400M","2025/01/27",500],[227,"Eagle-X5-34B-Chat",36.8,"Yi-34B","Clip-448
ConvNeXT-1024
SAM-1024
DET-1024
Pix2Struct-1024","2024/11/29",495],[228,"Falcon2-VLM-11B",11.4,"Falcon2-11B","CLIP ViT-L/14","2024/10/30",491],[229,"XVERSE-V-13B",13.0,"XVERSE-13B","CLIP ViT-L/14","2024/05/10",489],[230,"Qwen-VL-Chat",9.6,"Qwen-7B","ViT-G/16","2023/08/24",488],[231,"Janus-1.3B",2.1,"DeepSeek-1B","SigLIP-400M","2024/10/24",482],[232,"SmolVLM-Synthetic",2.3,"SmolLM2-1.7B","SigLIP-400M","2025/01/27",461],[233,"VILA1.5-13B",13.0,"Vicuna-v1.5-13B","SigLIP-400M","2024/08/25",460],[234,"LLaVA-Next-Interleave-7B-DPO",8.0,"Qwen-1.5-7B","SigLIP-400M","2024/07/29",460],[235,"InternLM-XComposer2-1.8B",2.0,"InternLM2-1.8B","CLIP ViT-L/14","2024/06/09",447],[236,"Bunny-Llama3-8B",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/07/18",444],[237,"Llama-3-VILA1.5-8B",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/08/25",438],[238,"VILA1.5-3B",3.0,"Sheared-LLaMA-2.7B","SigLIP-400M","2024/08/25",437],[239,"Emu2_chat",37.0,"Llama-33B","EVA-02-CLIP-E-plus","2024/01/17",436],[240,"DeepSeek-VL-7B",7.3,"DeekSeek-7B","SAM-B
SigLIP-L","2024/03/21",435],[241,"OmniLMM-12B",12.0,"Zephyr-7B-β","EVA-02-5B","2024/02/07",420],[242,"LLaVA-LLaMA-3-8B",8.0,"Llama-3-8B-Instruct","CLIP ViT-L/14","2024/05/07",420],[243,"DeepSeek-VL-1.3B",2.0,"DeekSeek-1B","SAM-B
SigLIP-L","2024/03/21",413],[244,"LLaVA-Next-Interleave-7B",8.0,"Qwen-1.5-7B","SigLIP-400M","2024/08/08",411],[245,"LLaVA-v1.5-13B (QLoRA)",13.4,"Vicuna-v1.5-13B","CLIP ViT-L/14","2023/12/28",407],[246,"TransCore-M",13.4,"PCITransGPT-13B","CLIP ViT-L/14","2024/04/16",405],[247,"LLaVA-InternLM2-7B (QLoRA)",8.1,"InternLM2-7B","CLIP ViT-L/14","2024/01/17",402],[248,"LLaVA-InternLM2-20B (QLoRA)",20.2,"InternLM2-20B","CLIP ViT-L/14","2024/01/17",400],[249,"ShareGPT4V-13B",13.4,"Vicuna-v1.5-13B","CLIP ViT-L/14","2023/12/08",398],[250,"360VL-70B",70.0,"Llama-3-70B-Instruct","CLIP ViT-L/14","2024/05/25",397],[251,"LLaVA-v1.5-7B (QLoRA)",7.2,"Vicuna-v1.5-7B","CLIP ViT-L/14","2023/12/28",385],[252,"LLaVA-Next-Qwen-32B",33.0,"Qwen-1.5-32B","SigLIP-400M","2024/08/08",384],[253,"ShareGPT4V-7B",7.2,"Vicuna-v1.5-7B","CLIP ViT-L/14","2023/12/08",371],[254,"Mantis-8B-Fuyu",8.0,"Fuyu-8B","","2024/09/07",366],[255,"MiniCPM-V",3.0,"MiniCPM-2.4B","SigLIP-400M","2024/02/07",366],[256,"LLaVA-InternLM-7B (QLoRA)",7.6,"InternLM-7B","CLIP ViT-L/14","2023/12/28",347],[257,"Mantis-8B-siglip-llama3",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/08/08",347],[258,"LLaVA-v1.5-13B",13.4,"Vicuna-v1.5-13B","CLIP ViT-L/14","2023/10/05",337],[259,"Parrot-7B",8.0,"Qwen2-7B","CLIP ViT-L/14","2024/08/22",334],[260,"ShareCaptioner",8.0,"InternLM-7B","EVA-G","2024/01/03",322],[261,"LLaVA-v1.5-7B",7.2,"Vicuna-v1.5-7B","CLIP ViT-L/14","2023/10/05",318],[262,"Moondream1",1.9,"SigLIP-400M","Phi-1.5","2024/09/26",309],[263,"AKI-4B",4.33,"Phi-3.5","SigLIP-400M","2025/03/25",308],[264,"InternLM-XComposer",8.0,"InternLM-7B","EVA-G","2023/09/26",290],[265,"Yi-VL-6B",6.6,"Yi-6B","CLIP ViT-H/14","2024/01/25",290],[266,"Yi-VL-34B",34.6,"Yi-34B","CLIP ViT-H/14","2024/01/25",290],[267,"IDEFICS-80B-Instruct",80.0,"Llama-65B","CLIP ViT-H/14","2023/07/25",283],[268,"InstructBLIP-7B",8.0,"Vicuna-7B","EVA-G","2023/05/11",276],[269,"LLaVA-v1-7B",7.2,"Llama-7B","CLIP ViT-L/14","2023/04/17",269],[270,"mPLUG-Owl2",8.2,"Llama-2-7B","CLIP ViT-L/14","2023/11/10",255],[271,"IDEFICS-9B-Instruct",9.0,"Llama-7B","CLIP ViT-H/14","2023/07/25",252],[272,"Slime-13B",13.0,"Vicuna-v1.5-13B","CLIP ViT-L/14","2024/09/14",245],[273,"Kosmos2",1.7,"","","2024/10/19",244],[274,"Slime-8B",8.0,"Llama-3-8B-Instruct","CLIP ViT-L/14","2024/09/14",233],[275,"MMAlaya",7.8,"Alaya-7B-Chat","EVA-G","2024/01/29",223],[276,"Slime-7B",7.0,"Vicuna-v1.5-7B","CLIP ViT-L/14","2024/09/14",211],[277,"Mantis-8B-clip-llama3",8.0,"Llama-3-8B-Instruct","CLIP ViT-L/14","2024/08/08",200],[278,"MiniGPT-4-v1-7B",8.0,"Vicuna-7B","EVA-G","2023/04/20",172],[279,"VisualGLM",8.0,"ChatGLM 6B","EVA-CLIP","2023/05/17",170],[280,"OpenFlamingo v2",9.0,"MPT 7B","CLIP ViT-L/14","2023/06/28",149],[281,"Qwen-VL",9.6,"Qwen-7B","ViT-G/16","2023/08/24",127],[282,"PandaGPT-13B",14.0,"Vicuna-13B","ImageBind ViT-H/14","2023/05/25",36],[283,"MiniGPT-4-v2",8.0,"Llama-2-13B","EVA-G","2023/10/27",31],[284,"Chameleon-30B",30.0,"","","2024/07/29",27],[285,"Chameleon-7B",7.0,"","","2024/07/29",5]],"metadata":null},"headers":["1","2","3"],"row_count":[1,"dynamic"],"col_count":[3,"dynamic"],"datatype":["number","html","number","html","html","str","number"],"type":"pandas","latex_delimiters":[{"left":"$$","right":"$$","display":true}],"show_label":true,"height":500,"min_width":160,"interactive":false,"visible":true,"elem_classes":[],"wrap":true,"line_breaks":true,"column_widths":[],"name":"dataframe","_selectable":false},"skip_api":false,"component_class_id":"6a51bb3357f2e94c40fb8d4fbe06aa8e","key":null,"api_info":{"properties":{"headers":{"items":{"type":"string"},"title":"Headers","type":"array"},"data":{"items":{"items":{},"type":"array"},"title":"Data","type":"array"},"metadata":{"anyOf":[{"additionalProperties":{"anyOf":[{"items":{},"type":"array"},{"type":"null"}]},"type":"object"},{"type":"null"}],"default":null,"title":"Metadata"}},"required":["headers","data"],"title":"DataframeData","type":"object"},"example_inputs":{"headers":["a","b"],"data":[["foo","bar"]]}},{"id":212,"type":"textbox","props":{"value":"OCRBench","lines":1,"max_lines":20,"label":"OCRBench","show_label":true,"container":true,"min_width":160,"visible":false,"autofocus":false,"autoscroll":true,"elem_classes":[],"type":"text","rtl":false,"show_copy_button":false,"name":"textbox","_selectable":false},"skip_api":false,"component_class_id":"d0491bb0fbd427bdb2a4549c4d1ac869","key":null,"api_info":{"type":"string"},"example_inputs":"Hello!!"},{"id":213,"type":"form","props":{"scale":0,"min_width":0,"name":"form"},"skip_api":true,"component_class_id":"43cda85c6ff7a5dd8f83d29496b014ee","key":null},{"id":214,"type":"form","props":{"scale":0,"min_width":0,"name":"form"},"skip_api":true,"component_class_id":"43cda85c6ff7a5dd8f83d29496b014ee","key":null},{"id":215,"type":"tabitem","props":{"label":"📊 MMStar Leaderboard","visible":true,"interactive":true,"id":19,"elem_id":"MMStar","name":"tab"},"skip_api":true,"component_class_id":"18f46968e2b273dc5dbda0fe78433d7e","key":null},{"id":216,"type":"markdown","props":{"value":"## MMStar Evaluation Results\n\n- MMStar is an elite vision-indispensable multi-modal benchmark, including 1,500 challenging samples meticulously selected by humans.\n- During the evaluation of MMStar, we find that some API models may reject to answer some of the questions. Currently, we treat such cases as wrong answers when reporting the results. ","show_label":true,"rtl":false,"latex_delimiters":[{"left":"$$","right":"$$","display":true}],"visible":true,"elem_classes":[],"sanitize_html":true,"line_breaks":false,"header_links":false,"show_copy_button":false,"name":"markdown","_selectable":false},"skip_api":false,"component_class_id":"0f35515b9a3362b42bb6721c836157a0","key":null,"api_info":{"type":"string"},"example_inputs":"# Hello!"},{"id":217,"type":"checkboxgroup","props":{"choices":[["Overall","Overall"],["coarse perception","coarse perception"],["fine-grained perception","fine-grained perception"],["instance reasoning","instance reasoning"],["logical reasoning","logical reasoning"],["math","math"],["science & technology","science & technology"]],"value":["Overall"],"type":"value","label":"MMStar CheckBoxes","show_label":true,"container":true,"min_width":160,"interactive":true,"visible":true,"elem_classes":[],"name":"checkboxgroup","_selectable":false},"skip_api":false,"component_class_id":"0635a5d3bf87369f1c2c1c69f8a3d0cc","key":null,"api_info":{"items":{"enum":["Overall","coarse perception","fine-grained perception","instance reasoning","logical reasoning","math","science & technology"],"type":"string"},"title":"Checkbox Group","type":"array"},"example_inputs":["Overall"]},{"id":218,"type":"row","props":{"variant":"default","visible":true,"equal_height":true,"show_progress":false,"name":"row"},"skip_api":true,"component_class_id":"b5cf3d15e2293fb5ccc071d7b8d69f64","key":null},{"id":219,"type":"textbox","props":{"value":"Input the Model Name (fuzzy, case insensitive)","lines":1,"max_lines":20,"label":"Model Name","show_label":true,"container":true,"min_width":160,"interactive":true,"visible":true,"autofocus":false,"autoscroll":true,"elem_classes":[],"type":"text","rtl":false,"show_copy_button":false,"name":"textbox","_selectable":false},"skip_api":false,"component_class_id":"d0491bb0fbd427bdb2a4549c4d1ac869","key":null,"api_info":{"type":"string"},"example_inputs":"Hello!!"},{"id":220,"type":"checkboxgroup","props":{"choices":[["<4B","<4B"],["4B-10B","4B-10B"],["10B-20B","10B-20B"],["20B-40B","20B-40B"],[">40B",">40B"],["Unknown","Unknown"]],"value":["<4B","4B-10B","10B-20B","20B-40B",">40B","Unknown"],"type":"value","label":"Model Size","show_label":true,"container":true,"min_width":160,"interactive":true,"visible":true,"elem_classes":[],"name":"checkboxgroup","_selectable":false},"skip_api":false,"component_class_id":"0635a5d3bf87369f1c2c1c69f8a3d0cc","key":null,"api_info":{"items":{"enum":["<4B","4B-10B","10B-20B","20B-40B",">40B","Unknown"],"type":"string"},"title":"Checkbox Group","type":"array"},"example_inputs":["<4B"]},{"id":221,"type":"checkboxgroup","props":{"choices":[["API","API"],["OpenSource","OpenSource"]],"value":["API","OpenSource"],"type":"value","label":"Model Type","show_label":true,"container":true,"min_width":160,"interactive":true,"visible":true,"elem_classes":[],"name":"checkboxgroup","_selectable":false},"skip_api":false,"component_class_id":"0635a5d3bf87369f1c2c1c69f8a3d0cc","key":null,"api_info":{"items":{"enum":["API","OpenSource"],"type":"string"},"title":"Checkbox Group","type":"array"},"example_inputs":["API"]},{"id":222,"type":"form","props":{"scale":3,"min_width":480,"name":"form"},"skip_api":true,"component_class_id":"43cda85c6ff7a5dd8f83d29496b014ee","key":null},{"id":223,"type":"dataframe","props":{"value":{"headers":["Rank","Method","Param (B)","Language Model","Vision Model","Eval Date","Overall"],"data":[[1,"JT-VL-Chat-V3.0",null,"","","2025/08/04",82.1],[2,"BlueLM-2.6-3B",3.0,"","","2025/09/17",80.1],[3,"SenseNova-V6-5-Pro",null,"","","2025/09/03",76.1],[4,"GPT-5-20250807",null,"","","2025/08/14",75.7],[5,"CongRong-v2.0",null,"","","2025/05/20",75.3],[6,"SenseNova-V6-Pro",null,"","","2025/05/05",73.7],[7,"Gemini-2.5-Pro",null,"","","2025/04/07",73.6],[8,"InternVL3-78B",78.4,"Qwen2.5-72B","InternViT-6B-v2.5","2025/04/14",73.4],[9,"GPT-5-mini-20250807",null,"","","2025/08/14",73.2],[10,"HunYuan-Standard-Vision",null,"","","2025/01/15",72.9],[11,"SenseNova",null,"","","2024/12/12",72.7],[12,"R-4B",4.82,"Qwen3-4B","SigLip-400M","2025/08/11",72.6],[13,"InternVL3-38B",38.4,"Qwen2.5-32B","InternViT-6B-v2.5","2025/04/14",72.6],[14,"GLM-4v-Plus-20250111",null,"","","2025/01/25",72.5],[15,"InternVL2.5-78B-MPO",78.0,"Qwen-2.5-72B","InternViT-6B-v2.5","2024/12/29",72.1],[16,"TeleMM",null,"","","2024/12/31",70.8],[17,"Ola-7b",8.88,"Qwen2.5-7B","Oryx-ViT","2025/02/05",70.8],[18,"Qwen2.5-VL-72B",73.4,"Qwen2.5-72B","QwenViT","2025/02/02",70.5],[19,"Qwen2.5-VL-32B",33.5,"Qwen2.5-32B","QwenViT","2025/07/02",70.3],[20,"ChatGPT-4o-latest",null,"","","2025/04/07",70.2],[21,"InternVL2.5-38B-MPO",38.0,"Qwen-2.5-32B","InternViT-6B-v2.5","2024/12/28",70.1],[22,"Kimi-VL-A3B-Thinking-2506",16.4,"Moonlight-16B-A3B","MoonViT","2025/07/02",70.0],[23,"GPT-4.1-20250414",null,"","","2025/04/16",69.8],[24,"SAIL-VL-1.5-8B",7.95,"Qwen2.5-7B","InternViT-300B","2025/04/23",69.7],[25,"InternVL2.5-78B",78.0,"Qwen-2.5-72B","InternViT-6B-v2.5","2024/12/10",69.5],[26,"SAIL-VL-1.6-8B",8.33,"Qwen2.5-7B","AIMv2 Huge","2025/04/24",69.5],[27,"Gemini-2.0-Flash",null,"","","2025/01/02",69.4],[28,"BailingMM-Pro-0120",81.0,"Bailing-80B","SigLIP-400M","2025/01/25",69.4],[29,"GPT-4.5",null,"","","2025/03/26",69.3],[30,"Step-1o",null,"","","2025/01/13",69.3],[31,"Qwen-VL-Max-0809",72.0,"Qwen2-72B","QwenViT","2024/09/12",69.2],[32,"Ovis2-34B",34.9,"Qwen2.5-32B","AIMv2-1B","2025/02/18",69.2],[33,"Taiyi",null,"","","2024/12/11",69.0],[34,"InternVL3-14B",15.1,"Qwen2.5-14B","InternViT-300M-v2.5","2025/04/14",68.9],[35,"InternVL3-8B",7.94,"Qwen2.5-7B","InternViT-300M-v2.5","2025/04/14",68.7],[36,"Qwen2-VL-72B",73.4,"Qwen2-72B","QwenViT","2024/10/28",68.6],[37,"InternVL2.5-38B",38.0,"Qwen-2.5-32B","InternViT-6B-v2.5","2024/12/10",68.5],[38,"Gemini-2.0-Pro",null,"","","2025/02/27",68.5],[39,"GPT-5-nano-20250807",null,"","","2025/08/14",68.3],[40,"BlueLM-2.5-3B",2.9,"BlueLM-base-3B","Siglip2-So400M","2025/07/16",67.8],[41,"InternVL2.5-26B-MPO",26.0,"InternLM2.5-20B","InternViT-6B-v2.5","2024/12/28",67.7],[42,"InternVL3-9B",9.14,"InternLM3-8B","InternViT-300M-v2.5","2025/04/14",67.4],[43,"BailingMM-Lite-1203",21.0,"Bailing-20B","SigLIP-400M","2024/12/08",67.3],[44,"Ovis2-16B",16.2,"Qwen2.5-14B","AIMv2 Huge","2025/02/18",67.2],[45,"InternVL2-Llama3-76B",76.0,"Llama-3-70B-Instruct","InternViT-6B","2024/07/19",67.1],[46,"Gemini-1.5-Pro-002",null,"","","2024/12/02",67.1],[47,"VARCO-VISION-2.0-14B",15.2,"Qwen3-14B","SigLIP-400M","2025/08/04",66.9],[48,"MUG-U-7B",7.0,"","","2025/03/19",66.6],[49,"InternVL2.5-26B",26.0,"InternLM2.5-20B","InternViT-6B-v2.5","2024/12/10",66.5],[50,"GLM-4v-Plus",null,"","","2024/12/11",66.3],[51,"abab7-preview",null,"","","2024/12/11",66.0],[52,"LLaVA-OneVision-72B",73.0,"Qwen2-72B","SigLIP-400M","2024/09/19",65.8],[53,"LLaVA-OneVision-72B (SI)",73.0,"Qwen2-72B","SigLIP-400M","2024/09/19",65.3],[54,"InternVL2.5-8B-MPO",8.0,"InternLM2.5-7B","InternViT-300M-v2.5","2024/12/28",65.2],[55,"grok-2-vision-1212",null,"","","2025/03/03",65.2],[56,"Step-1.5V",null,"Step-1.5","stepencoder","2024/10/11",65.1],[57,"Claude3.7-Sonnet",null,"","","2025/02/27",65.1],[58,"GPT-4o (1120, detail-high)",null,"","","2024/12/02",65.1],[59,"Claude3.5-Sonnet-20241022",null,"","","2024/11/06",65.1],[60,"InternVL2-40B",40.0,"Nous-Hermes-2-Yi-34B","InternViT-6B","2024/07/11",64.7],[61,"GPT-4o (0806, detail-high)",null,"","","2024/08/08",64.7],[62,"Ovis2-8B",8.94,"Qwen2.5-7B","AIMv2 Huge","2025/02/18",64.6],[63,"Gemini-1.5-Flash-002",null,"","","2024/12/02",64.4],[64,"WeThink-Qwen2.5VL-7B",8.29,"Qwen2.5-7B","QwenViT","2025/05/26",64.2],[65,"Qwen2.5-VL-7B",8.29,"Qwen2.5-7B","QwenViT","2025/02/02",64.1],[66,"VARCO-VISION-14B",15.2,"Qwen2.5-14B","SigLIP-400M","2025/01/02",64.1],[67,"GPT-4o (0513, detail-high)",null,"","","2024/05/31",63.9],[68,"NVLM-D-72B",79.4,"Qwen2-72B","InternViT-6B","2024/10/19",63.7],[69,"RBDash-v1.5",79.0,"Qwen2-72B","CLIP ViT-L/14
InternViT-6B","2024/11/17",63.5],[70,"Ovis1.6-Gemma2-27B",28.9,"Gemma2-27B","SigLIP-400M","2024/11/29",63.5],[71,"MiniCPM-o-2.6",8.67,"Qwen2.5-7B","SigLIP-400M","2025/01/21",63.3],[72,"Molmo-72B",73.3,"Qwen2-72B","CLIP ViT-L/14","2024/10/28",63.3],[73,"InternVL2.5-8B",8.0,"InternLM2.5-7B","InternViT-300M-v2.5","2024/12/10",63.2],[74,"Ovis1.6-Gemma2-9B",10.2,"Gemma2-9B-It","SigLIP-400M","2024/09/19",62.9],[75,"Ristretto-3B",3.84,"Qwen2.5-3B","SigLIP-400M","2025/04/01",62.8],[76,"SAIL-VL-1.5-2B",2.47,"Qwen2.5-1.5B","AIMv2 Huge","2025/04/23",62.6],[77,"InternVL2-8B-MPO",8.0,"InternLM2.5-7B","InternViT-300M","2024/11/25",62.5],[78,"BlueLM-V-3B",3.0,"BlueLM-3B","SigLIP-400M","2024/10/30",62.3],[79,"InternVL2-8B-MPO-CoT",8.0,"InternLM2.5-7B","InternViT-300M","2024/11/25",62.2],[80,"Claude3.5-Sonnet",null,"","","2024/06/24",62.2],[81,"Kimi-VL-A3B-Instruct",16.4,"Moonlight-16B-A3B","MoonViT","2025/04/14",62.0],[82,"Ovis2-4B",4.62,"Qwen2.5-3B","AIMv2 Huge","2025/02/18",61.9],[83,"valley2_dpo",8.88,"Qwen2.5-7B","SigLIP-400M","2025/05/30",61.9],[84,"LLaVA-OneVision-7B",8.0,"Qwen2-7B","SigLIP-400M","2024/09/16",61.9],[85,"DeepSeek-VL2",27.5,"DeepSeekMoE-27B","SigLIP-400M","2025/01/01",61.9],[86,"GPT-4o (0513, detail-low)",null,"","","2024/05/15",61.6],[87,"InternVL2-8B",8.0,"InternLM2.5-7B","InternViT-300M","2024/07/11",61.5],[88,"bailingMM-mini",17.0,"bailing-mini","bailingMM-encoder-1B
InternViT-6B","2024/10/24",61.3],[89,"Ovis-U1-3B",3.64,"Qwen3-1.7B","aimv2-large-path14-448","2025/07/20",61.3],[90,"POINTS1.5-Qwen2.5-7B",8.3,"Qwen-2.5-7B","NaViT","2024/12/06",61.1],[91,"InternVL3-2B",2.09,"Qwen2.5-1.5B","InternViT-300M-v2.5","2025/04/14",61.1],[92,"InternVL2-26B",26.0,"InternLM2-20B","InternViT-6B","2024/07/11",61.0],[93,"InternVL2.5-4B-MPO",4.0,"Qwen-2.5-3B","InternViT-300M-v2.5","2024/12/28",61.0],[94,"GPT-4.1-mini-20250414",null,"","","2025/04/16",60.9],[95,"Valley-Eagle",8.9,"Qwen2.5-7B","Qwen-ViT
SigLIP-400M","2024/12/29",60.9],[96,"POINTS-Qwen2.5-7B",8.3,"Qwen-2.5-7B","CLIP ViT-L/14","2024/10/19",60.9],[97,"QTuneVL1.5-2B",2.09,"Qwen2.5-1.5B","InternViT-300M-v2.5","2025/08/11",60.8],[98,"Kimi-VL-A3B-Thinking",16.4,"Moonlight-16B-A3B","MoonViT","2025/04/23",60.8],[99,"Aria",25.3,"Aria-MoE","SigLIP-400M","2024/12/05",60.7],[100,"Qwen2-VL-7B",8.0,"Qwen2-7B","QwenViT","2024/09/12",60.7],[101,"CongRong",null,"","","2024/06/26",60.6],[102,"Yi-Vision",null,"","","2024/08/03",60.5],[103,"VITA-1.5",8.3,"Qwen2-7B","InternViT-300M","2025/01/01",60.2],[104,"Long-VITA-16K",14.0,"Qwen2.5-14B","InternViT-300M","2025/06/13",60.1],[105,"moonshot-v1-8k",null,"","","2025/03/03",60.1],[106,"valley2",8.88,"Qwen2.5-7B","SigLIP-400M","2025/05/30",60.0],[107,"InternLM-XComposer2.5",8.0,"InternLM2-7B","CLIP ViT-L/14","2024/07/11",59.9],[108,"Qwen-VL-Plus-0809",null,"","","2024/09/17",59.9],[109,"Gemma3-27B",27.4,"Gemma3-27B","SigLIP-400M","2025/03/19",59.6],[110,"Gemini-1.5-Pro",null,"","","2024/06/10",59.1],[111,"Phi-4-MultiModal",5.57,"Phi-4-Mini","SigLIP-400M","2025/03/13",58.9],[112,"InternVL2.5-4B",4.0,"Qwen-2.5-3B","InternViT-300M-v2.5","2024/12/10",58.7],[113,"OmChat-v2.0-13B",13.0,"Qwen2-7B","InternViT-6B","2024/08/22",58.2],[114,"MMAlaya2",26.0,"InternLM2-20B","InternViT-6B","2024/08/27",58.1],[115,"Ovis1.5-Gemma2-9B",11.4,"Gemma2-9B-It","SigLIP-400M","2024/08/04",58.1],[116,"MiniCPM-V-2.6",8.0,"Qwen2-7B","SigLIP-400M","2024/08/08",57.5],[117,"DeepSeek-VL2-Small",16.1,"DeepSeekMoE-16B","SigLIP-400M","2025/01/01",57.5],[118,"Ovis1.5-Llama3-8B",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/07/29",57.3],[119,"InternVL-Chat-V1.5",26.0,"InternLM2-20B","InternViT-6B","2024/04/17",57.1],[120,"QTuneVL1.5-3B",3.75,"Qwen2.5-3B","QwenViT","2025/08/11",57.1],[121,"WeMM",7.0,"InternLM2-7B","SigLIP-400M","2024/06/09",57.0],[122,"POINTS-Yi-1.5-9B",9.5,"Yi-1.5-9B","CLIP ViT-L/14","2024/10/11",56.9],[123,"Ovis2-2B",2.46,"Qwen2.5-1.5B","AIMv2 Large","2025/02/18",56.7],[124,"LLaVA-OneVision-7B (SI)",8.0,"Qwen2-7B","SigLIP-400M","2024/09/17",56.7],[125,"SAIL-VL-2B",2.1,"Qwen2.5-1.5B","InternViT-300M","2024/12/25",56.5],[126,"Qwen2.5-VL-3B",3.75,"Qwen2.5-3B","QwenViT","2025/02/02",56.3],[127,"InternLM-XComposer2",7.0,"InternLM2-7B","CLIP ViT-L/14","2024/01/26",56.2],[128,"granite-vision-3.1-2b-preview",2.98,"granite-3.1-2b-instruct","SigLip","2025/06/20",56.1],[129,"Molmo-7B-D",8.0,"Qwen2-7B","CLIP ViT-L/14","2024/10/12",56.1],[130,"Gemma3-12B",12.2,"Gemma3-12B","SigLIP-400M","2025/03/19",56.1],[131,"GPT-4v (0409, detail-high)",null,"","","2024/05/15",56.0],[132,"Gemini-1.5-Flash",null,"","","2024/09/16",55.8],[133,"Eagle-X5-34B-Chat",36.8,"Yi-34B","Clip-448
ConvNeXT-1024
SAM-1024
DET-1024
Pix2Struct-1024","2024/11/29",55.5],[134,"Llama-3.2-90B-Vision-Instruct",88.6,"Llama-3.1-70B","","2024/10/19",55.3],[135,"InternLM-XComposer2-4KHD",7.0,"InternLM2-7B","CLIP ViT-L/14","2024/06/09",55.3],[136,"VILA1.5-40B",40.0,"Yi-34B","InternViT-6B","2024/08/25",55.2],[137,"Idefics3-8B-Llama3",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/08/27",55.0],[138,"InternVL2.5-2B-MPO",2.0,"InternLM2.5-1.8B","InternViT-300M-v2.5","2024/12/28",54.9],[139,"Aquila-VL-2B",2.2,"Qwen-2.5-1.5B","SigLIP-400M","2024/10/24",54.9],[140,"LLaVA-CoT",11.0,"","","2025/01/05",54.9],[141,"GLM-4v-9B",9.0,"GLM-4-9B","EVA-02-5B","2024/06/14",54.8],[142,"GPT-4o-mini (0718, detail-high)",null,"","","2024/07/20",54.8],[143,"Step-1.5V-mini",null,"","","2024/12/11",54.7],[144,"granite-vision-3.2-2b",2.98,"granite-3.1-2b-instruct","SigLip","2025/06/20",54.6],[145,"Pixtral-12B",13.0,"Nemo-12B","ViT-400M","2024/09/16",54.5],[146,"InternVL2.5-2B",2.0,"InternLM2.5-1.8B","InternViT-300M-v2.5","2024/12/10",54.3],[147,"Cambrian-34B",34.0,"Nous-Hermes-2-Yi-34B","CLIP ViT-L/14","2024/07/18",54.2],[148,"InternVL2-4B",4.0,"Phi-3","InternViT-300M","2024/07/11",53.9],[149,"Ross-Qwen2-7B",8.2,"Qwen2-7B","CLIP ViT-L/14","2025/01/17",53.9],[150,"Flash-VL-2B-Dynamic-ISS",2.53,"Qwen-2.5-1.5B-Instruct","SigLIP2-400M-512","2025/05/30",53.8],[151,"QTuneVL1-2B",2.21,"InternLM2.5-1.8B","InternViT-300M-v2.5","2025/05/05",53.6],[152,"GLM-4v",null,"","","2024/05/20",53.2],[153,"Llama-3-MixSense-v1.1",8.0,"Llama-3-8B-Instruct","Florence-2-Large-FT","2024/08/21",53.1],[154,"Mini-InternVL-Chat-4B-V1.5",4.0,"Phi-3","InternViT-300M","2024/06/10",53.1],[155,"GPT-4v (0409, detail-low)",null,"","","2024/05/15",52.9],[156,"VARCO-VISION-2.0-1.7B",2.12,"Qwen3-1.7B","SigLIP-400M","2025/08/04",52.5],[157,"XinYuan-VL-2B-Instruct",2.0,"Qwen2-1.5B","QwenViT","2024/09/27",52.3],[158,"InternVL3-1B",0.94,"Qwen2.5-0.5B","InternViT-300M-v2.5","2025/04/14",52.3],[159,"Ovis2-1B",1.27,"Qwen2.5-0.5B","AIMv2 Large","2025/02/18",52.1],[160,"Ovis1.6-Llama3.2-3B",4.1,"Llama-3.2-3B","SigLIP-400M","2024/10/24",52.0],[161,"granite-vision-3.3-2b",2.98,"granite-3.1-2b-instruct","SigLIP2-400M","2025/06/20",51.9],[162,"MiniCPM-Llama3-V2.5",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/05/27",51.8],[163,"LLaVA-Next-Yi-34B",34.8,"Yi-34B","CLIP ViT-L/14","2024/03/25",51.6],[164,"InternVL2.5-1B",1.0,"Qwen-2.5-0.5B","InternViT-300M-v2.5","2024/12/10",51.3],[165,"Cambrian-8B",8.0,"Vicuna-v1.5-7B","CLIP ViT-L/14","2024/07/11",50.7],[166,"CogVLM2-19B-Chat",19.0,"Llama-3-8B-Instruct","EVA2-CLIP-E","2024/05/31",50.5],[167,"GPT-4v (1106, detail-high)",null,"","","2024/04/22",50.4],[168,"MiniMonkey",2.2,"InternLM2-1.8B","InternViT-300M","2024/09/26",50.4],[169,"RekaFlash",null,"","","2024/05/07",50.2],[170,"Molmo-7B-O",8.0,"Qwen2-7B","CLIP ViT-L/14","2024/10/20",50.1],[171,"InternVL2-2B",2.0,"InternLM2-1.8B","InternViT-300M","2024/07/11",49.8],[172,"Llama-3.2-11B-Vision-Instruct",11.0,"Llama-3.1-8B","","2024/10/07",49.8],[173,"DeepSeek-VL2-Tiny",3.4,"DeepSeekMoE-3B","SigLIP-400M","2025/01/01",49.8],[174,"GPT-4v (1106, detail-low)",null,"","","2023/12/23",49.7],[175,"InternVL2.5-1B-MPO",1.0,"Qwen-2.5-0.5B","InternViT-300M-v2.5","2024/12/28",49.5],[176,"IDEFICS2-8B",8.0,"Mistral-7B","SigLIP-400M","2024/04/26",49.5],[177,"Qwen-VL-Max",null,"QwenLM","","2024/02/02",49.5],[178,"XVERSE-V-13B",13.0,"XVERSE-13B","CLIP ViT-L/14","2024/05/10",49.3],[179,"H2OVL-2B",2.2,"H2O-DANUBE2-1.8B","InternViT-300M","2024/10/31",48.9],[180,"LLaVA-Next-Qwen-32B",33.0,"Qwen-1.5-32B","SigLIP-400M","2024/08/08",48.5],[181,"XGen-MM-Instruct-Interleave-v1.5",4.4,"Phi-3","SigLIP-400M","2024/09/06",48.4],[182,"PaliGemma-3B-mix-448",3.0,"Gemma-2B","SigLIP-400M","2024/05/17",48.3],[183,"HawkVL-2B",2.44,"Qwen2.5-1.5B","QwenViT","2025/06/16",48.1],[184,"360VL-70B",70.0,"Llama-3-70B-Instruct","CLIP ViT-L/14","2024/05/25",48.1],[185,"Gemma3-4B",4.3,"Gemma3-4B","SigLIP-400M","2025/03/19",47.9],[186,"Phi-3-Vision",4.2,"Phi-3","CLIP ViT-L/14","2024/05/31",47.7],[187,"Vintern-3B-beta",3.7,"Qwen-2.5-3B","InternViT-300M","2024/10/24",47.5],[188,"Phi-3.5-Vision",4.0,"Phi-3.5","CLIP ViT-L/14","2024/08/28",47.5],[189,"Qwen2-VL-2B",2.0,"Qwen2-1.5B","QwenViT","2024/09/12",47.5],[190,"GPT-4.1-nano-20250414",null,"","","2025/04/16",47.5],[191,"XGen-MM-Instruct-DPO-v1.5",4.4,"Phi-3","SigLIP-400M","2024/09/06",47.2],[192,"Cambrian-13B",13.0,"Vicuna-v1.5-13B","CLIP ViT-L/14","2024/07/29",47.1],[193,"Mini-InternVL-Chat-2B-V1.5",2.0,"InternLM2-1.8B","InternViT-300M","2024/06/10",46.7],[194,"VITA",47.0,"Mixtral-8x7B","InternViT-300M","2025/01/20",46.6],[195,"Emu3_chat",8.49,"","","2025/01/26",46.6],[196,"Janus-Pro-7B",7.42,"DeepSeek-7B","SigLIP-400M","2025/02/02",46.5],[197,"InternLM-XComposer2-1.8B",2.0,"InternLM2-1.8B","CLIP ViT-L/14","2024/06/09",46.4],[198,"LLaVA-LLaMA-3-8B",8.0,"Llama-3-8B-Instruct","CLIP ViT-L/14","2024/05/07",46.1],[199,"SmolVLM2",2.25,"SmolLM2-1.7M","SigLIP-400M","2025/03/13",46.0],[200,"Claude3-Opus",null,"","","2024/03/28",45.7],[201,"InternVL2-1B",1.0,"Qwen2-0.5B","InternViT-300M","2024/07/11",45.6],[202,"Falcon2-VLM-11B",11.4,"Falcon2-11B","CLIP ViT-L/14","2024/10/30",45.4],[203,"Bunny-Llama3-8B",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/07/18",45.4],[204,"LLaVA-Next-Interleave-7B-DPO",8.0,"Qwen-1.5-7B","SigLIP-400M","2024/07/29",45.3],[205,"Mantis-8B-Idefics2",8.0,"Mistral-7B","SigLIP-400M","2024/08/08",44.8],[206,"LLaVA-Next-Interleave-7B",8.0,"Qwen-1.5-7B","SigLIP-400M","2024/08/08",44.5],[207,"VILA1.5-13B",13.0,"Vicuna-v1.5-13B","SigLIP-400M","2024/08/25",44.2],[208,"Claude3-Sonnet",null,"","","2024/03/28",44.2],[209,"LLaVA-Next-Llama3",8.0,"Llama-3-8B-Instruct","CLIP ViT-L/14","2024/07/29",43.9],[210,"Eagle-X5-13B",15.0,"Vicuna-v1.5-13B","Clip-448
ConvNeXT-1024
SAM-1024
DET-1024
Pix2Struct-1024","2024/09/26",43.7],[211,"Slime-8B",8.0,"Llama-3-8B-Instruct","CLIP ViT-L/14","2024/09/14",43.5],[212,"MolmoE-1B",7.2,"OLMoE-1B-7B-0924","CLIP ViT-L/14","2024/10/21",43.1],[213,"Moondream2",1.9,"SigLIP-400M","Phi-1.5","2024/10/20",42.1],[214,"LLaVA-InternLM2-20B (QLoRA)",20.2,"InternLM2-20B","CLIP ViT-L/14","2024/01/17",41.9],[215,"SmolVLM-Instruct",2.3,"SmolLM2-1.7B","SigLIP-400M","2025/01/27",41.7],[216,"Eagle-X5-7B",9.0,"Vicuna-v1.5-7B","Clip-448
ConvNeXT-1024
SAM-1024
DET-1024
Pix2Struct-1024","2024/09/26",41.7],[217,"Mantis-8B-siglip-llama3",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/08/08",41.3],[218,"Monkey-Chat",9.8,"Qwen-7B","ViT-BigHuge","2024/01/16",40.7],[219,"Emu2_chat",37.0,"Llama-33B","EVA-02-CLIP-E-plus","2024/01/17",40.7],[220,"VILA1.5-3B",3.0,"Sheared-LLaMA-2.7B","SigLIP-400M","2024/08/25",40.6],[221,"Yi-VL-34B",34.6,"Yi-34B","CLIP ViT-H/14","2024/01/25",40.5],[222,"DeepSeek-VL-7B",7.3,"DeekSeek-7B","SAM-B
SigLIP-L","2024/03/21",40.5],[223,"LLaVA-Next-Vicuna-13B",13.4,"Vicuna-v1.5-13B","CLIP ViT-L/14","2024/03/25",40.4],[224,"LLaVA-v1.5-13B (QLoRA)",13.4,"Vicuna-v1.5-13B","CLIP ViT-L/14","2023/12/28",40.1],[225,"CogVLM-17B-Chat",17.0,"Vicuna-v1.5-7B","EVA2-CLIP-E","2024/01/03",39.9],[226,"DeepSeek-VL-1.3B",2.0,"DeekSeek-1B","SAM-B
SigLIP-L","2024/03/21",39.9],[227,"Llama-3-VILA1.5-8B",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/08/25",39.7],[228,"Qwen-VL-Plus",null,"QwenLM","","2024/01/10",39.7],[229,"OmniLMM-12B",12.0,"Zephyr-7B-β","EVA-02-5B","2024/02/07",39.6],[230,"RekaEdge",null,"","","2024/05/31",39.6],[231,"H2OVL-800M",0.83,"H2O-DANUBE3-500M","InternViT-300M","2024/10/31",39.5],[232,"Slime-13B",13.0,"Vicuna-v1.5-13B","CLIP ViT-L/14","2024/09/14",39.4],[233,"SmolVLM-Instruct-DPO",2.3,"SmolLM2-1.7B","SigLIP-400M","2025/01/27",39.2],[234,"Parrot-7B",8.0,"Qwen2-7B","CLIP ViT-L/14","2024/08/22",39.1],[235,"MiniCPM-V-2",2.8,"MiniCPM-2.4B","SigLIP-400M","2024/04/15",39.1],[236,"Vintern-1B-v2",3.7,"Qwen2-0.5B","InternViT-300M","2024/11/16",39.0],[237,"MiMo-VL-7B",8.31,"Mimo-7B","Qwen2.5-ViT","2025/07/02",38.9],[238,"Gemini-1.0-Pro",null,"","","2023/12/23",38.6],[239,"MiniCPM-V",3.0,"MiniCPM-2.4B","SigLIP-400M","2024/02/07",38.6],[240,"LLaVA-Next-Mistral-7B",7.6,"Mistral-7B","CLIP ViT-L/14","2024/03/25",38.4],[241,"ShareCaptioner",8.0,"InternLM-7B","EVA-G","2024/01/03",38.4],[242,"SmolVLM-500M",0.51,"SmolLM2-360M","ViT-93M","2025/01/27",38.3],[243,"ShareGPT4V-13B",13.4,"Vicuna-v1.5-13B","CLIP ViT-L/14","2023/12/08",38.3],[244,"Mantis-8B-clip-llama3",8.0,"Llama-3-8B-Instruct","CLIP ViT-L/14","2024/08/08",38.3],[245,"LLaVA-InternLM2-7B (QLoRA)",8.1,"InternLM2-7B","CLIP ViT-L/14","2024/01/17",38.3],[246,"SmolVLM2-500M",0.51,"SmolLM2-360M","ViT-93M","2025/03/13",38.2],[247,"Claude3-Haiku",null,"","","2024/03/28",38.1],[248,"AKI-4B",4.33,"Phi-3.5","SigLIP-400M","2025/03/25",37.8],[249,"Yi-VL-6B",6.6,"Yi-6B","CLIP ViT-H/14","2024/01/25",37.7],[250,"LLaVA-OneVision-0.5B",1.0,"Qwen2-0.5B","SigLIP-400M","2024/09/16",37.7],[251,"Janus-1.3B",2.1,"DeepSeek-1B","SigLIP-400M","2024/10/24",37.6],[252,"LLaVA-Next-Vicuna-7B",7.1,"Vicuna-v1.5-7B","CLIP ViT-L/14","2024/03/25",37.6],[253,"LLaVA-OneVision-0.5B (SI)",1.0,"Qwen2-0.5B","SigLIP-400M","2024/09/17",37.5],[254,"Slime-7B",7.0,"Vicuna-v1.5-7B","CLIP ViT-L/14","2024/09/14",37.3],[255,"Monkey",9.8,"Qwen-7B","ViT-BigHuge","2024/01/11",37.0],[256,"ShareGPT4V-7B",7.2,"Vicuna-v1.5-7B","CLIP ViT-L/14","2023/12/08",35.7],[257,"TransCore-M",13.4,"PCITransGPT-13B","CLIP ViT-L/14","2024/04/16",35.6],[258,"LLaVA-InternLM-7B (QLoRA)",7.6,"InternLM-7B","CLIP ViT-L/14","2023/12/28",35.5],[259,"Moondream1",1.9,"SigLIP-400M","Phi-1.5","2024/09/26",35.3],[260,"SmolVLM-Synthetic",2.3,"SmolLM2-1.7B","SigLIP-400M","2025/01/27",34.9],[261,"mPLUG-Owl2",8.2,"Llama-2-7B","CLIP ViT-L/14","2023/11/10",34.8],[262,"LLaVA-v1.5-7B (QLoRA)",7.2,"Vicuna-v1.5-7B","CLIP ViT-L/14","2023/12/28",34.6],[263,"SmolVLM-256M",0.26,"SmolLM2-135M","ViT-93M","2025/01/27",34.5],[264,"Qwen-VL-Chat",9.6,"Qwen-7B","ViT-G/16","2023/08/24",34.5],[265,"Mantis-8B-Fuyu",8.0,"Fuyu-8B","","2024/09/07",34.4],[266,"MMAlaya",7.8,"Alaya-7B-Chat","EVA-G","2024/01/29",34.3],[267,"LLaVA-v1.5-13B",13.4,"Vicuna-v1.5-13B","CLIP ViT-L/14","2023/10/05",34.3],[268,"LLaVA-v1.5-7B",7.2,"Vicuna-v1.5-7B","CLIP ViT-L/14","2023/10/05",33.1],[269,"InstructBLIP-7B",8.0,"Vicuna-7B","EVA-G","2023/05/11",32.7],[270,"Qwen-VL",9.6,"Qwen-7B","ViT-G/16","2023/08/24",32.5],[271,"abab6.5s",null,"","","2024/12/11",32.1],[272,"Chameleon-30B",30.0,"","","2024/07/29",31.8],[273,"Chameleon-7B",7.0,"","","2024/07/29",31.1],[274,"SmolVLM2-256M",0.26,"SmolLM2-135M","ViT-93M","2025/03/13",30.9],[275,"LLaVA-v1-7B",7.2,"Llama-7B","CLIP ViT-L/14","2023/04/17",27.1],[276,"OpenFlamingo v2",9.0,"MPT 7B","CLIP ViT-L/14","2023/06/28",26.9],[277,"IDEFICS-80B-Instruct",80.0,"Llama-65B","CLIP ViT-H/14","2023/07/25",26.1],[278,"VisualGLM",8.0,"ChatGLM 6B","EVA-CLIP","2023/05/17",25.9],[279,"PandaGPT-13B",14.0,"Vicuna-13B","ImageBind ViT-H/14","2023/05/25",25.6],[280,"Kosmos2",1.7,"","","2024/10/19",24.9],[281,"IDEFICS-9B-Instruct",9.0,"Llama-7B","CLIP ViT-H/14","2023/07/25",21.6],[282,"MiniGPT-4-v2",8.0,"Llama-2-13B","EVA-G","2023/10/27",21.3],[283,"MiniGPT-4-v1-7B",8.0,"Vicuna-7B","EVA-G","2023/04/20",16.3],[284,"InternLM-XComposer",8.0,"InternLM-7B","EVA-G","2023/09/26",6.9]],"metadata":null},"headers":["1","2","3"],"row_count":[1,"dynamic"],"col_count":[3,"dynamic"],"datatype":["number","html","number","html","html","str","number"],"type":"pandas","latex_delimiters":[{"left":"$$","right":"$$","display":true}],"show_label":true,"height":500,"min_width":160,"interactive":false,"visible":true,"elem_classes":[],"wrap":true,"line_breaks":true,"column_widths":[],"name":"dataframe","_selectable":false},"skip_api":false,"component_class_id":"6a51bb3357f2e94c40fb8d4fbe06aa8e","key":null,"api_info":{"properties":{"headers":{"items":{"type":"string"},"title":"Headers","type":"array"},"data":{"items":{"items":{},"type":"array"},"title":"Data","type":"array"},"metadata":{"anyOf":[{"additionalProperties":{"anyOf":[{"items":{},"type":"array"},{"type":"null"}]},"type":"object"},{"type":"null"}],"default":null,"title":"Metadata"}},"required":["headers","data"],"title":"DataframeData","type":"object"},"example_inputs":{"headers":["a","b"],"data":[["foo","bar"]]}},{"id":224,"type":"textbox","props":{"value":"MMStar","lines":1,"max_lines":20,"label":"MMStar","show_label":true,"container":true,"min_width":160,"visible":false,"autofocus":false,"autoscroll":true,"elem_classes":[],"type":"text","rtl":false,"show_copy_button":false,"name":"textbox","_selectable":false},"skip_api":false,"component_class_id":"d0491bb0fbd427bdb2a4549c4d1ac869","key":null,"api_info":{"type":"string"},"example_inputs":"Hello!!"},{"id":225,"type":"form","props":{"scale":0,"min_width":0,"name":"form"},"skip_api":true,"component_class_id":"43cda85c6ff7a5dd8f83d29496b014ee","key":null},{"id":226,"type":"form","props":{"scale":0,"min_width":0,"name":"form"},"skip_api":true,"component_class_id":"43cda85c6ff7a5dd8f83d29496b014ee","key":null},{"id":227,"type":"tabitem","props":{"label":"📊 RealWorldQA Leaderboard","visible":true,"interactive":true,"id":20,"elem_id":"RealWorldQA","name":"tab"},"skip_api":true,"component_class_id":"18f46968e2b273dc5dbda0fe78433d7e","key":null},{"id":228,"type":"markdown","props":{"value":"## RealWorldQA Evaluation Results\n\n- RealWorldQA is a benchmark designed to evaluate the real-world spatial understanding capabilities of multimodal AI models, contributed by XAI. It assesses how well these models comprehend physical environments. The benchmark consists of 700+ images, each accompanied by a question and a verifiable answer. These images are drawn from real-world scenarios, including those captured from vehicles. The goal is to advance AI models' understanding of our physical world.","show_label":true,"rtl":false,"latex_delimiters":[{"left":"$$","right":"$$","display":true}],"visible":true,"elem_classes":[],"sanitize_html":true,"line_breaks":false,"header_links":false,"show_copy_button":false,"name":"markdown","_selectable":false},"skip_api":false,"component_class_id":"0f35515b9a3362b42bb6721c836157a0","key":null,"api_info":{"type":"string"},"example_inputs":"# Hello!"},{"id":229,"type":"checkboxgroup","props":{"choices":[["Overall","Overall"]],"value":["Overall"],"type":"value","label":"RealWorldQA CheckBoxes","show_label":true,"container":true,"min_width":160,"interactive":true,"visible":true,"elem_classes":[],"name":"checkboxgroup","_selectable":false},"skip_api":false,"component_class_id":"0635a5d3bf87369f1c2c1c69f8a3d0cc","key":null,"api_info":{"items":{"enum":["Overall"],"type":"string"},"title":"Checkbox Group","type":"array"},"example_inputs":["Overall"]},{"id":230,"type":"row","props":{"variant":"default","visible":true,"equal_height":true,"show_progress":false,"name":"row"},"skip_api":true,"component_class_id":"b5cf3d15e2293fb5ccc071d7b8d69f64","key":null},{"id":231,"type":"textbox","props":{"value":"Input the Model Name (fuzzy, case insensitive)","lines":1,"max_lines":20,"label":"Model Name","show_label":true,"container":true,"min_width":160,"interactive":true,"visible":true,"autofocus":false,"autoscroll":true,"elem_classes":[],"type":"text","rtl":false,"show_copy_button":false,"name":"textbox","_selectable":false},"skip_api":false,"component_class_id":"d0491bb0fbd427bdb2a4549c4d1ac869","key":null,"api_info":{"type":"string"},"example_inputs":"Hello!!"},{"id":232,"type":"checkboxgroup","props":{"choices":[["<4B","<4B"],["4B-10B","4B-10B"],["10B-20B","10B-20B"],["20B-40B","20B-40B"],[">40B",">40B"],["Unknown","Unknown"]],"value":["<4B","4B-10B","10B-20B","20B-40B",">40B","Unknown"],"type":"value","label":"Model Size","show_label":true,"container":true,"min_width":160,"interactive":true,"visible":true,"elem_classes":[],"name":"checkboxgroup","_selectable":false},"skip_api":false,"component_class_id":"0635a5d3bf87369f1c2c1c69f8a3d0cc","key":null,"api_info":{"items":{"enum":["<4B","4B-10B","10B-20B","20B-40B",">40B","Unknown"],"type":"string"},"title":"Checkbox Group","type":"array"},"example_inputs":["<4B"]},{"id":233,"type":"checkboxgroup","props":{"choices":[["API","API"],["OpenSource","OpenSource"]],"value":["API","OpenSource"],"type":"value","label":"Model Type","show_label":true,"container":true,"min_width":160,"interactive":true,"visible":true,"elem_classes":[],"name":"checkboxgroup","_selectable":false},"skip_api":false,"component_class_id":"0635a5d3bf87369f1c2c1c69f8a3d0cc","key":null,"api_info":{"items":{"enum":["API","OpenSource"],"type":"string"},"title":"Checkbox Group","type":"array"},"example_inputs":["API"]},{"id":234,"type":"form","props":{"scale":3,"min_width":480,"name":"form"},"skip_api":true,"component_class_id":"43cda85c6ff7a5dd8f83d29496b014ee","key":null},{"id":235,"type":"dataframe","props":{"value":{"headers":["Rank","Method","Param (B)","Language Model","Vision Model","Eval Date","Overall"],"data":[[1,"GPT-4.1-20250414",null,"","","2025/04/16",78.7],[2,"InternVL3-78B",78.4,"Qwen2.5-72B","InternViT-6B-v2.5","2025/04/14",78.4],[3,"GPT-4.1-mini-20250414",null,"","","2025/04/16",77.5],[4,"InternVL2.5-78B-MPO",78.0,"Qwen-2.5-72B","InternViT-6B-v2.5","2024/12/29",77.4],[5,"Qwen2-VL-72B",73.4,"Qwen2-72B","QwenViT","2024/10/28",76.7],[6,"GPT-4o (0806, detail-high)",null,"","","2024/08/08",76.5],[7,"InternVL3-38B",38.4,"Qwen2.5-32B","InternViT-6B-v2.5","2025/04/14",75.8],[8,"Ovis2-34B",34.9,"Qwen2.5-32B","AIMv2-1B","2025/02/18",75.6],[9,"GPT-4o (0513, detail-high)",null,"","","2024/05/31",75.4],[10,"Qwen2.5-VL-72B",73.4,"Qwen2.5-72B","QwenViT","2025/02/02",75.3],[11,"Gemini-2.0-Pro",null,"","","2025/02/27",74.8],[12,"InternVL2.5-38B-MPO",38.0,"Qwen-2.5-32B","InternViT-6B-v2.5","2024/12/28",74.4],[13,"Qwen-VL-Max-0809",72.0,"Qwen2-72B","QwenViT","2024/09/12",74.2],[14,"Ovis2-16B",16.2,"Qwen2.5-14B","AIMv2 Huge","2025/02/18",74.1],[15,"Step-1o",null,"","","2025/01/13",74.1],[16,"LLaVA-OneVision-72B",73.0,"Qwen2-72B","SigLIP-400M","2024/09/19",73.9],[17,"LLaVA-OneVision-72B (SI)",73.0,"Qwen2-72B","SigLIP-400M","2024/09/19",73.7],[18,"InternVL2.5-26B-MPO",26.0,"InternLM2.5-20B","InternViT-6B-v2.5","2024/12/28",73.7],[19,"Molmo-72B",73.3,"Qwen2-72B","CLIP ViT-L/14","2024/10/28",73.7],[20,"Taiyi",null,"","","2024/12/11",73.1],[21,"InternVL2-Llama3-76B",76.0,"Llama-3-70B-Instruct","InternViT-6B","2024/07/19",72.7],[22,"Ovis1.6-Gemma2-27B",28.9,"Gemma2-27B","SigLIP-400M","2024/11/29",72.7],[23,"VARCO-VISION-14B",15.2,"Qwen2.5-14B","SigLIP-400M","2025/01/02",72.5],[24,"Ovis2-8B",8.94,"Qwen2.5-7B","AIMv2 Huge","2025/02/18",72.5],[25,"Gemini-2.0-Flash",null,"","","2025/01/02",72.3],[26,"GLM-4v-Plus-20250111",null,"","","2025/01/25",72.2],[27,"MUG-U-7B",7.0,"","","2025/03/19",71.6],[28,"InternVL3-8B",7.94,"Qwen2.5-7B","InternViT-300M-v2.5","2025/04/14",71.4],[29,"Ovis2-4B",4.62,"Qwen2.5-3B","AIMv2 Huge","2025/02/18",71.1],[30,"InternVL2.5-8B-MPO",8.0,"InternLM2.5-7B","InternViT-300M-v2.5","2024/12/28",71.1],[31,"Molmo-7B-D",8.0,"Qwen2-7B","CLIP ViT-L/14","2024/10/12",71.1],[32,"InternVL3-9B",9.14,"InternLM3-8B","InternViT-300M-v2.5","2025/04/14",71.0],[33,"BailingMM-Pro-0120",81.0,"Bailing-80B","SigLIP-400M","2025/01/25",70.8],[34,"Ovis1.6-Gemma2-9B",10.2,"Gemma2-9B-It","SigLIP-400M","2024/09/19",70.7],[35,"GLM-4v-Plus",null,"","","2024/12/11",70.5],[36,"DeepSeek-VL2",27.5,"DeepSeekMoE-27B","SigLIP-400M","2025/01/01",70.1],[37,"InternVL2-40B",40.0,"Nous-Hermes-2-Yi-34B","InternViT-6B","2024/07/11",70.1],[38,"Qwen-VL-Plus-0809",null,"","","2024/09/17",70.1],[39,"LLaVA-OneVision-7B",8.0,"Qwen2-7B","SigLIP-400M","2024/09/16",69.9],[40,"NVLM-D-72B",79.4,"Qwen2-72B","InternViT-6B","2024/10/19",69.9],[41,"OmChat-v2.0-13B",13.0,"Qwen2-7B","InternViT-6B","2024/08/22",69.8],[42,"InternVL3-14B",15.1,"Qwen2.5-14B","InternViT-300M-v2.5","2025/04/14",69.8],[43,"Step-1.5V",null,"Step-1.5","stepencoder","2024/10/11",69.7],[44,"LLaVA-OneVision-7B (SI)",8.0,"Qwen2-7B","SigLIP-400M","2024/09/17",69.5],[45,"InternVL2.5-8B",8.0,"InternLM2.5-7B","InternViT-300M-v2.5","2024/12/10",69.5],[46,"DeepSeek-VL2-Small",16.1,"DeepSeekMoE-16B","SigLIP-400M","2025/01/01",69.4],[47,"Gemini-1.5-Flash",null,"","","2024/09/16",69.0],[48,"Kimi-VL-A3B-Instruct",16.4,"Moonlight-16B-A3B","MoonViT","2025/04/14",68.8],[49,"GPT-4o (0513, detail-low)",null,"","","2024/05/15",68.6],[50,"Qwen2-VL-7B",8.0,"Qwen2-7B","QwenViT","2024/09/12",68.5],[51,"Aria",25.3,"Aria-MoE","SigLIP-400M","2024/12/05",68.4],[52,"Qwen2.5-VL-7B",8.29,"Qwen2.5-7B","QwenViT","2025/02/02",68.4],[53,"Llama-3.2-90B-Vision-Instruct",88.6,"Llama-3.1-70B","","2024/10/19",68.2],[54,"WeMM",7.0,"InternLM2-7B","SigLIP-400M","2024/06/09",68.1],[55,"InternVL2-26B",26.0,"InternLM2-20B","InternViT-6B","2024/07/11",68.1],[56,"RBDash-v1.5",79.0,"Qwen2-72B","CLIP ViT-L/14
InternViT-6B","2024/11/17",68.1],[57,"GPT-4v (0409, detail-high)",null,"","","2024/05/15",68.0],[58,"MiniCPM-o-2.6",8.67,"Qwen2.5-7B","SigLIP-400M","2025/01/21",68.0],[59,"InternLM-XComposer2.5",8.0,"InternLM2-7B","CLIP ViT-L/14","2024/07/11",67.8],[60,"POINTS-Qwen2.5-7B",8.3,"Qwen-2.5-7B","CLIP ViT-L/14","2024/10/19",67.8],[61,"HunYuan-Standard-Vision",null,"","","2025/01/15",67.7],[62,"POINTS1.5-Qwen2.5-7B",8.3,"Qwen-2.5-7B","NaViT","2024/12/06",67.5],[63,"abab7-preview",null,"","","2024/12/11",67.3],[64,"GLM-4v",null,"","","2024/05/20",67.3],[65,"Cambrian-34B",34.0,"Nous-Hermes-2-Yi-34B","CLIP ViT-L/14","2024/07/18",67.1],[66,"GPT-4o-mini (0718, detail-high)",null,"","","2024/07/20",67.1],[67,"BailingMM-Lite-1203",21.0,"Bailing-20B","SigLIP-400M","2024/12/08",67.1],[68,"VITA-1.5",8.3,"Qwen2-7B","InternViT-300M","2025/01/01",66.9],[69,"CongRong",null,"","","2024/06/26",66.9],[70,"Ovis1.5-Gemma2-9B",11.4,"Gemma2-9B-It","SigLIP-400M","2024/08/04",66.9],[71,"BlueLM-V-3B",3.0,"BlueLM-3B","SigLIP-400M","2024/10/30",66.7],[72,"Ovis1.6-Llama3.2-3B",4.1,"Llama-3.2-3B","SigLIP-400M","2024/10/24",66.7],[73,"MMAlaya2",26.0,"InternLM2-20B","InternViT-6B","2024/08/27",66.5],[74,"POINTS-Yi-1.5-9B",9.5,"Yi-1.5-9B","CLIP ViT-L/14","2024/10/11",66.3],[75,"granite-vision-3.3-2b",2.98,"granite-3.1-2b-instruct","SigLIP2-400M","2025/06/20",66.0],[76,"GLM-4v-9B",9.0,"GLM-4-9B","EVA-02-5B","2024/06/14",66.0],[77,"Ovis2-2B",2.46,"Qwen2.5-1.5B","AIMv2 Large","2025/02/18",66.0],[78,"LLaVA-Next-Yi-34B",34.8,"Yi-34B","CLIP ViT-L/14","2024/03/25",66.0],[79,"Claude3.5-Sonnet-20241022",null,"","","2024/11/06",65.8],[80,"InternVL-Chat-V1.5",26.0,"InternLM2-20B","InternViT-6B","2024/04/17",65.6],[81,"Step-1.5V-mini",null,"","","2024/12/11",65.6],[82,"Qwen2.5-VL-3B",3.75,"Qwen2.5-3B","QwenViT","2025/02/02",65.5],[83,"VILA1.5-40B",40.0,"Yi-34B","InternViT-6B","2024/08/25",65.4],[84,"Pixtral-12B",13.0,"Nemo-12B","ViT-400M","2024/09/16",65.4],[85,"InternVL3-2B",2.09,"Qwen2.5-1.5B","InternViT-300M-v2.5","2025/04/14",65.1],[86,"Aquila-VL-2B",2.2,"Qwen-2.5-1.5B","SigLIP-400M","2024/10/24",65.0],[87,"MiniCPM-V-2.6",8.0,"Qwen2-7B","SigLIP-400M","2024/08/08",65.0],[88,"Eagle-X5-34B-Chat",36.8,"Yi-34B","Clip-448
ConvNeXT-1024
SAM-1024
DET-1024
Pix2Struct-1024","2024/11/29",64.6],[89,"InternVL2.5-4B-MPO",4.0,"Qwen-2.5-3B","InternViT-300M-v2.5","2024/12/28",64.4],[90,"DeepSeek-VL2-Tiny",3.4,"DeepSeekMoE-3B","SigLIP-400M","2025/01/01",64.3],[91,"Ovis1.5-Llama3-8B",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/07/29",64.2],[92,"InternVL2-8B-MPO-CoT",8.0,"InternLM2.5-7B","InternViT-300M","2024/11/25",64.2],[93,"InternVL2-8B",8.0,"InternLM2.5-7B","InternViT-300M","2024/07/11",64.2],[94,"Gemini-1.5-Pro",null,"","","2024/06/10",64.1],[95,"Phi-4-MultiModal",5.57,"Phi-4-Mini","SigLIP-400M","2025/03/13",64.1],[96,"Ovis2-1B",1.27,"Qwen2.5-0.5B","AIMv2 Large","2025/02/18",63.9],[97,"Eagle-X5-7B",9.0,"Vicuna-v1.5-7B","Clip-448
ConvNeXT-1024
SAM-1024
DET-1024
Pix2Struct-1024","2024/09/26",63.8],[98,"InternLM-XComposer2",7.0,"InternLM2-7B","CLIP ViT-L/14","2024/01/26",63.8],[99,"Llama-3-MixSense-v1.1",8.0,"Llama-3-8B-Instruct","Florence-2-Large-FT","2024/08/21",63.5],[100,"MiniCPM-Llama3-V2.5",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/05/27",63.5],[101,"granite-vision-3.2-2b",2.98,"granite-3.1-2b-instruct","SigLip","2025/06/20",63.4],[102,"InternLM-XComposer2-4KHD",7.0,"InternLM2-7B","CLIP ViT-L/14","2024/06/09",63.3],[103,"Llama-3.2-11B-Vision-Instruct",11.0,"Llama-3.1-8B","","2024/10/07",63.3],[104,"XinYuan-VL-2B-Instruct",2.0,"Qwen2-1.5B","QwenViT","2024/09/27",63.1],[105,"InternVL2-8B-MPO",8.0,"InternLM2.5-7B","InternViT-300M","2024/11/25",63.1],[106,"grok-2-vision-1212",null,"","","2025/03/03",63.0],[107,"moonshot-v1-8k",null,"","","2025/03/03",63.0],[108,"GPT-4v (1106, detail-high)",null,"","","2024/04/22",63.0],[109,"CogVLM2-19B-Chat",19.0,"Llama-3-8B-Instruct","EVA2-CLIP-E","2024/05/31",62.9],[110,"Eagle-X5-13B",15.0,"Vicuna-v1.5-13B","Clip-448
ConvNeXT-1024
SAM-1024
DET-1024
Pix2Struct-1024","2024/09/26",62.9],[111,"H2OVL-2B",2.2,"H2O-DANUBE2-1.8B","InternViT-300M","2024/10/31",62.9],[112,"Idefics3-8B-Llama3",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/08/27",62.6],[113,"Gemma3-27B",27.4,"Gemma3-27B","SigLIP-400M","2025/03/19",62.5],[114,"360VL-70B",70.0,"Llama-3-70B-Instruct","CLIP ViT-L/14","2024/05/25",62.4],[115,"Molmo-7B-O",8.0,"Qwen2-7B","CLIP ViT-L/14","2024/10/20",62.2],[116,"SAIL-VL-2B",2.1,"Qwen2.5-1.5B","InternViT-300M","2024/12/25",62.0],[117,"GPT-4.1-nano-20250414",null,"","","2025/04/16",61.7],[118,"XGen-MM-Instruct-DPO-v1.5",4.4,"Phi-3","SigLIP-400M","2024/09/06",61.6],[119,"LLaVA-Next-Qwen-32B",33.0,"Qwen-1.5-32B","SigLIP-400M","2024/08/08",61.4],[120,"GPT-4v (0409, detail-low)",null,"","","2024/05/15",61.4],[121,"InternVL2.5-2B-MPO",2.0,"InternLM2.5-1.8B","InternViT-300M-v2.5","2024/12/28",61.3],[122,"Qwen-VL-Max",null,"QwenLM","","2024/02/02",61.3],[123,"XGen-MM-Instruct-Interleave-v1.5",4.4,"Phi-3","SigLIP-400M","2024/09/06",61.2],[124,"Falcon2-VLM-11B",11.4,"Falcon2-11B","CLIP ViT-L/14","2024/10/30",61.2],[125,"Yi-Vision",null,"","","2024/08/03",60.9],[126,"XVERSE-V-13B",13.0,"XVERSE-13B","CLIP ViT-L/14","2024/05/10",60.8],[127,"Mini-InternVL-Chat-4B-V1.5",4.0,"Phi-3","InternViT-300M","2024/06/10",60.8],[128,"Qwen2-VL-2B",2.0,"Qwen2-1.5B","QwenViT","2024/09/12",60.7],[129,"IDEFICS2-8B",8.0,"Mistral-7B","SigLIP-400M","2024/04/26",60.7],[130,"InternVL2-4B",4.0,"Phi-3","InternViT-300M","2024/07/11",60.5],[131,"Bunny-Llama3-8B",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/07/18",60.4],[132,"Gemini-1.0-Pro",null,"","","2023/12/23",60.4],[133,"LLaVA-Next-Interleave-7B-DPO",8.0,"Qwen-1.5-7B","SigLIP-400M","2024/07/29",60.4],[134,"CogVLM-17B-Chat",17.0,"Vicuna-v1.5-7B","EVA2-CLIP-E","2024/01/03",60.3],[135,"Claude3.5-Sonnet",null,"","","2024/06/24",60.1],[136,"LLaVA-Next-Mistral-7B",7.6,"Mistral-7B","CLIP ViT-L/14","2024/03/25",60.0],[137,"Cambrian-8B",8.0,"Vicuna-v1.5-7B","CLIP ViT-L/14","2024/07/11",60.0],[138,"Mantis-8B-Idefics2",8.0,"Mistral-7B","SigLIP-400M","2024/08/08",59.5],[139,"Gemma3-12B",12.2,"Gemma3-12B","SigLIP-400M","2025/03/19",59.1],[140,"Phi-3-Vision",4.2,"Phi-3","CLIP ViT-L/14","2024/05/31",58.8],[141,"Ross-Qwen2-7B",8.2,"Qwen2-7B","CLIP ViT-L/14","2025/01/17",58.7],[142,"Cambrian-13B",13.0,"Vicuna-v1.5-13B","CLIP ViT-L/14","2024/07/29",58.6],[143,"MiMo-VL-7B",8.31,"Mimo-7B","Qwen2.5-ViT","2025/07/02",58.6],[144,"OmniLMM-12B",12.0,"Zephyr-7B-β","EVA-02-5B","2024/02/07",58.4],[145,"LLaVA-Next-Llama3",8.0,"Llama-3-8B-Instruct","CLIP ViT-L/14","2024/07/29",58.4],[146,"Vintern-3B-beta",3.7,"Qwen-2.5-3B","InternViT-300M","2024/10/24",58.2],[147,"Slime-8B",8.0,"Llama-3-8B-Instruct","CLIP ViT-L/14","2024/09/14",58.0],[148,"Mini-InternVL-Chat-2B-V1.5",2.0,"InternLM2-1.8B","InternViT-300M","2024/06/10",57.9],[149,"LLaVA-Next-Vicuna-7B",7.1,"Vicuna-v1.5-7B","CLIP ViT-L/14","2024/03/25",57.8],[150,"LLaVA-Next-Interleave-7B",8.0,"Qwen-1.5-7B","SigLIP-400M","2024/08/08",57.6],[151,"LLaVA-Next-Vicuna-13B",13.4,"Vicuna-v1.5-13B","CLIP ViT-L/14","2024/03/25",57.6],[152,"MolmoE-1B",7.2,"OLMoE-1B-7B-0924","CLIP ViT-L/14","2024/10/21",57.5],[153,"SmolVLM2",2.25,"SmolLM2-1.7M","SigLIP-400M","2025/03/13",57.5],[154,"InternVL2-2B",2.0,"InternLM2-1.8B","InternViT-300M","2024/07/11",57.4],[155,"Emu2_chat",37.0,"Llama-33B","EVA-02-CLIP-E-plus","2024/01/17",57.3],[156,"Emu3_chat",8.49,"","","2025/01/26",57.1],[157,"MiniMonkey",2.2,"InternLM2-1.8B","InternViT-300M","2024/09/26",57.1],[158,"TransCore-M",13.4,"PCITransGPT-13B","CLIP ViT-L/14","2024/04/16",57.1],[159,"InternVL3-1B",0.94,"Qwen2.5-0.5B","InternViT-300M-v2.5","2025/04/14",57.0],[160,"RekaEdge",null,"","","2024/05/31",57.0],[161,"bailingMM-mini",17.0,"bailing-mini","bailingMM-encoder-1B
InternViT-6B","2024/10/24",57.0],[162,"InternVL2.5-1B-MPO",1.0,"Qwen-2.5-0.5B","InternViT-300M-v2.5","2024/12/28",57.0],[163,"ShareGPT4V-13B",13.4,"Vicuna-v1.5-13B","CLIP ViT-L/14","2023/12/08",57.0],[164,"LLaVA-InternLM2-20B (QLoRA)",20.2,"InternLM2-20B","CLIP ViT-L/14","2024/01/17",56.9],[165,"LLaVA-LLaMA-3-8B",8.0,"Llama-3-8B-Instruct","CLIP ViT-L/14","2024/05/07",56.7],[166,"AKI-4B",4.33,"Phi-3.5","SigLIP-400M","2025/03/25",56.6],[167,"GPT-4v (1106, detail-low)",null,"","","2023/12/23",56.5],[168,"InternLM-XComposer2-1.8B",2.0,"InternLM2-1.8B","CLIP ViT-L/14","2024/06/09",56.3],[169,"LLaVA-InternLM2-7B (QLoRA)",8.1,"InternLM2-7B","CLIP ViT-L/14","2024/01/17",56.1],[170,"RekaFlash",null,"","","2024/05/07",55.9],[171,"MiniCPM-V-2",2.8,"MiniCPM-2.4B","SigLIP-400M","2024/04/15",55.8],[172,"Gemma3-4B",4.3,"Gemma3-4B","SigLIP-400M","2025/03/19",55.6],[173,"Claude3.7-Sonnet",null,"","","2025/02/27",55.4],[174,"LLaVA-v1.5-13B",13.4,"Vicuna-v1.5-13B","CLIP ViT-L/14","2023/10/05",55.3],[175,"PaliGemma-3B-mix-448",3.0,"Gemma-2B","SigLIP-400M","2024/05/17",55.2],[176,"ShareGPT4V-7B",7.2,"Vicuna-v1.5-7B","CLIP ViT-L/14","2023/12/08",54.9],[177,"SmolVLM-Instruct",2.3,"SmolLM2-1.7B","SigLIP-400M","2025/01/27",54.9],[178,"Yi-VL-34B",34.6,"Yi-34B","CLIP ViT-H/14","2024/01/25",54.8],[179,"Parrot-7B",8.0,"Qwen2-7B","CLIP ViT-L/14","2024/08/22",54.8],[180,"LLaVA-v1.5-7B",7.2,"Vicuna-v1.5-7B","CLIP ViT-L/14","2023/10/05",54.8],[181,"DeepSeek-VL-7B",7.3,"DeekSeek-7B","SAM-B
SigLIP-L","2024/03/21",54.2],[182,"LLaVA-v1.5-7B (QLoRA)",7.2,"Vicuna-v1.5-7B","CLIP ViT-L/14","2023/12/28",53.7],[183,"Phi-3.5-Vision",4.0,"Phi-3.5","CLIP ViT-L/14","2024/08/28",53.6],[184,"Yi-VL-6B",6.6,"Yi-6B","CLIP ViT-H/14","2024/01/25",53.5],[185,"VILA1.5-13B",13.0,"Vicuna-v1.5-13B","SigLIP-400M","2024/08/25",53.3],[186,"VILA1.5-3B",3.0,"Sheared-LLaMA-2.7B","SigLIP-400M","2024/08/25",53.2],[187,"Slime-13B",13.0,"Vicuna-v1.5-13B","CLIP ViT-L/14","2024/09/14",53.2],[188,"H2OVL-800M",0.83,"H2O-DANUBE3-500M","InternViT-300M","2024/10/31",52.7],[189,"ShareCaptioner",8.0,"InternLM-7B","EVA-G","2024/01/03",52.7],[190,"Monkey-Chat",9.8,"Qwen-7B","ViT-BigHuge","2024/01/16",52.4],[191,"Mantis-8B-clip-llama3",8.0,"Llama-3-8B-Instruct","CLIP ViT-L/14","2024/08/08",52.3],[192,"Mantis-8B-siglip-llama3",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/08/08",52.2],[193,"LLaVA-v1.5-13B (QLoRA)",13.4,"Vicuna-v1.5-13B","CLIP ViT-L/14","2023/12/28",52.0],[194,"Slime-7B",7.0,"Vicuna-v1.5-7B","CLIP ViT-L/14","2024/09/14",51.9],[195,"LLaVA-OneVision-0.5B",1.0,"Qwen2-0.5B","SigLIP-400M","2024/09/16",51.8],[196,"Monkey",9.8,"Qwen-7B","ViT-BigHuge","2024/01/11",51.6],[197,"LLaVA-InternLM-7B (QLoRA)",7.6,"InternLM-7B","CLIP ViT-L/14","2023/12/28",51.2],[198,"MiniCPM-V",3.0,"MiniCPM-2.4B","SigLIP-400M","2024/02/07",51.2],[199,"mPLUG-Owl2",8.2,"Llama-2-7B","CLIP ViT-L/14","2023/11/10",50.8],[200,"Claude3-Sonnet",null,"","","2024/03/28",50.7],[201,"Moondream1",1.9,"SigLIP-400M","Phi-1.5","2024/09/26",50.7],[202,"InternVL2-1B",1.0,"Qwen2-0.5B","InternViT-300M","2024/07/11",50.2],[203,"SmolVLM2-500M",0.51,"SmolLM2-360M","ViT-93M","2025/03/13",49.9],[204,"DeepSeek-VL-1.3B",2.0,"DeekSeek-1B","SAM-B
SigLIP-L","2024/03/21",49.7],[205,"Moondream2",1.9,"SigLIP-400M","Phi-1.5","2024/10/20",49.3],[206,"Qwen-VL-Chat",9.6,"Qwen-7B","ViT-G/16","2023/08/24",49.3],[207,"IDEFICS-80B-Instruct",80.0,"Llama-65B","CLIP ViT-H/14","2023/07/25",49.0],[208,"Claude3-Opus",null,"","","2024/03/28",48.4],[209,"SmolVLM-Instruct-DPO",2.3,"SmolLM2-1.7B","SigLIP-400M","2025/01/27",47.6],[210,"LLaVA-OneVision-0.5B (SI)",1.0,"Qwen2-0.5B","SigLIP-400M","2024/09/17",46.1],[211,"LLaVA-v1-7B",7.2,"Llama-7B","CLIP ViT-L/14","2023/04/17",45.8],[212,"Claude3-Haiku",null,"","","2024/03/28",45.5],[213,"MMAlaya",7.8,"Alaya-7B-Chat","EVA-G","2024/01/29",45.2],[214,"Qwen-VL-Plus",null,"QwenLM","","2024/01/10",44.6],[215,"SmolVLM-Synthetic",2.3,"SmolLM2-1.7B","SigLIP-400M","2025/01/27",44.2],[216,"Mantis-8B-Fuyu",8.0,"Fuyu-8B","","2024/09/07",43.7],[217,"Llama-3-VILA1.5-8B",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/08/25",43.4],[218,"Janus-Pro-7B",7.42,"DeepSeek-7B","SigLIP-400M","2025/02/02",42.7],[219,"IDEFICS-9B-Instruct",9.0,"Llama-7B","CLIP ViT-H/14","2023/07/25",42.1],[220,"Janus-1.3B",2.1,"DeepSeek-1B","SigLIP-400M","2024/10/24",41.8],[221,"SmolVLM-500M",0.51,"SmolLM2-360M","ViT-93M","2025/01/27",41.0],[222,"VisualGLM",8.0,"ChatGLM 6B","EVA-CLIP","2023/05/17",39.9],[223,"Chameleon-30B",30.0,"","","2024/07/29",39.2],[224,"Chameleon-7B",7.0,"","","2024/07/29",39.0],[225,"Qwen-VL",9.6,"Qwen-7B","ViT-G/16","2023/08/24",37.8],[226,"InstructBLIP-7B",8.0,"Vicuna-7B","EVA-G","2023/05/11",36.9],[227,"SmolVLM2-256M",0.26,"SmolLM2-135M","ViT-93M","2025/03/13",35.2],[228,"OpenFlamingo v2",9.0,"MPT 7B","CLIP ViT-L/14","2023/06/28",35.2],[229,"PandaGPT-13B",14.0,"Vicuna-13B","ImageBind ViT-H/14","2023/05/25",32.8],[230,"Kosmos2",1.7,"","","2024/10/19",32.7],[231,"SmolVLM-256M",0.26,"SmolLM2-135M","ViT-93M","2025/01/27",32.2],[232,"MiniGPT-4-v2",8.0,"Llama-2-13B","EVA-G","2023/10/27",30.7],[233,"abab6.5s",null,"","","2024/12/11",30.3],[234,"MiniGPT-4-v1-7B",8.0,"Vicuna-7B","EVA-G","2023/04/20",21.3],[235,"InternLM-XComposer",8.0,"InternLM-7B","EVA-G","2023/09/26",10.2]],"metadata":null},"headers":["1","2","3"],"row_count":[1,"dynamic"],"col_count":[3,"dynamic"],"datatype":["number","html","number","html","html","str","number"],"type":"pandas","latex_delimiters":[{"left":"$$","right":"$$","display":true}],"show_label":true,"height":500,"min_width":160,"interactive":false,"visible":true,"elem_classes":[],"wrap":true,"line_breaks":true,"column_widths":[],"name":"dataframe","_selectable":false},"skip_api":false,"component_class_id":"6a51bb3357f2e94c40fb8d4fbe06aa8e","key":null,"api_info":{"properties":{"headers":{"items":{"type":"string"},"title":"Headers","type":"array"},"data":{"items":{"items":{},"type":"array"},"title":"Data","type":"array"},"metadata":{"anyOf":[{"additionalProperties":{"anyOf":[{"items":{},"type":"array"},{"type":"null"}]},"type":"object"},{"type":"null"}],"default":null,"title":"Metadata"}},"required":["headers","data"],"title":"DataframeData","type":"object"},"example_inputs":{"headers":["a","b"],"data":[["foo","bar"]]}},{"id":236,"type":"textbox","props":{"value":"RealWorldQA","lines":1,"max_lines":20,"label":"RealWorldQA","show_label":true,"container":true,"min_width":160,"visible":false,"autofocus":false,"autoscroll":true,"elem_classes":[],"type":"text","rtl":false,"show_copy_button":false,"name":"textbox","_selectable":false},"skip_api":false,"component_class_id":"d0491bb0fbd427bdb2a4549c4d1ac869","key":null,"api_info":{"type":"string"},"example_inputs":"Hello!!"},{"id":237,"type":"form","props":{"scale":0,"min_width":0,"name":"form"},"skip_api":true,"component_class_id":"43cda85c6ff7a5dd8f83d29496b014ee","key":null},{"id":238,"type":"form","props":{"scale":0,"min_width":0,"name":"form"},"skip_api":true,"component_class_id":"43cda85c6ff7a5dd8f83d29496b014ee","key":null},{"id":239,"type":"tabitem","props":{"label":"📊 TextVQA_VAL Leaderboard","visible":true,"interactive":true,"id":21,"elem_id":"TextVQA_VAL","name":"tab"},"skip_api":true,"component_class_id":"18f46968e2b273dc5dbda0fe78433d7e","key":null},{"id":240,"type":"markdown","props":{"value":"## TextVQA Evaluation Results\n\n- TextVQA is a dataset to benchmark visual reasoning based on text in images. TextVQA requires models to read and reason about text in images to answer questions about them. Specifically, models need to incorporate a new modality of text present in the images and reason over it to answer TextVQA questions.\n- Note that some models may not be able to generate standardized responses based on the prompt. We currently do not have reports for these models.","show_label":true,"rtl":false,"latex_delimiters":[{"left":"$$","right":"$$","display":true}],"visible":true,"elem_classes":[],"sanitize_html":true,"line_breaks":false,"header_links":false,"show_copy_button":false,"name":"markdown","_selectable":false},"skip_api":false,"component_class_id":"0f35515b9a3362b42bb6721c836157a0","key":null,"api_info":{"type":"string"},"example_inputs":"# Hello!"},{"id":241,"type":"checkboxgroup","props":{"choices":[["Overall","Overall"]],"value":["Overall"],"type":"value","label":"TextVQA_VAL CheckBoxes","show_label":true,"container":true,"min_width":160,"interactive":true,"visible":true,"elem_classes":[],"name":"checkboxgroup","_selectable":false},"skip_api":false,"component_class_id":"0635a5d3bf87369f1c2c1c69f8a3d0cc","key":null,"api_info":{"items":{"enum":["Overall"],"type":"string"},"title":"Checkbox Group","type":"array"},"example_inputs":["Overall"]},{"id":242,"type":"row","props":{"variant":"default","visible":true,"equal_height":true,"show_progress":false,"name":"row"},"skip_api":true,"component_class_id":"b5cf3d15e2293fb5ccc071d7b8d69f64","key":null},{"id":243,"type":"textbox","props":{"value":"Input the Model Name (fuzzy, case insensitive)","lines":1,"max_lines":20,"label":"Model Name","show_label":true,"container":true,"min_width":160,"interactive":true,"visible":true,"autofocus":false,"autoscroll":true,"elem_classes":[],"type":"text","rtl":false,"show_copy_button":false,"name":"textbox","_selectable":false},"skip_api":false,"component_class_id":"d0491bb0fbd427bdb2a4549c4d1ac869","key":null,"api_info":{"type":"string"},"example_inputs":"Hello!!"},{"id":244,"type":"checkboxgroup","props":{"choices":[["<4B","<4B"],["4B-10B","4B-10B"],["10B-20B","10B-20B"],["20B-40B","20B-40B"],[">40B",">40B"],["Unknown","Unknown"]],"value":["<4B","4B-10B","10B-20B","20B-40B",">40B","Unknown"],"type":"value","label":"Model Size","show_label":true,"container":true,"min_width":160,"interactive":true,"visible":true,"elem_classes":[],"name":"checkboxgroup","_selectable":false},"skip_api":false,"component_class_id":"0635a5d3bf87369f1c2c1c69f8a3d0cc","key":null,"api_info":{"items":{"enum":["<4B","4B-10B","10B-20B","20B-40B",">40B","Unknown"],"type":"string"},"title":"Checkbox Group","type":"array"},"example_inputs":["<4B"]},{"id":245,"type":"checkboxgroup","props":{"choices":[["API","API"],["OpenSource","OpenSource"]],"value":["API","OpenSource"],"type":"value","label":"Model Type","show_label":true,"container":true,"min_width":160,"interactive":true,"visible":true,"elem_classes":[],"name":"checkboxgroup","_selectable":false},"skip_api":false,"component_class_id":"0635a5d3bf87369f1c2c1c69f8a3d0cc","key":null,"api_info":{"items":{"enum":["API","OpenSource"],"type":"string"},"title":"Checkbox Group","type":"array"},"example_inputs":["API"]},{"id":246,"type":"form","props":{"scale":3,"min_width":480,"name":"form"},"skip_api":true,"component_class_id":"43cda85c6ff7a5dd8f83d29496b014ee","key":null},{"id":247,"type":"dataframe","props":{"value":{"headers":["Rank","Method","Param (B)","Language Model","Vision Model","Eval Date","Overall"],"data":[[1,"Kimi-VL-A3B-Instruct",16.4,"Moonlight-16B-A3B","MoonViT","2025/04/14",92.5],[2,"Qwen2-VL-72B",73.4,"Qwen2-72B","QwenViT","2024/10/28",85.5],[3,"InternVL2-Llama3-76B",76.0,"Llama-3-70B-Instruct","InternViT-6B","2024/07/19",84.2],[4,"InternVL2-40B",40.0,"Nous-Hermes-2-Yi-34B","InternViT-6B","2024/07/11",83.5],[5,"InternVL2-26B",26.0,"InternLM2-20B","InternViT-6B","2024/07/11",82.5],[6,"MUG-U-7B",7.0,"","","2025/03/19",82.4],[7,"InternVL3-14B",15.1,"Qwen2.5-14B","InternViT-300M-v2.5","2025/04/14",82.2],[8,"InternVL3-8B",7.94,"Qwen2.5-7B","InternViT-300M-v2.5","2025/04/14",82.1],[9,"Taiyi",null,"","","2024/12/11",82.0],[10,"Ovis1.6-Gemma2-27B",28.9,"Gemma2-27B","SigLIP-400M","2024/11/29",80.9],[11,"MMAlaya2",26.0,"InternLM2-20B","InternViT-6B","2024/08/27",80.5],[12,"InternVL-Chat-V1.5",26.0,"InternLM2-20B","InternViT-6B","2024/04/17",80.4],[13,"InternVL3-2B",2.09,"Qwen2.5-1.5B","InternViT-300M-v2.5","2025/04/14",78.6],[14,"LLaVA-OneVision-7B (SI)",8.0,"Qwen2-7B","SigLIP-400M","2024/09/17",78.5],[15,"BlueLM-V-3B",3.0,"BlueLM-3B","SigLIP-400M","2024/10/30",78.4],[16,"MiniCPM-V-2.6",8.0,"Qwen2-7B","SigLIP-400M","2024/08/08",78.3],[17,"CogVLM-17B-Chat",17.0,"Vicuna-v1.5-7B","EVA2-CLIP-E","2024/01/03",78.2],[18,"InternLM-XComposer2.5",8.0,"InternLM2-7B","CLIP ViT-L/14","2024/07/11",78.2],[19,"Ovis1.6-Gemma2-9B",10.2,"Gemma2-9B-It","SigLIP-400M","2024/09/19",78.2],[20,"Phi-4-MultiModal",5.57,"Phi-4-Mini","SigLIP-400M","2025/03/13",76.9],[21,"Aquila-VL-2B",2.2,"Qwen-2.5-1.5B","SigLIP-400M","2024/10/24",76.5],[22,"Pixtral-12B",13.0,"Nemo-12B","ViT-400M","2024/09/16",75.7],[23,"InternVL3-1B",0.94,"Qwen2.5-0.5B","InternViT-300M-v2.5","2025/04/14",75.0],[24,"H2OVL-2B",2.2,"H2O-DANUBE2-1.8B","InternViT-300M","2024/10/31",74.8],[25,"InternVL2-4B",4.0,"Phi-3","InternViT-300M","2024/07/11",74.7],[26,"Ovis1.6-Llama3.2-3B",4.1,"Llama-3.2-3B","SigLIP-400M","2024/10/24",74.2],[27,"Ovis1.5-Llama3-8B",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/07/29",74.0],[28,"InternVL2-2B",2.0,"InternLM2-1.8B","InternViT-300M","2024/07/11",73.4],[29,"Idefics3-8B-Llama3",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/08/27",73.2],[30,"MiniCPM-V-2",2.8,"MiniCPM-2.4B","SigLIP-400M","2024/04/15",73.2],[31,"SmolVLM2",2.25,"SmolLM2-1.7M","SigLIP-400M","2025/03/13",73.0],[32,"Cambrian-8B",8.0,"Vicuna-v1.5-7B","CLIP ViT-L/14","2024/07/11",72.6],[33,"Phi-3-Vision",4.2,"Phi-3","CLIP ViT-L/14","2024/05/31",72.4],[34,"SmolVLM-Instruct",2.3,"SmolLM2-1.7B","SigLIP-400M","2025/01/27",72.1],[35,"Cambrian-34B",34.0,"Nous-Hermes-2-Yi-34B","CLIP ViT-L/14","2024/07/18",72.1],[36,"Eagle-X5-13B",15.0,"Vicuna-v1.5-13B","Clip-448
ConvNeXT-1024
SAM-1024
DET-1024
Pix2Struct-1024","2024/09/26",71.8],[37,"GPT-4.1-20250414",null,"","","2025/04/16",71.0],[38,"InternVL2-1B",1.0,"Qwen2-0.5B","InternViT-300M","2024/07/11",70.9],[39,"Eagle-X5-7B",9.0,"Vicuna-v1.5-7B","Clip-448
ConvNeXT-1024
SAM-1024
DET-1024
Pix2Struct-1024","2024/09/26",70.5],[40,"Molmo-7B-D",8.0,"Qwen2-7B","CLIP ViT-L/14","2024/10/12",70.3],[41,"InternLM-XComposer2",7.0,"InternLM2-7B","CLIP ViT-L/14","2024/01/26",69.7],[42,"LLaVA-Next-Yi-34B",34.8,"Yi-34B","CLIP ViT-L/14","2024/03/25",69.3],[43,"H2OVL-800M",0.83,"H2O-DANUBE3-500M","InternViT-300M","2024/10/31",69.0],[44,"IDEFICS2-8B",8.0,"Mistral-7B","SigLIP-400M","2024/04/26",68.9],[45,"VILA1.5-40B",40.0,"Yi-34B","InternViT-6B","2024/08/25",68.8],[46,"PaliGemma-3B-mix-448",3.0,"Gemma-2B","SigLIP-400M","2024/05/17",68.1],[47,"Emu2_chat",37.0,"Llama-33B","EVA-02-CLIP-E-plus","2024/01/17",67.6],[48,"Vintern-3B-beta",3.7,"Qwen-2.5-3B","InternViT-300M","2024/10/24",67.2],[49,"LLaVA-Next-Vicuna-13B",13.4,"Vicuna-v1.5-13B","CLIP ViT-L/14","2024/03/25",66.9],[50,"Gemma3-27B",27.4,"Gemma3-27B","SigLIP-400M","2025/03/19",66.7],[51,"Gemma3-12B",12.2,"Gemma3-12B","SigLIP-400M","2025/03/19",66.5],[52,"LLaVA-OneVision-0.5B (SI)",1.0,"Qwen2-0.5B","SigLIP-400M","2024/09/17",66.3],[53,"Monkey",9.8,"Qwen-7B","ViT-BigHuge","2024/01/11",65.8],[54,"Monkey-Chat",9.8,"Qwen-7B","ViT-BigHuge","2024/01/16",65.5],[55,"LLaVA-Next-Llama3",8.0,"Llama-3-8B-Instruct","CLIP ViT-L/14","2024/07/29",65.3],[56,"LLaVA-Next-Mistral-7B",7.6,"Mistral-7B","CLIP ViT-L/14","2024/03/25",65.2],[57,"GPT-4.1-mini-20250414",null,"","","2025/04/16",64.9],[58,"DeepSeek-VL-7B",7.3,"DeekSeek-7B","SAM-B
SigLIP-L","2024/03/21",64.9],[59,"LLaVA-Next-Vicuna-7B",7.1,"Vicuna-v1.5-7B","CLIP ViT-L/14","2024/03/25",63.8],[60,"Mantis-8B-Idefics2",8.0,"Mistral-7B","SigLIP-400M","2024/08/08",63.5],[61,"Qwen-VL",9.6,"Qwen-7B","ViT-G/16","2023/08/24",63.1],[62,"Falcon2-VLM-11B",11.4,"Falcon2-11B","CLIP ViT-L/14","2024/10/30",62.9],[63,"OmniLMM-12B",12.0,"Zephyr-7B-β","EVA-02-5B","2024/02/07",62.3],[64,"Bunny-Llama3-8B",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/07/18",62.1],[65,"Gemini-1.5-Flash",null,"","","2024/09/16",61.6],[66,"MolmoE-1B",7.2,"OLMoE-1B-7B-0924","CLIP ViT-L/14","2024/10/21",61.5],[67,"LLaVA-Next-Qwen-32B",33.0,"Qwen-1.5-32B","SigLIP-400M","2024/08/08",61.0],[68,"GPT-4.1-nano-20250414",null,"","","2025/04/16",60.9],[69,"Qwen-VL-Chat",9.6,"Qwen-7B","ViT-G/16","2023/08/24",60.7],[70,"POINTS-Yi-1.5-9B",9.5,"Yi-1.5-9B","CLIP ViT-L/14","2024/10/11",60.6],[71,"SmolVLM2-500M",0.51,"SmolLM2-360M","ViT-93M","2025/03/13",60.3],[72,"SmolVLM-500M",0.51,"SmolLM2-360M","ViT-93M","2025/01/27",60.2],[73,"POINTS-Qwen2.5-7B",8.3,"Qwen-2.5-7B","CLIP ViT-L/14","2024/10/19",60.0],[74,"Molmo-7B-O",8.0,"Qwen2-7B","CLIP ViT-L/14","2024/10/20",59.8],[75,"SmolVLM-Instruct-DPO",2.3,"SmolLM2-1.7B","SigLIP-400M","2025/01/27",59.2],[76,"DeepSeek-VL-1.3B",2.0,"DeekSeek-1B","SAM-B
SigLIP-L","2024/03/21",57.8],[77,"Gemma3-4B",4.3,"Gemma3-4B","SigLIP-400M","2025/03/19",57.7],[78,"LLaVA-Next-Interleave-7B",8.0,"Qwen-1.5-7B","SigLIP-400M","2024/08/08",56.7],[79,"MiniCPM-V",3.0,"MiniCPM-2.4B","SigLIP-400M","2024/02/07",56.6],[80,"LLaVA-Next-Interleave-7B-DPO",8.0,"Qwen-1.5-7B","SigLIP-400M","2024/07/29",56.5],[81,"mPLUG-Owl2",8.2,"Llama-2-7B","CLIP ViT-L/14","2023/11/10",56.4],[82,"TransCore-M",13.4,"PCITransGPT-13B","CLIP ViT-L/14","2024/04/16",55.2],[83,"ShareGPT4V-13B",13.4,"Vicuna-v1.5-13B","CLIP ViT-L/14","2023/12/08",52.7],[84,"LLaVA-LLaMA-3-8B",8.0,"Llama-3-8B-Instruct","CLIP ViT-L/14","2024/05/07",52.0],[85,"Slime-13B",13.0,"Vicuna-v1.5-13B","CLIP ViT-L/14","2024/09/14",51.7],[86,"ShareGPT4V-7B",7.2,"Vicuna-v1.5-7B","CLIP ViT-L/14","2023/12/08",51.1],[87,"Janus-1.3B",2.1,"DeepSeek-1B","SigLIP-400M","2024/10/24",50.7],[88,"LLaVA-v1.5-13B (QLoRA)",13.4,"Vicuna-v1.5-13B","CLIP ViT-L/14","2023/12/28",50.7],[89,"Mantis-8B-siglip-llama3",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/08/08",50.5],[90,"SmolVLM2-256M",0.26,"SmolLM2-135M","ViT-93M","2025/03/13",50.4],[91,"LLaVA-InternLM2-20B (QLoRA)",20.2,"InternLM2-20B","CLIP ViT-L/14","2024/01/17",50.4],[92,"SmolVLM-256M",0.26,"SmolLM2-135M","ViT-93M","2025/01/27",50.2],[93,"Slime-7B",7.0,"Vicuna-v1.5-7B","CLIP ViT-L/14","2024/09/14",49.7],[94,"LLaVA-v1.5-7B (QLoRA)",7.2,"Vicuna-v1.5-7B","CLIP ViT-L/14","2023/12/28",49.7],[95,"Slime-8B",8.0,"Llama-3-8B-Instruct","CLIP ViT-L/14","2024/09/14",49.4],[96,"LLaVA-InternLM2-7B (QLoRA)",8.1,"InternLM2-7B","CLIP ViT-L/14","2024/01/17",49.3],[97,"Mantis-8B-Fuyu",8.0,"Fuyu-8B","","2024/09/07",49.0],[98,"LLaVA-v1.5-13B",13.4,"Vicuna-v1.5-13B","CLIP ViT-L/14","2023/10/05",48.9],[99,"Moondream1",1.9,"SigLIP-400M","Phi-1.5","2024/09/26",46.1],[100,"LLaVA-InternLM-7B (QLoRA)",7.6,"InternLM-7B","CLIP ViT-L/14","2023/12/28",45.8],[101,"Mantis-8B-clip-llama3",8.0,"Llama-3-8B-Instruct","CLIP ViT-L/14","2024/08/08",45.6],[102,"LLaVA-v1.5-7B",7.2,"Vicuna-v1.5-7B","CLIP ViT-L/14","2023/10/05",45.5],[103,"Yi-VL-6B",6.6,"Yi-6B","CLIP ViT-H/14","2024/01/25",44.8],[104,"AKI-4B",4.33,"Phi-3.5","SigLIP-400M","2025/03/25",43.9],[105,"Yi-VL-34B",34.6,"Yi-34B","CLIP ViT-H/14","2024/01/25",42.5],[106,"SmolVLM-Synthetic",2.3,"SmolLM2-1.7B","SigLIP-400M","2025/01/27",40.5],[107,"InternLM-XComposer",8.0,"InternLM-7B","EVA-G","2023/09/26",38.5],[108,"ShareCaptioner",8.0,"InternLM-7B","EVA-G","2024/01/03",38.0],[109,"Gemini-1.0-Pro",null,"","","2023/12/23",36.9],[110,"InstructBLIP-7B",8.0,"Vicuna-7B","EVA-G","2023/05/11",33.6],[111,"MMAlaya",7.8,"Alaya-7B-Chat","EVA-G","2024/01/29",27.1],[112,"OpenFlamingo v2",9.0,"MPT 7B","CLIP ViT-L/14","2023/06/28",16.3],[113,"Kosmos2",1.7,"","","2024/10/19",14.7],[114,"Qwen-VL-Max",null,"QwenLM","","2024/02/02",8.6],[115,"Qwen-VL-Plus",null,"QwenLM","","2024/01/10",8.4],[116,"Chameleon-30B",30.0,"","","2024/07/29",6.6],[117,"Chameleon-7B",7.0,"","","2024/07/29",4.8],[118,"CogVLM2-19B-Chat",19.0,"Llama-3-8B-Instruct","EVA2-CLIP-E","2024/05/31",4.5],[119,"IDEFICS-9B-Instruct",9.0,"Llama-7B","CLIP ViT-H/14","2023/07/25",1.0],[120,"MiniGPT-4-v1-7B",8.0,"Vicuna-7B","EVA-G","2023/04/20",0.6],[121,"MiniGPT-4-v2",8.0,"Llama-2-13B","EVA-G","2023/10/27",0.0],[122,"PandaGPT-13B",14.0,"Vicuna-13B","ImageBind ViT-H/14","2023/05/25",0.0],[123,"VisualGLM",8.0,"ChatGLM 6B","EVA-CLIP","2023/05/17",0.0],[124,"IDEFICS-80B-Instruct",80.0,"Llama-65B","CLIP ViT-H/14","2023/07/25",0.0],[125,"GPT-4v (1106, detail-low)",null,"","","2023/12/23",0.0]],"metadata":null},"headers":["1","2","3"],"row_count":[1,"dynamic"],"col_count":[3,"dynamic"],"datatype":["number","html","number","html","html","str","number"],"type":"pandas","latex_delimiters":[{"left":"$$","right":"$$","display":true}],"show_label":true,"height":500,"min_width":160,"interactive":false,"visible":true,"elem_classes":[],"wrap":true,"line_breaks":true,"column_widths":[],"name":"dataframe","_selectable":false},"skip_api":false,"component_class_id":"6a51bb3357f2e94c40fb8d4fbe06aa8e","key":null,"api_info":{"properties":{"headers":{"items":{"type":"string"},"title":"Headers","type":"array"},"data":{"items":{"items":{},"type":"array"},"title":"Data","type":"array"},"metadata":{"anyOf":[{"additionalProperties":{"anyOf":[{"items":{},"type":"array"},{"type":"null"}]},"type":"object"},{"type":"null"}],"default":null,"title":"Metadata"}},"required":["headers","data"],"title":"DataframeData","type":"object"},"example_inputs":{"headers":["a","b"],"data":[["foo","bar"]]}},{"id":248,"type":"textbox","props":{"value":"TextVQA_VAL","lines":1,"max_lines":20,"label":"TextVQA_VAL","show_label":true,"container":true,"min_width":160,"visible":false,"autofocus":false,"autoscroll":true,"elem_classes":[],"type":"text","rtl":false,"show_copy_button":false,"name":"textbox","_selectable":false},"skip_api":false,"component_class_id":"d0491bb0fbd427bdb2a4549c4d1ac869","key":null,"api_info":{"type":"string"},"example_inputs":"Hello!!"},{"id":249,"type":"form","props":{"scale":0,"min_width":0,"name":"form"},"skip_api":true,"component_class_id":"43cda85c6ff7a5dd8f83d29496b014ee","key":null},{"id":250,"type":"form","props":{"scale":0,"min_width":0,"name":"form"},"skip_api":true,"component_class_id":"43cda85c6ff7a5dd8f83d29496b014ee","key":null},{"id":251,"type":"tabitem","props":{"label":"📊 ChartQA_TEST Leaderboard","visible":true,"interactive":true,"id":22,"elem_id":"ChartQA_TEST","name":"tab"},"skip_api":true,"component_class_id":"18f46968e2b273dc5dbda0fe78433d7e","key":null},{"id":252,"type":"markdown","props":{"value":"## ChartQA Evaluation Results\n\n- ChartQA is a benchmark for question answering about charts with visual and logical reasoning. \n- Note that some models may not be able to generate standardized responses based on the prompt. We currently do not have reports for these models.","show_label":true,"rtl":false,"latex_delimiters":[{"left":"$$","right":"$$","display":true}],"visible":true,"elem_classes":[],"sanitize_html":true,"line_breaks":false,"header_links":false,"show_copy_button":false,"name":"markdown","_selectable":false},"skip_api":false,"component_class_id":"0f35515b9a3362b42bb6721c836157a0","key":null,"api_info":{"type":"string"},"example_inputs":"# Hello!"},{"id":253,"type":"checkboxgroup","props":{"choices":[["Overall","Overall"],["test_augmented","test_augmented"],["test_human","test_human"]],"value":["Overall"],"type":"value","label":"ChartQA_TEST CheckBoxes","show_label":true,"container":true,"min_width":160,"interactive":true,"visible":true,"elem_classes":[],"name":"checkboxgroup","_selectable":false},"skip_api":false,"component_class_id":"0635a5d3bf87369f1c2c1c69f8a3d0cc","key":null,"api_info":{"items":{"enum":["Overall","test_augmented","test_human"],"type":"string"},"title":"Checkbox Group","type":"array"},"example_inputs":["Overall"]},{"id":254,"type":"row","props":{"variant":"default","visible":true,"equal_height":true,"show_progress":false,"name":"row"},"skip_api":true,"component_class_id":"b5cf3d15e2293fb5ccc071d7b8d69f64","key":null},{"id":255,"type":"textbox","props":{"value":"Input the Model Name (fuzzy, case insensitive)","lines":1,"max_lines":20,"label":"Model Name","show_label":true,"container":true,"min_width":160,"interactive":true,"visible":true,"autofocus":false,"autoscroll":true,"elem_classes":[],"type":"text","rtl":false,"show_copy_button":false,"name":"textbox","_selectable":false},"skip_api":false,"component_class_id":"d0491bb0fbd427bdb2a4549c4d1ac869","key":null,"api_info":{"type":"string"},"example_inputs":"Hello!!"},{"id":256,"type":"checkboxgroup","props":{"choices":[["<4B","<4B"],["4B-10B","4B-10B"],["10B-20B","10B-20B"],["20B-40B","20B-40B"],[">40B",">40B"],["Unknown","Unknown"]],"value":["<4B","4B-10B","10B-20B","20B-40B",">40B","Unknown"],"type":"value","label":"Model Size","show_label":true,"container":true,"min_width":160,"interactive":true,"visible":true,"elem_classes":[],"name":"checkboxgroup","_selectable":false},"skip_api":false,"component_class_id":"0635a5d3bf87369f1c2c1c69f8a3d0cc","key":null,"api_info":{"items":{"enum":["<4B","4B-10B","10B-20B","20B-40B",">40B","Unknown"],"type":"string"},"title":"Checkbox Group","type":"array"},"example_inputs":["<4B"]},{"id":257,"type":"checkboxgroup","props":{"choices":[["API","API"],["OpenSource","OpenSource"]],"value":["API","OpenSource"],"type":"value","label":"Model Type","show_label":true,"container":true,"min_width":160,"interactive":true,"visible":true,"elem_classes":[],"name":"checkboxgroup","_selectable":false},"skip_api":false,"component_class_id":"0635a5d3bf87369f1c2c1c69f8a3d0cc","key":null,"api_info":{"items":{"enum":["API","OpenSource"],"type":"string"},"title":"Checkbox Group","type":"array"},"example_inputs":["API"]},{"id":258,"type":"form","props":{"scale":3,"min_width":480,"name":"form"},"skip_api":true,"component_class_id":"43cda85c6ff7a5dd8f83d29496b014ee","key":null},{"id":259,"type":"dataframe","props":{"value":{"headers":["Rank","Method","Param (B)","Language Model","Vision Model","Eval Date","Overall"],"data":[[1,"Qwen2-VL-72B",73.4,"Qwen2-72B","QwenViT","2024/10/28",88.2],[2,"InternVL2-Llama3-76B",76.0,"Llama-3-70B-Instruct","InternViT-6B","2024/07/19",88.1],[3,"InternVL3-14B",15.1,"Qwen2.5-14B","InternViT-300M-v2.5","2025/04/14",87.8],[4,"Kimi-VL-A3B-Instruct",16.4,"Moonlight-16B-A3B","MoonViT","2025/04/14",87.7],[5,"MUG-U-7B",7.0,"","","2025/03/19",86.0],[6,"InternVL3-8B",7.94,"Qwen2.5-7B","InternViT-300M-v2.5","2025/04/14",85.8],[7,"Ovis1.6-Gemma2-27B",28.9,"Gemma2-27B","SigLIP-400M","2024/11/29",85.3],[8,"InternVL2-26B",26.0,"InternLM2-20B","InternViT-6B","2024/07/11",85.1],[9,"InternVL-Chat-V1.5",26.0,"InternLM2-20B","InternViT-6B","2024/04/17",83.9],[10,"InternVL2-40B",40.0,"Nous-Hermes-2-Yi-34B","InternViT-6B","2024/07/11",83.8],[11,"MMAlaya2",26.0,"InternLM2-20B","InternViT-6B","2024/08/27",83.6],[12,"Phi-4-MultiModal",5.57,"Phi-4-Mini","SigLIP-400M","2025/03/13",83.0],[13,"MiniCPM-V-2.6",8.0,"Qwen2-7B","SigLIP-400M","2024/08/08",82.4],[14,"Phi-3-Vision",4.2,"Phi-3","CLIP ViT-L/14","2024/05/31",81.8],[15,"Taiyi",null,"","","2024/12/11",81.2],[16,"Ovis1.6-Gemma2-9B",10.2,"Gemma2-9B-It","SigLIP-400M","2024/09/19",81.1],[17,"LLaVA-OneVision-7B (SI)",8.0,"Qwen2-7B","SigLIP-400M","2024/09/17",80.9],[18,"InternVL2-4B",4.0,"Phi-3","InternViT-300M","2024/07/11",80.7],[19,"Ovis1.5-Llama3-8B",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/07/29",76.4],[20,"InternVL3-2B",2.09,"Qwen2.5-1.5B","InternViT-300M-v2.5","2025/04/14",76.0],[21,"Ovis1.6-Llama3.2-3B",4.1,"Llama-3.2-3B","SigLIP-400M","2024/10/24",75.6],[22,"Cambrian-34B",34.0,"Nous-Hermes-2-Yi-34B","CLIP ViT-L/14","2024/07/18",73.7],[23,"Cambrian-8B",8.0,"Vicuna-v1.5-7B","CLIP ViT-L/14","2024/07/11",72.6],[24,"Pixtral-12B",13.0,"Nemo-12B","ViT-400M","2024/09/16",72.2],[25,"InternLM-XComposer2",7.0,"InternLM2-7B","CLIP ViT-L/14","2024/01/26",71.8],[26,"SmolVLM-Instruct",2.3,"SmolLM2-1.7B","SigLIP-400M","2025/01/27",71.8],[27,"InternVL2-2B",2.0,"InternLM2-1.8B","InternViT-300M","2024/07/11",71.7],[28,"Eagle-X5-13B",15.0,"Vicuna-v1.5-13B","Clip-448
ConvNeXT-1024
SAM-1024
DET-1024
Pix2Struct-1024","2024/09/26",69.6],[29,"SmolVLM2",2.25,"SmolLM2-1.7M","SigLIP-400M","2025/03/13",68.7],[30,"LLaVA-Next-Llama3",8.0,"Llama-3-8B-Instruct","CLIP ViT-L/14","2024/07/29",68.7],[31,"Vintern-3B-beta",3.7,"Qwen-2.5-3B","InternViT-300M","2024/10/24",68.3],[32,"InternVL3-1B",0.94,"Qwen2.5-0.5B","InternViT-300M-v2.5","2025/04/14",68.1],[33,"InternVL2-1B",1.0,"Qwen2-0.5B","InternViT-300M","2024/07/11",67.8],[34,"LLaVA-Next-Yi-34B",34.8,"Yi-34B","CLIP ViT-L/14","2024/03/25",67.6],[35,"VILA1.5-40B",40.0,"Yi-34B","InternViT-6B","2024/08/25",67.2],[36,"Eagle-X5-7B",9.0,"Vicuna-v1.5-7B","Clip-448
ConvNeXT-1024
SAM-1024
DET-1024
Pix2Struct-1024","2024/09/26",66.4],[37,"CogVLM-17B-Chat",17.0,"Vicuna-v1.5-7B","EVA2-CLIP-E","2024/01/03",65.5],[38,"Falcon2-VLM-11B",11.4,"Falcon2-11B","CLIP ViT-L/14","2024/10/30",64.0],[39,"Mantis-8B-Idefics2",8.0,"Mistral-7B","SigLIP-400M","2024/08/08",63.8],[40,"SmolVLM-500M",0.51,"SmolLM2-360M","ViT-93M","2025/01/27",62.8],[41,"LLaVA-Next-Vicuna-13B",13.4,"Vicuna-v1.5-13B","CLIP ViT-L/14","2024/03/25",61.4],[42,"LLaVA-OneVision-0.5B (SI)",1.0,"Qwen2-0.5B","SigLIP-400M","2024/09/17",60.5],[43,"SmolVLM2-256M",0.26,"SmolLM2-135M","ViT-93M","2025/03/13",59.6],[44,"SmolVLM2-500M",0.51,"SmolLM2-360M","ViT-93M","2025/03/13",59.6],[45,"Monkey-Chat",9.8,"Qwen-7B","ViT-BigHuge","2024/01/16",59.5],[46,"H2OVL-2B",2.2,"H2O-DANUBE2-1.8B","InternViT-300M","2024/10/31",59.4],[47,"DeepSeek-VL-7B",7.3,"DeekSeek-7B","SAM-B
SigLIP-L","2024/03/21",59.1],[48,"Monkey",9.8,"Qwen-7B","ViT-BigHuge","2024/01/11",59.0],[49,"Qwen-VL",9.6,"Qwen-7B","ViT-G/16","2023/08/24",59.0],[50,"SmolVLM-Instruct-DPO",2.3,"SmolLM2-1.7B","SigLIP-400M","2025/01/27",58.0],[51,"POINTS-Yi-1.5-9B",9.5,"Yi-1.5-9B","CLIP ViT-L/14","2024/10/11",58.0],[52,"SmolVLM-256M",0.26,"SmolLM2-135M","ViT-93M","2025/01/27",55.6],[53,"MiniCPM-V-2",2.8,"MiniCPM-2.4B","SigLIP-400M","2024/04/15",55.6],[54,"LLaVA-Next-Vicuna-7B",7.1,"Vicuna-v1.5-7B","CLIP ViT-L/14","2024/03/25",54.3],[55,"Mantis-8B-Fuyu",8.0,"Fuyu-8B","","2024/09/07",53.3],[56,"LLaVA-Next-Qwen-32B",33.0,"Qwen-1.5-32B","SigLIP-400M","2024/08/08",53.0],[57,"LLaVA-Next-Mistral-7B",7.6,"Mistral-7B","CLIP ViT-L/14","2024/03/25",51.8],[58,"LLaVA-LLaMA-3-8B",8.0,"Llama-3-8B-Instruct","CLIP ViT-L/14","2024/05/07",50.4],[59,"Qwen-VL-Chat",9.6,"Qwen-7B","ViT-G/16","2023/08/24",49.8],[60,"LLaVA-Next-Interleave-7B",8.0,"Qwen-1.5-7B","SigLIP-400M","2024/08/08",49.2],[61,"LLaVA-Next-Interleave-7B-DPO",8.0,"Qwen-1.5-7B","SigLIP-400M","2024/07/29",49.0],[62,"POINTS-Qwen2.5-7B",8.3,"Qwen-2.5-7B","CLIP ViT-L/14","2024/10/19",48.8],[63,"MolmoE-1B",7.2,"OLMoE-1B-7B-0924","CLIP ViT-L/14","2024/10/21",48.0],[64,"DeepSeek-VL-1.3B",2.0,"DeekSeek-1B","SAM-B
SigLIP-L","2024/03/21",47.4],[65,"MiniCPM-V",3.0,"MiniCPM-2.4B","SigLIP-400M","2024/02/07",44.2],[66,"Molmo-7B-D",8.0,"Qwen2-7B","CLIP ViT-L/14","2024/10/12",43.7],[67,"H2OVL-800M",0.83,"H2O-DANUBE3-500M","InternViT-300M","2024/10/31",43.4],[68,"Mantis-8B-siglip-llama3",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/08/08",42.9],[69,"Idefics3-8B-Llama3",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/08/27",40.4],[70,"Slime-8B",8.0,"Llama-3-8B-Instruct","CLIP ViT-L/14","2024/09/14",39.2],[71,"Gemma3-12B",12.2,"Gemma3-12B","SigLIP-400M","2025/03/19",37.2],[72,"Molmo-7B-O",8.0,"Qwen2-7B","CLIP ViT-L/14","2024/10/20",36.5],[73,"Slime-7B",7.0,"Vicuna-v1.5-7B","CLIP ViT-L/14","2024/09/14",33.9],[74,"PaliGemma-3B-mix-448",3.0,"Gemma-2B","SigLIP-400M","2024/05/17",33.7],[75,"Gemma3-4B",4.3,"Gemma3-4B","SigLIP-400M","2025/03/19",33.7],[76,"GPT-4.1-mini-20250414",null,"","","2025/04/16",33.7],[77,"GPT-4.1-20250414",null,"","","2025/04/16",33.3],[78,"CogVLM2-19B-Chat",19.0,"Llama-3-8B-Instruct","EVA2-CLIP-E","2024/05/31",33.0],[79,"Aquila-VL-2B",2.2,"Qwen-2.5-1.5B","SigLIP-400M","2024/10/24",32.0],[80,"GPT-4.1-nano-20250414",null,"","","2025/04/16",30.3],[81,"Bunny-Llama3-8B",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/07/18",30.1],[82,"Gemma3-27B",27.4,"Gemma3-27B","SigLIP-400M","2025/03/19",30.1],[83,"Gemini-1.5-Flash",null,"","","2024/09/16",29.7],[84,"TransCore-M",13.4,"PCITransGPT-13B","CLIP ViT-L/14","2024/04/16",28.0],[85,"Emu2_chat",37.0,"Llama-33B","EVA-02-CLIP-E-plus","2024/01/17",26.8],[86,"Slime-13B",13.0,"Vicuna-v1.5-13B","CLIP ViT-L/14","2024/09/14",25.2],[87,"ShareGPT4V-13B",13.4,"Vicuna-v1.5-13B","CLIP ViT-L/14","2023/12/08",24.6],[88,"mPLUG-Owl2",8.2,"Llama-2-7B","CLIP ViT-L/14","2023/11/10",22.8],[89,"OmniLMM-12B",12.0,"Zephyr-7B-β","EVA-02-5B","2024/02/07",22.7],[90,"Janus-1.3B",2.1,"DeepSeek-1B","SigLIP-400M","2024/10/24",22.5],[91,"ShareGPT4V-7B",7.2,"Vicuna-v1.5-7B","CLIP ViT-L/14","2023/12/08",21.3],[92,"LLaVA-v1.5-13B (QLoRA)",13.4,"Vicuna-v1.5-13B","CLIP ViT-L/14","2023/12/28",19.0],[93,"LLaVA-v1.5-7B (QLoRA)",7.2,"Vicuna-v1.5-7B","CLIP ViT-L/14","2023/12/28",18.7],[94,"LLaVA-v1.5-13B",13.4,"Vicuna-v1.5-13B","CLIP ViT-L/14","2023/10/05",18.2],[95,"LLaVA-v1.5-7B",7.2,"Vicuna-v1.5-7B","CLIP ViT-L/14","2023/10/05",17.8],[96,"LLaVA-InternLM2-20B (QLoRA)",20.2,"InternLM2-20B","CLIP ViT-L/14","2024/01/17",17.6],[97,"AKI-4B",4.33,"Phi-3.5","SigLIP-400M","2025/03/25",16.2],[98,"LLaVA-InternLM2-7B (QLoRA)",8.1,"InternLM2-7B","CLIP ViT-L/14","2024/01/17",16.0],[99,"LLaVA-InternLM-7B (QLoRA)",7.6,"InternLM-7B","CLIP ViT-L/14","2023/12/28",15.8],[100,"Yi-VL-6B",6.6,"Yi-6B","CLIP ViT-H/14","2024/01/25",15.5],[101,"Moondream1",1.9,"SigLIP-400M","Phi-1.5","2024/09/26",14.4],[102,"SmolVLM-Synthetic",2.3,"SmolLM2-1.7B","SigLIP-400M","2025/01/27",14.2],[103,"Yi-VL-34B",34.6,"Yi-34B","CLIP ViT-H/14","2024/01/25",14.0],[104,"InstructBLIP-7B",8.0,"Vicuna-7B","EVA-G","2023/05/11",10.9],[105,"MMAlaya",7.8,"Alaya-7B-Chat","EVA-G","2024/01/29",10.2],[106,"Kosmos2",1.7,"","","2024/10/19",5.9],[107,"Chameleon-30B",30.0,"","","2024/07/29",2.9],[108,"Chameleon-7B",7.0,"","","2024/07/29",2.6],[109,"Llama-3.2-11B-Vision-Instruct",11.0,"Llama-3.1-8B","","2024/10/07",0.0]],"metadata":null},"headers":["1","2","3"],"row_count":[1,"dynamic"],"col_count":[3,"dynamic"],"datatype":["number","html","number","html","html","str","number"],"type":"pandas","latex_delimiters":[{"left":"$$","right":"$$","display":true}],"show_label":true,"height":500,"min_width":160,"interactive":false,"visible":true,"elem_classes":[],"wrap":true,"line_breaks":true,"column_widths":[],"name":"dataframe","_selectable":false},"skip_api":false,"component_class_id":"6a51bb3357f2e94c40fb8d4fbe06aa8e","key":null,"api_info":{"properties":{"headers":{"items":{"type":"string"},"title":"Headers","type":"array"},"data":{"items":{"items":{},"type":"array"},"title":"Data","type":"array"},"metadata":{"anyOf":[{"additionalProperties":{"anyOf":[{"items":{},"type":"array"},{"type":"null"}]},"type":"object"},{"type":"null"}],"default":null,"title":"Metadata"}},"required":["headers","data"],"title":"DataframeData","type":"object"},"example_inputs":{"headers":["a","b"],"data":[["foo","bar"]]}},{"id":260,"type":"textbox","props":{"value":"ChartQA_TEST","lines":1,"max_lines":20,"label":"ChartQA_TEST","show_label":true,"container":true,"min_width":160,"visible":false,"autofocus":false,"autoscroll":true,"elem_classes":[],"type":"text","rtl":false,"show_copy_button":false,"name":"textbox","_selectable":false},"skip_api":false,"component_class_id":"d0491bb0fbd427bdb2a4549c4d1ac869","key":null,"api_info":{"type":"string"},"example_inputs":"Hello!!"},{"id":261,"type":"form","props":{"scale":0,"min_width":0,"name":"form"},"skip_api":true,"component_class_id":"43cda85c6ff7a5dd8f83d29496b014ee","key":null},{"id":262,"type":"form","props":{"scale":0,"min_width":0,"name":"form"},"skip_api":true,"component_class_id":"43cda85c6ff7a5dd8f83d29496b014ee","key":null},{"id":263,"type":"tabitem","props":{"label":"📊 OCRVQA_TESTCORE Leaderboard","visible":true,"interactive":true,"id":23,"elem_id":"OCRVQA_TESTCORE","name":"tab"},"skip_api":true,"component_class_id":"18f46968e2b273dc5dbda0fe78433d7e","key":null},{"id":264,"type":"markdown","props":{"value":"## OCRVQA Evaluation Results\n\n- OCRVQA is a benchmark for visual question answering by reading text in images. It presents a large-scale dataset, OCR-VQA-200K, comprising over 200,000 images of book covers. The study combines techniques from the Optical Character Recognition (OCR) and Visual Question Answering (VQA) domains to address the challenges associated with this new task and dataset. \n- Note that some models may not be able to generate standardized responses based on the prompt. We currently do not have reports for these models.","show_label":true,"rtl":false,"latex_delimiters":[{"left":"$$","right":"$$","display":true}],"visible":true,"elem_classes":[],"sanitize_html":true,"line_breaks":false,"header_links":false,"show_copy_button":false,"name":"markdown","_selectable":false},"skip_api":false,"component_class_id":"0f35515b9a3362b42bb6721c836157a0","key":null,"api_info":{"type":"string"},"example_inputs":"# Hello!"},{"id":265,"type":"checkboxgroup","props":{"choices":[["Overall","Overall"],["Arts & Photography","Arts & Photography"],["Biographies & Memoirs","Biographies & Memoirs"],["Business & Money","Business & Money"],["Calendars","Calendars"],["Children's Books","Children's Books"],["Christian Books & Bibles","Christian Books & Bibles"],["Comics & Graphic Novels","Comics & Graphic Novels"],["Computers & Technology","Computers & Technology"],["Cookbooks, Food & Wine","Cookbooks, Food & Wine"],["Crafts, Hobbies & Home","Crafts, Hobbies & Home"],["Education & Teaching","Education & Teaching"],["Engineering & Transportation","Engineering & Transportation"],["Gay & Lesbian","Gay & Lesbian"],["Health, Fitness & Dieting","Health, Fitness & Dieting"],["History","History"],["Humor & Entertainment","Humor & Entertainment"],["Law","Law"],["Literature & Fiction","Literature & Fiction"],["Medical Books","Medical Books"],["Mystery, Thriller & Suspense","Mystery, Thriller & Suspense"],["Parenting & Relationships","Parenting & Relationships"],["Politics & Social Sciences","Politics & Social Sciences"],["Reference","Reference"],["Religion & Spirituality","Religion & Spirituality"],["Romance","Romance"],["Science & Math","Science & Math"],["Science Fiction & Fantasy","Science Fiction & Fantasy"],["Self-Help","Self-Help"],["Sports & Outdoors","Sports & Outdoors"],["Teen & Young Adult","Teen & Young Adult"],["Test Preparation","Test Preparation"],["Travel","Travel"]],"value":["Overall"],"type":"value","label":"OCRVQA_TESTCORE CheckBoxes","show_label":true,"container":true,"min_width":160,"interactive":true,"visible":true,"elem_classes":[],"name":"checkboxgroup","_selectable":false},"skip_api":false,"component_class_id":"0635a5d3bf87369f1c2c1c69f8a3d0cc","key":null,"api_info":{"items":{"enum":["Overall","Arts & Photography","Biographies & Memoirs","Business & Money","Calendars","Children's Books","Christian Books & Bibles","Comics & Graphic Novels","Computers & Technology","Cookbooks, Food & Wine","Crafts, Hobbies & Home","Education & Teaching","Engineering & Transportation","Gay & Lesbian","Health, Fitness & Dieting","History","Humor & Entertainment","Law","Literature & Fiction","Medical Books","Mystery, Thriller & Suspense","Parenting & Relationships","Politics & Social Sciences","Reference","Religion & Spirituality","Romance","Science & Math","Science Fiction & Fantasy","Self-Help","Sports & Outdoors","Teen & Young Adult","Test Preparation","Travel"],"type":"string"},"title":"Checkbox Group","type":"array"},"example_inputs":["Overall"]},{"id":266,"type":"row","props":{"variant":"default","visible":true,"equal_height":true,"show_progress":false,"name":"row"},"skip_api":true,"component_class_id":"b5cf3d15e2293fb5ccc071d7b8d69f64","key":null},{"id":267,"type":"textbox","props":{"value":"Input the Model Name (fuzzy, case insensitive)","lines":1,"max_lines":20,"label":"Model Name","show_label":true,"container":true,"min_width":160,"interactive":true,"visible":true,"autofocus":false,"autoscroll":true,"elem_classes":[],"type":"text","rtl":false,"show_copy_button":false,"name":"textbox","_selectable":false},"skip_api":false,"component_class_id":"d0491bb0fbd427bdb2a4549c4d1ac869","key":null,"api_info":{"type":"string"},"example_inputs":"Hello!!"},{"id":268,"type":"checkboxgroup","props":{"choices":[["<4B","<4B"],["4B-10B","4B-10B"],["10B-20B","10B-20B"],["20B-40B","20B-40B"],[">40B",">40B"],["Unknown","Unknown"]],"value":["<4B","4B-10B","10B-20B","20B-40B",">40B","Unknown"],"type":"value","label":"Model Size","show_label":true,"container":true,"min_width":160,"interactive":true,"visible":true,"elem_classes":[],"name":"checkboxgroup","_selectable":false},"skip_api":false,"component_class_id":"0635a5d3bf87369f1c2c1c69f8a3d0cc","key":null,"api_info":{"items":{"enum":["<4B","4B-10B","10B-20B","20B-40B",">40B","Unknown"],"type":"string"},"title":"Checkbox Group","type":"array"},"example_inputs":["<4B"]},{"id":269,"type":"checkboxgroup","props":{"choices":[["API","API"],["OpenSource","OpenSource"]],"value":["API","OpenSource"],"type":"value","label":"Model Type","show_label":true,"container":true,"min_width":160,"interactive":true,"visible":true,"elem_classes":[],"name":"checkboxgroup","_selectable":false},"skip_api":false,"component_class_id":"0635a5d3bf87369f1c2c1c69f8a3d0cc","key":null,"api_info":{"items":{"enum":["API","OpenSource"],"type":"string"},"title":"Checkbox Group","type":"array"},"example_inputs":["API"]},{"id":270,"type":"form","props":{"scale":3,"min_width":480,"name":"form"},"skip_api":true,"component_class_id":"43cda85c6ff7a5dd8f83d29496b014ee","key":null},{"id":271,"type":"dataframe","props":{"value":{"headers":["Rank","Method","Param (B)","Language Model","Vision Model","Eval Date","Overall"],"data":[[1,"Kimi-VL-A3B-Instruct",16.4,"Moonlight-16B-A3B","MoonViT","2025/04/14",82.0],[2,"MUG-U-7B",7.0,"","","2025/03/19",80.9],[3,"Ovis1.6-Gemma2-27B",28.9,"Gemma2-27B","SigLIP-400M","2024/11/29",75.1],[4,"Qwen2-VL-72B",73.4,"Qwen2-72B","QwenViT","2024/10/28",73.7],[5,"Taiyi",null,"","","2024/12/11",73.5],[6,"Ovis1.6-Gemma2-9B",10.2,"Gemma2-9B-It","SigLIP-400M","2024/09/19",71.2],[7,"Ovis1.5-Llama3-8B",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/07/29",71.2],[8,"H2OVL-2B",2.2,"H2O-DANUBE2-1.8B","InternViT-300M","2024/10/31",70.3],[9,"Cambrian-34B",34.0,"Nous-Hermes-2-Yi-34B","CLIP ViT-L/14","2024/07/18",68.2],[10,"Qwen-VL",9.6,"Qwen-7B","ViT-G/16","2023/08/24",67.5],[11,"Monkey",9.8,"Qwen-7B","ViT-BigHuge","2024/01/11",67.0],[12,"DeepSeek-VL-7B",7.3,"DeekSeek-7B","SAM-B
SigLIP-L","2024/03/21",67.0],[13,"Ovis1.6-Llama3.2-3B",4.1,"Llama-3.2-3B","SigLIP-400M","2024/10/24",66.7],[14,"CogVLM-17B-Chat",17.0,"Vicuna-v1.5-7B","EVA2-CLIP-E","2024/01/03",66.3],[15,"LLaVA-Next-Yi-34B",34.8,"Yi-34B","CLIP ViT-L/14","2024/03/25",66.3],[16,"Cambrian-8B",8.0,"Vicuna-v1.5-7B","CLIP ViT-L/14","2024/07/11",66.0],[17,"LLaVA-Next-Vicuna-13B",13.4,"Vicuna-v1.5-13B","CLIP ViT-L/14","2024/03/25",65.3],[18,"mPLUG-Owl2",8.2,"Llama-2-7B","CLIP ViT-L/14","2023/11/10",65.2],[19,"Eagle-X5-13B",15.0,"Vicuna-v1.5-13B","Clip-448
ConvNeXT-1024
SAM-1024
DET-1024
Pix2Struct-1024","2024/09/26",65.0],[20,"CogVLM2-19B-Chat",19.0,"Llama-3-8B-Instruct","EVA2-CLIP-E","2024/05/31",64.9],[21,"LLaVA-OneVision-7B (SI)",8.0,"Qwen2-7B","SigLIP-400M","2024/09/17",64.7],[22,"BlueLM-V-3B",3.0,"BlueLM-3B","SigLIP-400M","2024/10/30",64.7],[23,"Pixtral-12B",13.0,"Nemo-12B","ViT-400M","2024/09/16",64.7],[24,"MMAlaya2",26.0,"InternLM2-20B","InternViT-6B","2024/08/27",64.6],[25,"Monkey-Chat",9.8,"Qwen-7B","ViT-BigHuge","2024/01/16",64.4],[26,"ShareGPT4V-13B",13.4,"Vicuna-v1.5-13B","CLIP ViT-L/14","2023/12/08",64.3],[27,"Eagle-X5-7B",9.0,"Vicuna-v1.5-7B","Clip-448
ConvNeXT-1024
SAM-1024
DET-1024
Pix2Struct-1024","2024/09/26",64.3],[28,"InternVL-Chat-V1.5",26.0,"InternLM2-20B","InternViT-6B","2024/04/17",64.2],[29,"Bunny-Llama3-8B",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/07/18",63.8],[30,"LLaVA-Next-Vicuna-7B",7.1,"Vicuna-v1.5-7B","CLIP ViT-L/14","2024/03/25",63.8],[31,"ShareGPT4V-7B",7.2,"Vicuna-v1.5-7B","CLIP ViT-L/14","2023/12/08",63.4],[32,"LLaVA-v1.5-13B",13.4,"Vicuna-v1.5-13B","CLIP ViT-L/14","2023/10/05",63.4],[33,"LLaVA-v1.5-13B (QLoRA)",13.4,"Vicuna-v1.5-13B","CLIP ViT-L/14","2023/12/28",63.4],[34,"Aquila-VL-2B",2.2,"Qwen-2.5-1.5B","SigLIP-400M","2024/10/24",63.3],[35,"LLaVA-Next-Qwen-32B",33.0,"Qwen-1.5-32B","SigLIP-400M","2024/08/08",63.2],[36,"InternLM-XComposer2",7.0,"InternLM2-7B","CLIP ViT-L/14","2024/01/26",62.9],[37,"Mantis-8B-Idefics2",8.0,"Mistral-7B","SigLIP-400M","2024/08/08",62.6],[38,"Phi-3-Vision",4.2,"Phi-3","CLIP ViT-L/14","2024/05/31",61.9],[39,"Falcon2-VLM-11B",11.4,"Falcon2-11B","CLIP ViT-L/14","2024/10/30",61.4],[40,"LLaVA-LLaMA-3-8B",8.0,"Llama-3-8B-Instruct","CLIP ViT-L/14","2024/05/07",61.3],[41,"LLaVA-Next-Mistral-7B",7.6,"Mistral-7B","CLIP ViT-L/14","2024/03/25",61.2],[42,"LLaVA-InternLM2-20B (QLoRA)",20.2,"InternLM2-20B","CLIP ViT-L/14","2024/01/17",61.2],[43,"LLaVA-v1.5-7B (QLoRA)",7.2,"Vicuna-v1.5-7B","CLIP ViT-L/14","2023/12/28",61.0],[44,"TransCore-M",13.4,"PCITransGPT-13B","CLIP ViT-L/14","2024/04/16",60.9],[45,"LLaVA-Next-Llama3",8.0,"Llama-3-8B-Instruct","CLIP ViT-L/14","2024/07/29",60.7],[46,"LLaVA-Next-Interleave-7B",8.0,"Qwen-1.5-7B","SigLIP-400M","2024/08/08",60.6],[47,"LLaVA-v1.5-7B",7.2,"Vicuna-v1.5-7B","CLIP ViT-L/14","2023/10/05",60.6],[48,"Phi-4-MultiModal",5.57,"Phi-4-Mini","SigLIP-400M","2025/03/13",60.2],[49,"Moondream1",1.9,"SigLIP-400M","Phi-1.5","2024/09/26",59.6],[50,"OmniLMM-12B",12.0,"Zephyr-7B-β","EVA-02-5B","2024/02/07",59.1],[51,"Qwen-VL-Chat",9.6,"Qwen-7B","ViT-G/16","2023/08/24",58.6],[52,"Mantis-8B-siglip-llama3",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/08/08",58.5],[53,"AKI-4B",4.33,"Phi-3.5","SigLIP-400M","2025/03/25",58.1],[54,"POINTS-Qwen2.5-7B",8.3,"Qwen-2.5-7B","CLIP ViT-L/14","2024/10/19",58.1],[55,"DeepSeek-VL-1.3B",2.0,"DeekSeek-1B","SAM-B
SigLIP-L","2024/03/21",58.1],[56,"LLaVA-InternLM2-7B (QLoRA)",8.1,"InternLM2-7B","CLIP ViT-L/14","2024/01/17",58.0],[57,"PaliGemma-3B-mix-448",3.0,"Gemma-2B","SigLIP-400M","2024/05/17",57.8],[58,"LLaVA-InternLM-7B (QLoRA)",7.6,"InternLM-7B","CLIP ViT-L/14","2023/12/28",57.6],[59,"LLaVA-Next-Interleave-7B-DPO",8.0,"Qwen-1.5-7B","SigLIP-400M","2024/07/29",57.3],[60,"LLaVA-OneVision-0.5B (SI)",1.0,"Qwen2-0.5B","SigLIP-400M","2024/09/17",56.9],[61,"Vintern-3B-beta",3.7,"Qwen-2.5-3B","InternViT-300M","2024/10/24",56.8],[62,"MiniCPM-V",3.0,"MiniCPM-2.4B","SigLIP-400M","2024/02/07",56.4],[63,"POINTS-Yi-1.5-9B",9.5,"Yi-1.5-9B","CLIP ViT-L/14","2024/10/11",56.3],[64,"MiniCPM-V-2",2.8,"MiniCPM-2.4B","SigLIP-400M","2024/04/15",55.8],[65,"Qwen-VL-Max",null,"QwenLM","","2024/02/02",55.0],[66,"InternLM-XComposer",8.0,"InternLM-7B","EVA-G","2023/09/26",54.5],[67,"Mantis-8B-Fuyu",8.0,"Fuyu-8B","","2024/09/07",54.2],[68,"Slime-13B",13.0,"Vicuna-v1.5-13B","CLIP ViT-L/14","2024/09/14",51.0],[69,"MMAlaya",7.8,"Alaya-7B-Chat","EVA-G","2024/01/29",51.0],[70,"ShareCaptioner",8.0,"InternLM-7B","EVA-G","2024/01/03",50.2],[71,"InstructBLIP-7B",8.0,"Vicuna-7B","EVA-G","2023/05/11",50.2],[72,"H2OVL-800M",0.83,"H2O-DANUBE3-500M","InternViT-300M","2024/10/31",50.0],[73,"Yi-VL-6B",6.6,"Yi-6B","CLIP ViT-H/14","2024/01/25",49.5],[74,"Slime-7B",7.0,"Vicuna-v1.5-7B","CLIP ViT-L/14","2024/09/14",49.0],[75,"Slime-8B",8.0,"Llama-3-8B-Instruct","CLIP ViT-L/14","2024/09/14",47.9],[76,"InternVL2-Llama3-76B",76.0,"Llama-3-70B-Instruct","InternViT-6B","2024/07/19",43.7],[77,"InternVL2-26B",26.0,"InternLM2-20B","InternViT-6B","2024/07/11",43.4],[78,"InternVL2-40B",40.0,"Nous-Hermes-2-Yi-34B","InternViT-6B","2024/07/11",42.9],[79,"InternVL2-8B",8.0,"InternLM2.5-7B","InternViT-300M","2024/07/11",42.6],[80,"Yi-VL-34B",34.6,"Yi-34B","CLIP ViT-H/14","2024/01/25",42.4],[81,"Emu2_chat",37.0,"Llama-33B","EVA-02-CLIP-E-plus","2024/01/17",41.0],[82,"InternVL3-8B",7.94,"Qwen2.5-7B","InternViT-300M-v2.5","2025/04/14",38.9],[83,"Qwen-VL-Plus",null,"QwenLM","","2024/01/10",38.8],[84,"GPT-4.1-nano-20250414",null,"","","2025/04/16",36.0],[85,"InternVL3-14B",15.1,"Qwen2.5-14B","InternViT-300M-v2.5","2025/04/14",30.5],[86,"MolmoE-1B",7.2,"OLMoE-1B-7B-0924","CLIP ViT-L/14","2024/10/21",28.6],[87,"Gemma3-4B",4.3,"Gemma3-4B","SigLIP-400M","2025/03/19",27.6],[88,"GPT-4.1-mini-20250414",null,"","","2025/04/16",26.3],[89,"InternVL3-1B",0.94,"Qwen2.5-0.5B","InternViT-300M-v2.5","2025/04/14",21.4],[90,"InternVL3-2B",2.09,"Qwen2.5-1.5B","InternViT-300M-v2.5","2025/04/14",19.1],[91,"GPT-4.1-20250414",null,"","","2025/04/16",18.7],[92,"Gemini-1.5-Flash",null,"","","2024/09/16",18.5],[93,"Gemma3-12B",12.2,"Gemma3-12B","SigLIP-400M","2025/03/19",17.7],[94,"Molmo-7B-D",8.0,"Qwen2-7B","CLIP ViT-L/14","2024/10/12",15.9],[95,"Molmo-7B-O",8.0,"Qwen2-7B","CLIP ViT-L/14","2024/10/20",15.1],[96,"Gemma3-27B",27.4,"Gemma3-27B","SigLIP-400M","2025/03/19",13.5],[97,"Gemini-1.0-Pro",null,"","","2023/12/23",12.3],[98,"Janus-1.3B",2.1,"DeepSeek-1B","SigLIP-400M","2024/10/24",11.7],[99,"Chameleon-7B",7.0,"","","2024/07/29",9.0],[100,"OpenFlamingo v2",9.0,"MPT 7B","CLIP ViT-L/14","2023/06/28",8.9],[101,"Chameleon-30B",30.0,"","","2024/07/29",3.7],[102,"Kosmos2",1.7,"","","2024/10/19",2.9],[103,"SmolVLM-Synthetic",2.3,"SmolLM2-1.7B","SigLIP-400M","2025/01/27",0.5],[104,"MiniGPT-4-v1-7B",8.0,"Vicuna-7B","EVA-G","2023/04/20",0.3],[105,"SmolVLM2-256M",0.26,"SmolLM2-135M","ViT-93M","2025/03/13",0.2],[106,"SmolVLM-Instruct-DPO",2.3,"SmolLM2-1.7B","SigLIP-400M","2025/01/27",0.1],[107,"SmolVLM-Instruct",2.3,"SmolLM2-1.7B","SigLIP-400M","2025/01/27",0.1],[108,"SmolVLM-500M",0.51,"SmolLM2-360M","ViT-93M","2025/01/27",0.0],[109,"SmolVLM2-500M",0.51,"SmolLM2-360M","ViT-93M","2025/03/13",0.0],[110,"SmolVLM-256M",0.26,"SmolLM2-135M","ViT-93M","2025/01/27",0.0],[111,"Idefics3-8B-Llama3",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/08/27",0.0],[112,"SmolVLM2",2.25,"SmolLM2-1.7M","SigLIP-400M","2025/03/13",0.0],[113,"VisualGLM",8.0,"ChatGLM 6B","EVA-CLIP","2023/05/17",0.0],[114,"MiniGPT-4-v2",8.0,"Llama-2-13B","EVA-G","2023/10/27",0.0],[115,"IDEFICS-80B-Instruct",80.0,"Llama-65B","CLIP ViT-H/14","2023/07/25",0.0],[116,"PandaGPT-13B",14.0,"Vicuna-13B","ImageBind ViT-H/14","2023/05/25",0.0],[117,"IDEFICS-9B-Instruct",9.0,"Llama-7B","CLIP ViT-H/14","2023/07/25",0.0],[118,"GPT-4v (1106, detail-low)",null,"","","2023/12/23",0.0]],"metadata":null},"headers":["1","2","3"],"row_count":[1,"dynamic"],"col_count":[3,"dynamic"],"datatype":["number","html","number","html","html","str","number"],"type":"pandas","latex_delimiters":[{"left":"$$","right":"$$","display":true}],"show_label":true,"height":500,"min_width":160,"interactive":false,"visible":true,"elem_classes":[],"wrap":true,"line_breaks":true,"column_widths":[],"name":"dataframe","_selectable":false},"skip_api":false,"component_class_id":"6a51bb3357f2e94c40fb8d4fbe06aa8e","key":null,"api_info":{"properties":{"headers":{"items":{"type":"string"},"title":"Headers","type":"array"},"data":{"items":{"items":{},"type":"array"},"title":"Data","type":"array"},"metadata":{"anyOf":[{"additionalProperties":{"anyOf":[{"items":{},"type":"array"},{"type":"null"}]},"type":"object"},{"type":"null"}],"default":null,"title":"Metadata"}},"required":["headers","data"],"title":"DataframeData","type":"object"},"example_inputs":{"headers":["a","b"],"data":[["foo","bar"]]}},{"id":272,"type":"textbox","props":{"value":"OCRVQA_TESTCORE","lines":1,"max_lines":20,"label":"OCRVQA_TESTCORE","show_label":true,"container":true,"min_width":160,"visible":false,"autofocus":false,"autoscroll":true,"elem_classes":[],"type":"text","rtl":false,"show_copy_button":false,"name":"textbox","_selectable":false},"skip_api":false,"component_class_id":"d0491bb0fbd427bdb2a4549c4d1ac869","key":null,"api_info":{"type":"string"},"example_inputs":"Hello!!"},{"id":273,"type":"form","props":{"scale":0,"min_width":0,"name":"form"},"skip_api":true,"component_class_id":"43cda85c6ff7a5dd8f83d29496b014ee","key":null},{"id":274,"type":"form","props":{"scale":0,"min_width":0,"name":"form"},"skip_api":true,"component_class_id":"43cda85c6ff7a5dd8f83d29496b014ee","key":null},{"id":275,"type":"tabitem","props":{"label":"📊 POPE Leaderboard","visible":true,"interactive":true,"id":24,"elem_id":"POPE","name":"tab"},"skip_api":true,"component_class_id":"18f46968e2b273dc5dbda0fe78433d7e","key":null},{"id":276,"type":"markdown","props":{"value":"## POPE Evaluation Results\n\n- POPE is a benchmark for object hallucination evaluation. It includes three tracks of object hallucination: random, popular, and adversarial.\n- Note that the official POPE dataset contains approximately 8910 cases. POPE includes three tracks, and there are some overlapping samples among the three tracks. To reduce the data file size, we have kept only a single copy of the overlapping samples (about 5127 examples). However, the final accuracy will be calculated on the ~9k samples.\n- Some API models, due to safety policies, refuse to answer certain questions, so their actual capabilities may be higher than the reported scores.\n- We report the average F1 score across the three types of data as the overall score. Accuracy, precision, and recall are also shown in the table. F1 score = 2 * (precision * recall) / (precision + recall). ","show_label":true,"rtl":false,"latex_delimiters":[{"left":"$$","right":"$$","display":true}],"visible":true,"elem_classes":[],"sanitize_html":true,"line_breaks":false,"header_links":false,"show_copy_button":false,"name":"markdown","_selectable":false},"skip_api":false,"component_class_id":"0f35515b9a3362b42bb6721c836157a0","key":null,"api_info":{"type":"string"},"example_inputs":"# Hello!"},{"id":277,"type":"checkboxgroup","props":{"choices":[["Overall","Overall"],["acc","acc"],["precision","precision"],["recall","recall"]],"value":["Overall"],"type":"value","label":"POPE CheckBoxes","show_label":true,"container":true,"min_width":160,"interactive":true,"visible":true,"elem_classes":[],"name":"checkboxgroup","_selectable":false},"skip_api":false,"component_class_id":"0635a5d3bf87369f1c2c1c69f8a3d0cc","key":null,"api_info":{"items":{"enum":["Overall","acc","precision","recall"],"type":"string"},"title":"Checkbox Group","type":"array"},"example_inputs":["Overall"]},{"id":278,"type":"row","props":{"variant":"default","visible":true,"equal_height":true,"show_progress":false,"name":"row"},"skip_api":true,"component_class_id":"b5cf3d15e2293fb5ccc071d7b8d69f64","key":null},{"id":279,"type":"textbox","props":{"value":"Input the Model Name (fuzzy, case insensitive)","lines":1,"max_lines":20,"label":"Model Name","show_label":true,"container":true,"min_width":160,"interactive":true,"visible":true,"autofocus":false,"autoscroll":true,"elem_classes":[],"type":"text","rtl":false,"show_copy_button":false,"name":"textbox","_selectable":false},"skip_api":false,"component_class_id":"d0491bb0fbd427bdb2a4549c4d1ac869","key":null,"api_info":{"type":"string"},"example_inputs":"Hello!!"},{"id":280,"type":"checkboxgroup","props":{"choices":[["<4B","<4B"],["4B-10B","4B-10B"],["10B-20B","10B-20B"],["20B-40B","20B-40B"],[">40B",">40B"],["Unknown","Unknown"]],"value":["<4B","4B-10B","10B-20B","20B-40B",">40B","Unknown"],"type":"value","label":"Model Size","show_label":true,"container":true,"min_width":160,"interactive":true,"visible":true,"elem_classes":[],"name":"checkboxgroup","_selectable":false},"skip_api":false,"component_class_id":"0635a5d3bf87369f1c2c1c69f8a3d0cc","key":null,"api_info":{"items":{"enum":["<4B","4B-10B","10B-20B","20B-40B",">40B","Unknown"],"type":"string"},"title":"Checkbox Group","type":"array"},"example_inputs":["<4B"]},{"id":281,"type":"checkboxgroup","props":{"choices":[["API","API"],["OpenSource","OpenSource"]],"value":["API","OpenSource"],"type":"value","label":"Model Type","show_label":true,"container":true,"min_width":160,"interactive":true,"visible":true,"elem_classes":[],"name":"checkboxgroup","_selectable":false},"skip_api":false,"component_class_id":"0635a5d3bf87369f1c2c1c69f8a3d0cc","key":null,"api_info":{"items":{"enum":["API","OpenSource"],"type":"string"},"title":"Checkbox Group","type":"array"},"example_inputs":["API"]},{"id":282,"type":"form","props":{"scale":3,"min_width":480,"name":"form"},"skip_api":true,"component_class_id":"43cda85c6ff7a5dd8f83d29496b014ee","key":null},{"id":283,"type":"dataframe","props":{"value":{"headers":["Rank","Method","Param (B)","Language Model","Vision Model","Eval Date","Overall"],"data":[[1,"InternVL3-78B",78.4,"Qwen2.5-72B","InternViT-6B-v2.5","2025/04/14",90.5],[2,"InternVL2.5-26B-MPO",26.0,"InternLM2.5-20B","InternViT-6B-v2.5","2024/12/28",90.5],[3,"InternVL3-8B",7.94,"Qwen2.5-7B","InternViT-300M-v2.5","2025/04/14",90.4],[4,"Eagle-X5-34B-Chat",36.8,"Yi-34B","Clip-448
ConvNeXT-1024
SAM-1024
DET-1024
Pix2Struct-1024","2024/11/29",90.2],[5,"InternVL3-2B",2.09,"Qwen2.5-1.5B","InternViT-300M-v2.5","2025/04/14",90.1],[6,"InternVL2.5-2B-MPO",2.0,"InternLM2.5-1.8B","InternViT-300M-v2.5","2024/12/28",90.0],[7,"GLM-4v",null,"","","2024/05/20",89.9],[8,"Eagle-X5-13B",15.0,"Vicuna-v1.5-13B","Clip-448
ConvNeXT-1024
SAM-1024
DET-1024
Pix2Struct-1024","2024/09/26",89.8],[9,"Llama-3-MixSense-v1.1",8.0,"Llama-3-8B-Instruct","Florence-2-Large-FT","2024/08/21",89.7],[10,"LLaVA-Next-Yi-34B",34.8,"Yi-34B","CLIP ViT-L/14","2024/03/25",89.6],[11,"InternVL2.5-4B-MPO",4.0,"Qwen-2.5-3B","InternViT-300M-v2.5","2024/12/28",89.6],[12,"InternVL3-9B",9.14,"InternLM3-8B","InternViT-300M-v2.5","2025/04/14",89.6],[13,"InternVL3-1B",0.94,"Qwen2.5-0.5B","InternViT-300M-v2.5","2025/04/14",89.5],[14,"InternVL2.5-78B-MPO",78.0,"Qwen-2.5-72B","InternViT-6B-v2.5","2024/12/29",89.5],[15,"InternVL2.5-1B-MPO",1.0,"Qwen-2.5-0.5B","InternViT-300M-v2.5","2024/12/28",89.4],[16,"InternVL3-14B",15.1,"Qwen2.5-14B","InternViT-300M-v2.5","2025/04/14",89.4],[17,"GLM-4v-9B",9.0,"GLM-4-9B","EVA-02-5B","2024/06/14",89.4],[18,"Eagle-X5-7B",9.0,"Vicuna-v1.5-7B","Clip-448
ConvNeXT-1024
SAM-1024
DET-1024
Pix2Struct-1024","2024/09/26",89.3],[19,"InternVL3-38B",38.4,"Qwen2.5-32B","InternViT-6B-v2.5","2025/04/14",89.2],[20,"Step-1o",null,"","","2025/01/13",89.1],[21,"Molmo-7B-D",8.0,"Qwen2-7B","CLIP ViT-L/14","2024/10/12",89.0],[22,"InternVL2.5-38B-MPO",38.0,"Qwen-2.5-32B","InternViT-6B-v2.5","2024/12/28",88.9],[23,"VITA-1.5",8.3,"Qwen2-7B","InternViT-300M","2025/01/01",88.9],[24,"VILA1.5-40B",40.0,"Yi-34B","InternViT-6B","2024/08/25",88.8],[25,"InternVL2.5-8B-MPO",8.0,"InternLM2.5-7B","InternViT-300M-v2.5","2024/12/28",88.7],[26,"Ovis2-4B",4.62,"Qwen2.5-3B","AIMv2 Huge","2025/02/18",88.7],[27,"Ovis2-8B",8.94,"Qwen2.5-7B","AIMv2 Huge","2025/02/18",88.6],[28,"Gemini-1.5-Flash",null,"","","2024/09/16",88.5],[29,"Kimi-VL-A3B-Instruct",16.4,"Moonlight-16B-A3B","MoonViT","2025/04/14",88.5],[30,"Ovis1.5-Llama3-8B",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/07/29",88.5],[31,"LLaVA-v1.5-13B",13.4,"Vicuna-v1.5-13B","CLIP ViT-L/14","2023/10/05",88.4],[32,"LLaVA-OneVision-7B",8.0,"Qwen2-7B","SigLIP-400M","2024/09/16",88.4],[33,"Qwen2-VL-7B",8.0,"Qwen2-7B","QwenViT","2024/09/12",88.4],[34,"Ovis1.6-Llama3.2-3B",4.1,"Llama-3.2-3B","SigLIP-400M","2024/10/24",88.2],[35,"Gemini-1.5-Pro",null,"","","2024/06/10",88.2],[36,"LLaVA-InternLM2-20B (QLoRA)",20.2,"InternLM2-20B","CLIP ViT-L/14","2024/01/17",88.1],[37,"Llama-3.2-11B-Vision-Instruct",11.0,"Llama-3.1-8B","","2024/10/07",88.1],[38,"XinYuan-VL-2B-Instruct",2.0,"Qwen2-1.5B","QwenViT","2024/09/27",88.1],[39,"SAIL-VL-2B",2.1,"Qwen2.5-1.5B","InternViT-300M","2024/12/25",88.1],[40,"Ross-Qwen2-7B",8.2,"Qwen2-7B","CLIP ViT-L/14","2025/01/17",88.1],[41,"CogVLM-17B-Chat",17.0,"Vicuna-v1.5-7B","EVA2-CLIP-E","2024/01/03",88.0],[42,"Emu2_chat",37.0,"Llama-33B","EVA-02-CLIP-E-plus","2024/01/17",88.0],[43,"Ovis2-34B",34.9,"Qwen2.5-32B","AIMv2-1B","2025/02/18",88.0],[44,"VARCO-VISION-14B",15.2,"Qwen2.5-14B","SigLIP-400M","2025/01/02",87.9],[45,"InternLM-XComposer2.5",8.0,"InternLM2-7B","CLIP ViT-L/14","2024/07/11",87.9],[46,"MiniMonkey",2.2,"InternLM2-1.8B","InternViT-300M","2024/09/26",87.8],[47,"LLaVA-Next-Vicuna-13B",13.4,"Vicuna-v1.5-13B","CLIP ViT-L/14","2024/03/25",87.8],[48,"Ovis2-2B",2.46,"Qwen2.5-1.5B","AIMv2 Large","2025/02/18",87.8],[49,"Ovis1.6-Gemma2-9B",10.2,"Gemma2-9B-It","SigLIP-400M","2024/09/19",87.8],[50,"LLaVA-InternLM2-7B (QLoRA)",8.1,"InternLM2-7B","CLIP ViT-L/14","2024/01/17",87.8],[51,"LLaVA-OneVision-0.5B",1.0,"Qwen2-0.5B","SigLIP-400M","2024/09/16",87.8],[52,"Ovis2-1B",1.27,"Qwen2.5-0.5B","AIMv2 Large","2025/02/18",87.7],[53,"Ovis1.6-Gemma2-27B",28.9,"Gemma2-27B","SigLIP-400M","2024/11/29",87.7],[54,"InternVL2-8B-MPO-CoT",8.0,"InternLM2.5-7B","InternViT-300M","2024/11/25",87.7],[55,"Taiyi",null,"","","2024/12/11",87.7],[56,"NVLM-D-72B",79.4,"Qwen2-72B","InternViT-6B","2024/10/19",87.6],[57,"Ovis1.5-Gemma2-9B",11.4,"Gemma2-9B-It","SigLIP-400M","2024/08/04",87.6],[58,"PaliGemma-3B-mix-448",3.0,"Gemma-2B","SigLIP-400M","2024/05/17",87.5],[59,"ShareGPT4V-13B",13.4,"Vicuna-v1.5-13B","CLIP ViT-L/14","2023/12/08",87.5],[60,"Ovis2-16B",16.2,"Qwen2.5-14B","AIMv2 Huge","2025/02/18",87.5],[61,"InternVL-Chat-V1.5",26.0,"InternLM2-20B","InternViT-6B","2024/04/17",87.5],[62,"LLaVA-Next-Vicuna-7B",7.1,"Vicuna-v1.5-7B","CLIP ViT-L/14","2024/03/25",87.5],[63,"Vintern-3B-beta",3.7,"Qwen-2.5-3B","InternViT-300M","2024/10/24",87.4],[64,"Falcon2-VLM-11B",11.4,"Falcon2-11B","CLIP ViT-L/14","2024/10/30",87.4],[65,"LLaVA-Next-Mistral-7B",7.6,"Mistral-7B","CLIP ViT-L/14","2024/03/25",87.3],[66,"Qwen2-VL-2B",2.0,"Qwen2-1.5B","QwenViT","2024/09/12",87.3],[67,"360VL-70B",70.0,"Llama-3-70B-Instruct","CLIP ViT-L/14","2024/05/25",87.3],[68,"InternVL2-Llama3-76B",76.0,"Llama-3-70B-Instruct","InternViT-6B","2024/07/19",87.3],[69,"MUG-U-7B",7.0,"","","2025/03/19",87.3],[70,"LLaVA-LLaMA-3-8B",8.0,"Llama-3-8B-Instruct","CLIP ViT-L/14","2024/05/07",87.3],[71,"LLaVA-OneVision-7B (SI)",8.0,"Qwen2-7B","SigLIP-400M","2024/09/17",87.2],[72,"granite-vision-3.2-2b",2.98,"granite-3.1-2b-instruct","SigLip","2025/06/20",87.2],[73,"Qwen2-VL-72B",73.4,"Qwen2-72B","QwenViT","2024/10/28",87.2],[74,"XGen-MM-Instruct-Interleave-v1.5",4.4,"Phi-3","SigLIP-400M","2024/09/06",87.2],[75,"GPT-4o (0806, detail-high)",null,"","","2024/08/08",87.2],[76,"LLaVA-v1.5-7B (QLoRA)",7.2,"Vicuna-v1.5-7B","CLIP ViT-L/14","2023/12/28",87.2],[77,"LLaVA-Next-Llama3",8.0,"Llama-3-8B-Instruct","CLIP ViT-L/14","2024/07/29",87.1],[78,"TransCore-M",13.4,"PCITransGPT-13B","CLIP ViT-L/14","2024/04/16",87.1],[79,"Bunny-Llama3-8B",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/07/18",86.9],[80,"GLM-4v-Plus",null,"","","2024/12/11",86.9],[81,"XGen-MM-Instruct-DPO-v1.5",4.4,"Phi-3","SigLIP-400M","2024/09/06",86.9],[82,"LLaVA-v1.5-13B (QLoRA)",13.4,"Vicuna-v1.5-13B","CLIP ViT-L/14","2023/12/28",86.9],[83,"Qwen-VL-Max-0809",72.0,"Qwen2-72B","QwenViT","2024/09/12",86.8],[84,"POINTS1.5-Qwen2.5-7B",8.3,"Qwen-2.5-7B","NaViT","2024/12/06",86.8],[85,"Cambrian-13B",13.0,"Vicuna-v1.5-13B","CLIP ViT-L/14","2024/07/29",86.8],[86,"VILA1.5-3B",3.0,"Sheared-LLaMA-2.7B","SigLIP-400M","2024/08/25",86.8],[87,"LLaVA-OneVision-0.5B (SI)",1.0,"Qwen2-0.5B","SigLIP-400M","2024/09/17",86.8],[88,"Molmo-7B-O",8.0,"Qwen2-7B","CLIP ViT-L/14","2024/10/20",86.7],[89,"MiniCPM-Llama3-V2.5",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/05/27",86.7],[90,"WeMM",7.0,"InternLM2-7B","SigLIP-400M","2024/06/09",86.7],[91,"MiniCPM-o-2.6",8.67,"Qwen2.5-7B","SigLIP-400M","2025/01/21",86.7],[92,"H2OVL-2B",2.2,"H2O-DANUBE2-1.8B","InternViT-300M","2024/10/31",86.6],[93,"MolmoE-1B",7.2,"OLMoE-1B-7B-0924","CLIP ViT-L/14","2024/10/21",86.6],[94,"LLaVA-OneVision-72B",73.0,"Qwen2-72B","SigLIP-400M","2024/09/19",86.6],[95,"CongRong",null,"","","2024/06/26",86.6],[96,"ShareGPT4V-7B",7.2,"Vicuna-v1.5-7B","CLIP ViT-L/14","2023/12/08",86.6],[97,"Moondream1",1.9,"SigLIP-400M","Phi-1.5","2024/09/26",86.5],[98,"POINTS-Qwen2.5-7B",8.3,"Qwen-2.5-7B","CLIP ViT-L/14","2024/10/19",86.5],[99,"Cambrian-8B",8.0,"Vicuna-v1.5-7B","CLIP ViT-L/14","2024/07/11",86.4],[100,"InternVL2-26B",26.0,"InternLM2-20B","InternViT-6B","2024/07/11",86.4],[101,"GPT-4.1-20250414",null,"","","2025/04/16",86.4],[102,"Llama-3.2-90B-Vision-Instruct",88.6,"Llama-3.1-70B","","2024/10/19",86.3],[103,"MMAlaya2",26.0,"InternLM2-20B","InternViT-6B","2024/08/27",86.3],[104,"MiniCPM-V-2",2.8,"MiniCPM-2.4B","SigLIP-400M","2024/04/15",86.3],[105,"BailingMM-Pro-0120",81.0,"Bailing-80B","SigLIP-400M","2025/01/25",86.2],[106,"IDEFICS2-8B",8.0,"Mistral-7B","SigLIP-400M","2024/04/26",86.2],[107,"Idefics3-8B-Llama3",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/08/27",86.2],[108,"POINTS-Yi-1.5-9B",9.5,"Yi-1.5-9B","CLIP ViT-L/14","2024/10/11",86.2],[109,"LLaVA-v1.5-7B",7.2,"Vicuna-v1.5-7B","CLIP ViT-L/14","2023/10/05",86.1],[110,"InstructBLIP-7B",8.0,"Vicuna-7B","EVA-G","2023/05/11",86.1],[111,"BailingMM-Lite-1203",21.0,"Bailing-20B","SigLIP-400M","2024/12/08",86.1],[112,"Qwen-VL-Plus-0809",null,"","","2024/09/17",86.1],[113,"LLaVA-InternLM-7B (QLoRA)",7.6,"InternLM-7B","CLIP ViT-L/14","2023/12/28",86.0],[114,"GLM-4v-Plus-20250111",null,"","","2025/01/25",86.0],[115,"Phi-4-MultiModal",5.57,"Phi-4-Mini","SigLIP-400M","2025/03/13",85.9],[116,"DeepSeek-VL-1.3B",2.0,"DeekSeek-1B","SAM-B
SigLIP-L","2024/03/21",85.9],[117,"InternVL2-8B-MPO",8.0,"InternLM2.5-7B","InternViT-300M","2024/11/25",85.9],[118,"abab7-preview",null,"","","2024/12/11",85.9],[119,"Qwen2.5-VL-7B",8.29,"Qwen2.5-7B","QwenViT","2025/02/02",85.9],[120,"Qwen2.5-VL-3B",3.75,"Qwen2.5-3B","QwenViT","2025/02/02",85.9],[121,"HunYuan-Standard-Vision",null,"","","2025/01/15",85.8],[122,"Qwen2.5-VL-72B",73.4,"Qwen2.5-72B","QwenViT","2025/02/02",85.7],[123,"DeepSeek-VL-7B",7.3,"DeekSeek-7B","SAM-B
SigLIP-L","2024/03/21",85.6],[124,"GPT-4.1-mini-20250414",null,"","","2025/04/16",85.6],[125,"GPT-4o (0513, detail-high)",null,"","","2024/05/31",85.6],[126,"SmolVLM-Instruct",2.3,"SmolLM2-1.7B","SigLIP-400M","2025/01/27",85.5],[127,"LLaVA-Next-Interleave-7B",8.0,"Qwen-1.5-7B","SigLIP-400M","2024/08/08",85.5],[128,"Gemma3-12B",12.2,"Gemma3-12B","SigLIP-400M","2025/03/19",85.5],[129,"Mini-InternVL-Chat-2B-V1.5",2.0,"InternLM2-1.8B","InternViT-300M","2024/06/10",85.4],[130,"Qwen-VL-Plus",null,"QwenLM","","2024/01/10",85.4],[131,"AKI-4B",4.33,"Phi-3.5","SigLIP-400M","2025/03/25",85.4],[132,"Step-1.5V",null,"Step-1.5","stepencoder","2024/10/11",85.4],[133,"Parrot-7B",8.0,"Qwen2-7B","CLIP ViT-L/14","2024/08/22",85.3],[134,"H2OVL-800M",0.83,"H2O-DANUBE3-500M","InternViT-300M","2024/10/31",85.3],[135,"granite-vision-3.3-2b",2.98,"granite-3.1-2b-instruct","SigLIP2-400M","2025/06/20",85.2],[136,"InternVL2-2B",2.0,"InternLM2-1.8B","InternViT-300M","2024/07/11",85.2],[137,"Cambrian-34B",34.0,"Nous-Hermes-2-Yi-34B","CLIP ViT-L/14","2024/07/18",85.1],[138,"Slime-8B",8.0,"Llama-3-8B-Instruct","CLIP ViT-L/14","2024/09/14",85.1],[139,"SmolVLM2",2.25,"SmolLM2-1.7M","SigLIP-400M","2025/03/13",85.1],[140,"GPT-4o (0513, detail-low)",null,"","","2024/05/15",85.0],[141,"VILA1.5-13B",13.0,"Vicuna-v1.5-13B","SigLIP-400M","2024/08/25",85.0],[142,"InternVL2-1B",1.0,"Qwen2-0.5B","InternViT-300M","2024/07/11",84.9],[143,"LLaVA-Next-Interleave-7B-DPO",8.0,"Qwen-1.5-7B","SigLIP-400M","2024/07/29",84.8],[144,"Gemma3-4B",4.3,"Gemma3-4B","SigLIP-400M","2025/03/19",84.6],[145,"InternVL2-4B",4.0,"Phi-3","InternViT-300M","2024/07/11",84.6],[146,"mPLUG-Owl2",8.2,"Llama-2-7B","CLIP ViT-L/14","2023/11/10",84.6],[147,"Mantis-8B-Idefics2",8.0,"Mistral-7B","SigLIP-400M","2024/08/08",84.5],[148,"ShareCaptioner",8.0,"InternLM-7B","EVA-G","2024/01/03",84.4],[149,"LLaVA-Next-Qwen-32B",33.0,"Qwen-1.5-32B","SigLIP-400M","2024/08/08",84.4],[150,"SmolVLM-500M",0.51,"SmolLM2-360M","ViT-93M","2025/01/27",84.3],[151,"Gemma3-27B",27.4,"Gemma3-27B","SigLIP-400M","2025/03/19",84.2],[152,"Step-1.5V-mini",null,"","","2024/12/11",84.2],[153,"InternVL2-8B",8.0,"InternLM2.5-7B","InternViT-300M","2024/07/11",84.2],[154,"Pixtral-12B",13.0,"Nemo-12B","ViT-400M","2024/09/16",84.2],[155,"InternLM-XComposer2-1.8B",2.0,"InternLM2-1.8B","CLIP ViT-L/14","2024/06/09",84.2],[156,"Yi-Vision",null,"","","2024/08/03",84.1],[157,"Janus-1.3B",2.1,"DeepSeek-1B","SigLIP-400M","2024/10/24",84.1],[158,"Mantis-8B-Fuyu",8.0,"Fuyu-8B","","2024/09/07",84.0],[159,"Mantis-8B-siglip-llama3",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/08/08",84.0],[160,"Slime-13B",13.0,"Vicuna-v1.5-13B","CLIP ViT-L/14","2024/09/14",83.9],[161,"Slime-7B",7.0,"Vicuna-v1.5-7B","CLIP ViT-L/14","2024/09/14",83.8],[162,"Monkey",9.8,"Qwen-7B","ViT-BigHuge","2024/01/11",83.7],[163,"Phi-3-Vision",4.2,"Phi-3","CLIP ViT-L/14","2024/05/31",83.7],[164,"Monkey-Chat",9.8,"Qwen-7B","ViT-BigHuge","2024/01/16",83.5],[165,"GPT-4.1-nano-20250414",null,"","","2025/04/16",83.5],[166,"CogVLM2-19B-Chat",19.0,"Llama-3-8B-Instruct","EVA2-CLIP-E","2024/05/31",83.4],[167,"Emu3_chat",8.49,"","","2025/01/26",83.3],[168,"Llama-3-VILA1.5-8B",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/08/25",83.3],[169,"RekaEdge",null,"","","2024/05/31",83.3],[170,"MiniCPM-V-2.6",8.0,"Qwen2-7B","SigLIP-400M","2024/08/08",83.2],[171,"grok-2-vision-1212",null,"","","2025/03/03",83.1],[172,"Aquila-VL-2B",2.2,"Qwen-2.5-1.5B","SigLIP-400M","2024/10/24",83.1],[173,"InternLM-XComposer2",7.0,"InternLM2-7B","CLIP ViT-L/14","2024/01/26",83.0],[174,"Mantis-8B-clip-llama3",8.0,"Llama-3-8B-Instruct","CLIP ViT-L/14","2024/08/08",82.9],[175,"Phi-3.5-Vision",4.0,"Phi-3.5","CLIP ViT-L/14","2024/08/28",82.8],[176,"MMAlaya",7.8,"Alaya-7B-Chat","EVA-G","2024/01/29",82.7],[177,"SmolVLM2-500M",0.51,"SmolLM2-360M","ViT-93M","2025/03/13",82.7],[178,"Yi-VL-34B",34.6,"Yi-34B","CLIP ViT-H/14","2024/01/25",82.5],[179,"Yi-VL-6B",6.6,"Yi-6B","CLIP ViT-H/14","2024/01/25",82.5],[180,"Claude3.7-Sonnet",null,"","","2025/02/27",82.4],[181,"InternVL2-40B",40.0,"Nous-Hermes-2-Yi-34B","InternViT-6B","2024/07/11",81.9],[182,"GPT-4o-mini (0718, detail-high)",null,"","","2024/07/20",81.9],[183,"IDEFICS-9B-Instruct",9.0,"Llama-7B","CLIP ViT-H/14","2023/07/25",81.9],[184,"GPT-4v (0409, detail-high)",null,"","","2024/05/15",81.8],[185,"OmniLMM-12B",12.0,"Zephyr-7B-β","EVA-02-5B","2024/02/07",81.7],[186,"SmolVLM-Instruct-DPO",2.3,"SmolLM2-1.7B","SigLIP-400M","2025/01/27",81.5],[187,"Mini-InternVL-Chat-4B-V1.5",4.0,"Phi-3","InternViT-300M","2024/06/10",81.4],[188,"RekaFlash",null,"","","2024/05/07",80.6],[189,"MiniCPM-V",3.0,"MiniCPM-2.4B","SigLIP-400M","2024/02/07",79.5],[190,"Janus-Pro-7B",7.42,"DeepSeek-7B","SigLIP-400M","2025/02/02",78.9],[191,"abab6.5s",null,"","","2024/12/11",77.6],[192,"SmolVLM-256M",0.26,"SmolLM2-135M","ViT-93M","2025/01/27",76.6],[193,"LLaVA-v1-7B",7.2,"Llama-7B","CLIP ViT-L/14","2023/04/17",75.9],[194,"GPT-4v (1106, detail-low)",null,"","","2023/12/23",75.4],[195,"PandaGPT-13B",14.0,"Vicuna-13B","ImageBind ViT-H/14","2023/05/25",75.1],[196,"Qwen-VL-Chat",9.6,"Qwen-7B","ViT-G/16","2023/08/24",74.9],[197,"Claude3-Haiku",null,"","","2024/03/28",74.4],[198,"Claude3-Opus",null,"","","2024/03/28",74.0],[199,"Claude3.5-Sonnet",null,"","","2024/06/24",73.6],[200,"Qwen-VL-Max",null,"QwenLM","","2024/02/02",71.9],[201,"InternLM-XComposer",8.0,"InternLM-7B","EVA-G","2023/09/26",70.9],[202,"VisualGLM",8.0,"ChatGLM 6B","EVA-CLIP","2023/05/17",70.4],[203,"Qwen-VL",9.6,"Qwen-7B","ViT-G/16","2023/08/24",70.0],[204,"Claude3-Sonnet",null,"","","2024/03/28",68.2],[205,"Kosmos2",1.7,"","","2024/10/19",66.3],[206,"IDEFICS-80B-Instruct",80.0,"Llama-65B","CLIP ViT-H/14","2023/07/25",66.0],[207,"SmolVLM-Synthetic",2.3,"SmolLM2-1.7B","SigLIP-400M","2025/01/27",63.5],[208,"MiniGPT-4-v2",8.0,"Llama-2-13B","EVA-G","2023/10/27",60.0],[209,"Chameleon-30B",30.0,"","","2024/07/29",59.8],[210,"SmolVLM2-256M",0.26,"SmolLM2-135M","ViT-93M","2025/03/13",54.3],[211,"OpenFlamingo v2",9.0,"MPT 7B","CLIP ViT-L/14","2023/06/28",52.6],[212,"MiniGPT-4-v1-7B",8.0,"Vicuna-7B","EVA-G","2023/04/20",34.6],[213,"XVERSE-V-13B",13.0,"XVERSE-13B","CLIP ViT-L/14","2024/05/10",29.3],[214,"Chameleon-7B",7.0,"","","2024/07/29",19.4],[215,"InternLM-XComposer2-4KHD",7.0,"InternLM2-7B","CLIP ViT-L/14","2024/06/09",2.9],[216,"moonshot-v1-8k",null,"","","2025/03/03",2.0]],"metadata":null},"headers":["1","2","3"],"row_count":[1,"dynamic"],"col_count":[3,"dynamic"],"datatype":["number","html","number","html","html","str","number"],"type":"pandas","latex_delimiters":[{"left":"$$","right":"$$","display":true}],"show_label":true,"height":500,"min_width":160,"interactive":false,"visible":true,"elem_classes":[],"wrap":true,"line_breaks":true,"column_widths":[],"name":"dataframe","_selectable":false},"skip_api":false,"component_class_id":"6a51bb3357f2e94c40fb8d4fbe06aa8e","key":null,"api_info":{"properties":{"headers":{"items":{"type":"string"},"title":"Headers","type":"array"},"data":{"items":{"items":{},"type":"array"},"title":"Data","type":"array"},"metadata":{"anyOf":[{"additionalProperties":{"anyOf":[{"items":{},"type":"array"},{"type":"null"}]},"type":"object"},{"type":"null"}],"default":null,"title":"Metadata"}},"required":["headers","data"],"title":"DataframeData","type":"object"},"example_inputs":{"headers":["a","b"],"data":[["foo","bar"]]}},{"id":284,"type":"textbox","props":{"value":"POPE","lines":1,"max_lines":20,"label":"POPE","show_label":true,"container":true,"min_width":160,"visible":false,"autofocus":false,"autoscroll":true,"elem_classes":[],"type":"text","rtl":false,"show_copy_button":false,"name":"textbox","_selectable":false},"skip_api":false,"component_class_id":"d0491bb0fbd427bdb2a4549c4d1ac869","key":null,"api_info":{"type":"string"},"example_inputs":"Hello!!"},{"id":285,"type":"form","props":{"scale":0,"min_width":0,"name":"form"},"skip_api":true,"component_class_id":"43cda85c6ff7a5dd8f83d29496b014ee","key":null},{"id":286,"type":"form","props":{"scale":0,"min_width":0,"name":"form"},"skip_api":true,"component_class_id":"43cda85c6ff7a5dd8f83d29496b014ee","key":null},{"id":287,"type":"tabitem","props":{"label":"📊 SEEDBench2 Leaderboard","visible":true,"interactive":true,"id":25,"elem_id":"SEEDBench2","name":"tab"},"skip_api":true,"component_class_id":"18f46968e2b273dc5dbda0fe78433d7e","key":null},{"id":288,"type":"markdown","props":{"value":"## SEEDBench2 Evaluation Results\n\n- SEEDBench2 comprises 24K multiple-choice questions with accurate human annotations, which spans 27 dimensions, including the evaluation of both text and image generation.\n- Note that we only evaluate and report the part of model's results on the SEEDBench2.","show_label":true,"rtl":false,"latex_delimiters":[{"left":"$$","right":"$$","display":true}],"visible":true,"elem_classes":[],"sanitize_html":true,"line_breaks":false,"header_links":false,"show_copy_button":false,"name":"markdown","_selectable":false},"skip_api":false,"component_class_id":"0f35515b9a3362b42bb6721c836157a0","key":null,"api_info":{"type":"string"},"example_inputs":"# Hello!"},{"id":289,"type":"checkboxgroup","props":{"choices":[["Overall","Overall"]],"value":["Overall"],"type":"value","label":"SEEDBench2 CheckBoxes","show_label":true,"container":true,"min_width":160,"interactive":true,"visible":true,"elem_classes":[],"name":"checkboxgroup","_selectable":false},"skip_api":false,"component_class_id":"0635a5d3bf87369f1c2c1c69f8a3d0cc","key":null,"api_info":{"items":{"enum":["Overall"],"type":"string"},"title":"Checkbox Group","type":"array"},"example_inputs":["Overall"]},{"id":290,"type":"row","props":{"variant":"default","visible":true,"equal_height":true,"show_progress":false,"name":"row"},"skip_api":true,"component_class_id":"b5cf3d15e2293fb5ccc071d7b8d69f64","key":null},{"id":291,"type":"textbox","props":{"value":"Input the Model Name (fuzzy, case insensitive)","lines":1,"max_lines":20,"label":"Model Name","show_label":true,"container":true,"min_width":160,"interactive":true,"visible":true,"autofocus":false,"autoscroll":true,"elem_classes":[],"type":"text","rtl":false,"show_copy_button":false,"name":"textbox","_selectable":false},"skip_api":false,"component_class_id":"d0491bb0fbd427bdb2a4549c4d1ac869","key":null,"api_info":{"type":"string"},"example_inputs":"Hello!!"},{"id":292,"type":"checkboxgroup","props":{"choices":[["<4B","<4B"],["4B-10B","4B-10B"],["10B-20B","10B-20B"],["20B-40B","20B-40B"],[">40B",">40B"],["Unknown","Unknown"]],"value":["<4B","4B-10B","10B-20B","20B-40B",">40B","Unknown"],"type":"value","label":"Model Size","show_label":true,"container":true,"min_width":160,"interactive":true,"visible":true,"elem_classes":[],"name":"checkboxgroup","_selectable":false},"skip_api":false,"component_class_id":"0635a5d3bf87369f1c2c1c69f8a3d0cc","key":null,"api_info":{"items":{"enum":["<4B","4B-10B","10B-20B","20B-40B",">40B","Unknown"],"type":"string"},"title":"Checkbox Group","type":"array"},"example_inputs":["<4B"]},{"id":293,"type":"checkboxgroup","props":{"choices":[["API","API"],["OpenSource","OpenSource"]],"value":["API","OpenSource"],"type":"value","label":"Model Type","show_label":true,"container":true,"min_width":160,"interactive":true,"visible":true,"elem_classes":[],"name":"checkboxgroup","_selectable":false},"skip_api":false,"component_class_id":"0635a5d3bf87369f1c2c1c69f8a3d0cc","key":null,"api_info":{"items":{"enum":["API","OpenSource"],"type":"string"},"title":"Checkbox Group","type":"array"},"example_inputs":["API"]},{"id":294,"type":"form","props":{"scale":3,"min_width":480,"name":"form"},"skip_api":true,"component_class_id":"43cda85c6ff7a5dd8f83d29496b014ee","key":null},{"id":295,"type":"dataframe","props":{"value":{"headers":["Rank","Method","Param (B)","Language Model","Vision Model","Eval Date","Overall"],"data":[[1,"GPT-4.1-20250414",null,"","","2025/04/16",76.0],[2,"GPT-4.1-mini-20250414",null,"","","2025/04/16",75.0],[3,"Gemini-1.5-Flash",null,"","","2024/09/16",70.2],[4,"InternVL3-14B",15.1,"Qwen2.5-14B","InternViT-300M-v2.5","2025/04/14",67.7],[5,"InternVL3-8B",7.94,"Qwen2.5-7B","InternViT-300M-v2.5","2025/04/14",67.1],[6,"MUG-U-7B",7.0,"","","2025/03/19",65.9],[7,"GPT-4.1-nano-20250414",null,"","","2025/04/16",64.4],[8,"InternVL3-2B",2.09,"Qwen2.5-1.5B","InternViT-300M-v2.5","2025/04/14",63.4],[9,"InternVL2-Llama3-76B",76.0,"Llama-3-70B-Instruct","InternViT-6B","2024/07/19",63.0],[10,"Gemma3-27B",27.4,"Gemma3-27B","SigLIP-400M","2025/03/19",59.9],[11,"LLaVA-Next-Interleave-7B",8.0,"Qwen-1.5-7B","SigLIP-400M","2024/08/08",59.9],[12,"POINTS-Qwen2.5-7B",8.3,"Qwen-2.5-7B","CLIP ViT-L/14","2024/10/19",59.5],[13,"POINTS-Yi-1.5-9B",9.5,"Yi-1.5-9B","CLIP ViT-L/14","2024/10/11",59.4],[14,"InternVL-Chat-V1.5",26.0,"InternLM2-20B","InternViT-6B","2024/04/17",59.1],[15,"LLaVA-Next-Yi-34B",34.8,"Yi-34B","CLIP ViT-L/14","2024/03/25",59.0],[16,"Molmo-7B-D",8.0,"Qwen2-7B","CLIP ViT-L/14","2024/10/12",58.2],[17,"InternVL3-1B",0.94,"Qwen2.5-0.5B","InternViT-300M-v2.5","2025/04/14",58.1],[18,"Phi-4-MultiModal",5.57,"Phi-4-Mini","SigLIP-400M","2025/03/13",58.1],[19,"Pixtral-12B",13.0,"Nemo-12B","ViT-400M","2024/09/16",57.9],[20,"SmolVLM2",2.25,"SmolLM2-1.7M","SigLIP-400M","2025/03/13",57.8],[21,"Gemma3-12B",12.2,"Gemma3-12B","SigLIP-400M","2025/03/19",57.6],[22,"InternLM-XComposer2-4KHD",7.0,"InternLM2-7B","CLIP ViT-L/14","2024/06/09",57.4],[23,"Mini-InternVL-Chat-4B-V1.5",4.0,"Phi-3","InternViT-300M","2024/06/10",57.3],[24,"Ovis1.6-Gemma2-9B",10.2,"Gemma2-9B-It","SigLIP-400M","2024/09/19",56.8],[25,"LLaVA-OneVision-7B (SI)",8.0,"Qwen2-7B","SigLIP-400M","2024/09/17",56.7],[26,"Mantis-8B-siglip-llama3",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/08/08",56.2],[27,"Molmo-7B-O",8.0,"Qwen2-7B","CLIP ViT-L/14","2024/10/20",56.1],[28,"Phi-3-Vision",4.2,"Phi-3","CLIP ViT-L/14","2024/05/31",55.7],[29,"LLaVA-Next-Vicuna-13B",13.4,"Vicuna-v1.5-13B","CLIP ViT-L/14","2024/03/25",55.0],[30,"Vintern-3B-beta",3.7,"Qwen-2.5-3B","InternViT-300M","2024/10/24",54.8],[31,"Falcon2-VLM-11B",11.4,"Falcon2-11B","CLIP ViT-L/14","2024/10/30",54.8],[32,"SmolVLM-Instruct",2.3,"SmolLM2-1.7B","SigLIP-400M","2025/01/27",54.7],[33,"LLaVA-Next-Mistral-7B",7.6,"Mistral-7B","CLIP ViT-L/14","2024/03/25",54.7],[34,"Mini-InternVL-Chat-2B-V1.5",2.0,"InternLM2-1.8B","InternViT-300M","2024/06/10",54.0],[35,"H2OVL-2B",2.2,"H2O-DANUBE2-1.8B","InternViT-300M","2024/10/31",54.0],[36,"Ovis1.6-Llama3.2-3B",4.1,"Llama-3.2-3B","SigLIP-400M","2024/10/24",53.7],[37,"IDEFICS2-8B",8.0,"Mistral-7B","SigLIP-400M","2024/04/26",53.4],[38,"SmolVLM-Instruct-DPO",2.3,"SmolLM2-1.7B","SigLIP-400M","2025/01/27",53.2],[39,"Gemma3-4B",4.3,"Gemma3-4B","SigLIP-400M","2025/03/19",52.7],[40,"MolmoE-1B",7.2,"OLMoE-1B-7B-0924","CLIP ViT-L/14","2024/10/21",52.5],[41,"AKI-4B",4.33,"Phi-3.5","SigLIP-400M","2025/03/25",52.0],[42,"GLM-4v-9B",9.0,"GLM-4-9B","EVA-02-5B","2024/06/14",49.4],[43,"Aquila-VL-2B",2.2,"Qwen-2.5-1.5B","SigLIP-400M","2024/10/24",49.3],[44,"Moondream1",1.9,"SigLIP-400M","Phi-1.5","2024/09/26",47.9],[45,"SmolVLM2-500M",0.51,"SmolLM2-360M","ViT-93M","2025/03/13",47.9],[46,"H2OVL-800M",0.83,"H2O-DANUBE3-500M","InternViT-300M","2024/10/31",46.2],[47,"LLaVA-OneVision-0.5B (SI)",1.0,"Qwen2-0.5B","SigLIP-400M","2024/09/17",45.8],[48,"SmolVLM-Synthetic",2.3,"SmolLM2-1.7B","SigLIP-400M","2025/01/27",44.7],[49,"Eagle-X5-7B",9.0,"Vicuna-v1.5-7B","Clip-448
ConvNeXT-1024
SAM-1024
DET-1024
Pix2Struct-1024","2024/09/26",44.5],[50,"Eagle-X5-13B",15.0,"Vicuna-v1.5-13B","Clip-448
ConvNeXT-1024
SAM-1024
DET-1024
Pix2Struct-1024","2024/09/26",44.5],[51,"Slime-8B",8.0,"Llama-3-8B-Instruct","CLIP ViT-L/14","2024/09/14",43.9],[52,"SmolVLM-500M",0.51,"SmolLM2-360M","ViT-93M","2025/01/27",43.7],[53,"Slime-13B",13.0,"Vicuna-v1.5-13B","CLIP ViT-L/14","2024/09/14",43.4],[54,"LLaVA-v1.5-7B",7.2,"Vicuna-v1.5-7B","CLIP ViT-L/14","2023/10/05",43.4],[55,"Slime-7B",7.0,"Vicuna-v1.5-7B","CLIP ViT-L/14","2024/09/14",43.0],[56,"Janus-1.3B",2.1,"DeepSeek-1B","SigLIP-400M","2024/10/24",40.0],[57,"SmolVLM2-256M",0.26,"SmolLM2-135M","ViT-93M","2025/03/13",34.4],[58,"SmolVLM-256M",0.26,"SmolLM2-135M","ViT-93M","2025/01/27",25.3],[59,"Kosmos2",1.7,"","","2024/10/19",25.1]],"metadata":null},"headers":["1","2","3"],"row_count":[1,"dynamic"],"col_count":[3,"dynamic"],"datatype":["number","html","number","html","html","str","number"],"type":"pandas","latex_delimiters":[{"left":"$$","right":"$$","display":true}],"show_label":true,"height":500,"min_width":160,"interactive":false,"visible":true,"elem_classes":[],"wrap":true,"line_breaks":true,"column_widths":[],"name":"dataframe","_selectable":false},"skip_api":false,"component_class_id":"6a51bb3357f2e94c40fb8d4fbe06aa8e","key":null,"api_info":{"properties":{"headers":{"items":{"type":"string"},"title":"Headers","type":"array"},"data":{"items":{"items":{},"type":"array"},"title":"Data","type":"array"},"metadata":{"anyOf":[{"additionalProperties":{"anyOf":[{"items":{},"type":"array"},{"type":"null"}]},"type":"object"},{"type":"null"}],"default":null,"title":"Metadata"}},"required":["headers","data"],"title":"DataframeData","type":"object"},"example_inputs":{"headers":["a","b"],"data":[["foo","bar"]]}},{"id":296,"type":"textbox","props":{"value":"SEEDBench2","lines":1,"max_lines":20,"label":"SEEDBench2","show_label":true,"container":true,"min_width":160,"visible":false,"autofocus":false,"autoscroll":true,"elem_classes":[],"type":"text","rtl":false,"show_copy_button":false,"name":"textbox","_selectable":false},"skip_api":false,"component_class_id":"d0491bb0fbd427bdb2a4549c4d1ac869","key":null,"api_info":{"type":"string"},"example_inputs":"Hello!!"},{"id":297,"type":"form","props":{"scale":0,"min_width":0,"name":"form"},"skip_api":true,"component_class_id":"43cda85c6ff7a5dd8f83d29496b014ee","key":null},{"id":298,"type":"form","props":{"scale":0,"min_width":0,"name":"form"},"skip_api":true,"component_class_id":"43cda85c6ff7a5dd8f83d29496b014ee","key":null},{"id":299,"type":"tabitem","props":{"label":"📊 SEEDBench2_Plus Leaderboard","visible":true,"interactive":true,"id":26,"elem_id":"SEEDBench2_Plus","name":"tab"},"skip_api":true,"component_class_id":"18f46968e2b273dc5dbda0fe78433d7e","key":null},{"id":300,"type":"markdown","props":{"value":"## SEEDBench2 Plus Evaluation Results\n\n- SEEDBench2 Plus comprises 2.3K multiple-choice questions with precise human annotations, spanning three broad categories: Charts, Maps, and Webs, each of which covers a wide spectrum of textrich scenarios in the real world.","show_label":true,"rtl":false,"latex_delimiters":[{"left":"$$","right":"$$","display":true}],"visible":true,"elem_classes":[],"sanitize_html":true,"line_breaks":false,"header_links":false,"show_copy_button":false,"name":"markdown","_selectable":false},"skip_api":false,"component_class_id":"0f35515b9a3362b42bb6721c836157a0","key":null,"api_info":{"type":"string"},"example_inputs":"# Hello!"},{"id":301,"type":"checkboxgroup","props":{"choices":[["Overall","Overall"],["chart","chart"],["map","map"],["web","web"]],"value":["Overall"],"type":"value","label":"SEEDBench2_Plus CheckBoxes","show_label":true,"container":true,"min_width":160,"interactive":true,"visible":true,"elem_classes":[],"name":"checkboxgroup","_selectable":false},"skip_api":false,"component_class_id":"0635a5d3bf87369f1c2c1c69f8a3d0cc","key":null,"api_info":{"items":{"enum":["Overall","chart","map","web"],"type":"string"},"title":"Checkbox Group","type":"array"},"example_inputs":["Overall"]},{"id":302,"type":"row","props":{"variant":"default","visible":true,"equal_height":true,"show_progress":false,"name":"row"},"skip_api":true,"component_class_id":"b5cf3d15e2293fb5ccc071d7b8d69f64","key":null},{"id":303,"type":"textbox","props":{"value":"Input the Model Name (fuzzy, case insensitive)","lines":1,"max_lines":20,"label":"Model Name","show_label":true,"container":true,"min_width":160,"interactive":true,"visible":true,"autofocus":false,"autoscroll":true,"elem_classes":[],"type":"text","rtl":false,"show_copy_button":false,"name":"textbox","_selectable":false},"skip_api":false,"component_class_id":"d0491bb0fbd427bdb2a4549c4d1ac869","key":null,"api_info":{"type":"string"},"example_inputs":"Hello!!"},{"id":304,"type":"checkboxgroup","props":{"choices":[["<4B","<4B"],["4B-10B","4B-10B"],["10B-20B","10B-20B"],["20B-40B","20B-40B"],[">40B",">40B"],["Unknown","Unknown"]],"value":["<4B","4B-10B","10B-20B","20B-40B",">40B","Unknown"],"type":"value","label":"Model Size","show_label":true,"container":true,"min_width":160,"interactive":true,"visible":true,"elem_classes":[],"name":"checkboxgroup","_selectable":false},"skip_api":false,"component_class_id":"0635a5d3bf87369f1c2c1c69f8a3d0cc","key":null,"api_info":{"items":{"enum":["<4B","4B-10B","10B-20B","20B-40B",">40B","Unknown"],"type":"string"},"title":"Checkbox Group","type":"array"},"example_inputs":["<4B"]},{"id":305,"type":"checkboxgroup","props":{"choices":[["API","API"],["OpenSource","OpenSource"]],"value":["API","OpenSource"],"type":"value","label":"Model Type","show_label":true,"container":true,"min_width":160,"interactive":true,"visible":true,"elem_classes":[],"name":"checkboxgroup","_selectable":false},"skip_api":false,"component_class_id":"0635a5d3bf87369f1c2c1c69f8a3d0cc","key":null,"api_info":{"items":{"enum":["API","OpenSource"],"type":"string"},"title":"Checkbox Group","type":"array"},"example_inputs":["API"]},{"id":306,"type":"form","props":{"scale":3,"min_width":480,"name":"form"},"skip_api":true,"component_class_id":"43cda85c6ff7a5dd8f83d29496b014ee","key":null},{"id":307,"type":"dataframe","props":{"value":{"headers":["Rank","Method","Param (B)","Language Model","Vision Model","Eval Date","Overall"],"data":[[1,"Qwen2.5-VL-72B",73.4,"Qwen2.5-72B","QwenViT","2025/02/02",73.8],[2,"GPT-4.1-20250414",null,"","","2025/04/16",73.1],[3,"Qwen2-VL-72B",73.4,"Qwen2-72B","QwenViT","2024/10/28",72.3],[4,"Ovis2-16B",16.2,"Qwen2.5-14B","AIMv2 Huge","2025/02/18",72.1],[5,"GPT-4o (0513, detail-high)",null,"","","2024/05/31",72.0],[6,"GPT-4.1-mini-20250414",null,"","","2025/04/16",71.9],[7,"Qwen-VL-Max-0809",72.0,"Qwen2-72B","QwenViT","2024/09/12",71.9],[8,"InternVL3-38B",38.4,"Qwen2.5-32B","InternViT-6B-v2.5","2025/04/14",71.8],[9,"GLM-4v-Plus",null,"","","2024/12/11",71.8],[10,"Claude3.5-Sonnet",null,"","","2024/06/24",71.7],[11,"InternVL3-78B",78.4,"Qwen2.5-72B","InternViT-6B-v2.5","2025/04/14",71.7],[12,"InternVL2.5-38B-MPO",38.0,"Qwen-2.5-32B","InternViT-6B-v2.5","2024/12/28",71.5],[13,"MiMo-VL-7B",8.31,"Mimo-7B","Qwen2.5-ViT","2025/07/02",71.5],[14,"GLM-4v-Plus-20250111",null,"","","2025/01/25",71.4],[15,"Ovis2-34B",34.9,"Qwen2.5-32B","AIMv2-1B","2025/02/18",71.3],[16,"Ovis1.6-Gemma2-27B",28.9,"Gemma2-27B","SigLIP-400M","2024/11/29",71.1],[17,"GPT-4o (0806, detail-high)",null,"","","2024/08/08",70.8],[18,"Gemini-1.5-Pro",null,"","","2024/06/10",70.8],[19,"InternVL2.5-78B-MPO",78.0,"Qwen-2.5-72B","InternViT-6B-v2.5","2024/12/29",70.8],[20,"Qwen2.5-VL-7B",8.29,"Qwen2.5-7B","QwenViT","2025/02/02",70.7],[21,"Ovis2-8B",8.94,"Qwen2.5-7B","AIMv2 Huge","2025/02/18",70.4],[22,"InternVL3-14B",15.1,"Qwen2.5-14B","InternViT-300M-v2.5","2025/04/14",70.1],[23,"InternVL2.5-26B-MPO",26.0,"InternLM2.5-20B","InternViT-6B-v2.5","2024/12/28",70.1],[24,"InternVL2-Llama3-76B",76.0,"Llama-3-70B-Instruct","InternViT-6B","2024/07/19",70.0],[25,"VARCO-VISION-14B",15.2,"Qwen2.5-14B","SigLIP-400M","2025/01/02",69.9],[26,"Step-1o",null,"","","2025/01/13",69.9],[27,"InternVL3-8B",7.94,"Qwen2.5-7B","InternViT-300M-v2.5","2025/04/14",69.4],[28,"Ovis2-4B",4.62,"Qwen2.5-3B","AIMv2 Huge","2025/02/18",69.3],[29,"InternVL2.5-8B-MPO",8.0,"InternLM2.5-7B","InternViT-300M-v2.5","2024/12/28",69.3],[30,"GPT-4v (0409, detail-high)",null,"","","2024/05/15",69.3],[31,"MUG-U-7B",7.0,"","","2025/03/19",69.3],[32,"InternVL2-40B",40.0,"Nous-Hermes-2-Yi-34B","InternViT-6B","2024/07/11",69.2],[33,"Qwen-VL-Plus-0809",null,"","","2024/09/17",69.2],[34,"HunYuan-Standard-Vision",null,"","","2025/01/15",69.0],[35,"BailingMM-Pro-0120",81.0,"Bailing-80B","SigLIP-400M","2025/01/25",68.9],[36,"Kimi-VL-A3B-Instruct",16.4,"Moonlight-16B-A3B","MoonViT","2025/04/14",68.9],[37,"Qwen2-VL-7B",8.0,"Qwen2-7B","QwenViT","2024/09/12",68.6],[38,"Gemini-1.5-Flash",null,"","","2024/09/16",68.6],[39,"Phi-4-MultiModal",5.57,"Phi-4-Mini","SigLIP-400M","2025/03/13",68.5],[40,"Qwen2.5-VL-3B",3.75,"Qwen2.5-3B","QwenViT","2025/02/02",68.5],[41,"NVLM-D-72B",79.4,"Qwen2-72B","InternViT-6B","2024/10/19",68.4],[42,"Llama-3.2-90B-Vision-Instruct",88.6,"Llama-3.1-70B","","2024/10/19",68.2],[43,"Ovis1.6-Gemma2-9B",10.2,"Gemma2-9B-It","SigLIP-400M","2024/09/19",67.9],[44,"POINTS1.5-Qwen2.5-7B",8.3,"Qwen-2.5-7B","NaViT","2024/12/06",67.9],[45,"MiniCPM-o-2.6",8.67,"Qwen2.5-7B","SigLIP-400M","2025/01/21",67.9],[46,"abab7-preview",null,"","","2024/12/11",67.7],[47,"Claude3.7-Sonnet",null,"","","2025/02/27",67.6],[48,"Molmo-7B-D",8.0,"Qwen2-7B","CLIP ViT-L/14","2024/10/12",67.6],[49,"InternVL2-26B",26.0,"InternLM2-20B","InternViT-6B","2024/07/11",67.6],[50,"CongRong",null,"","","2024/06/26",67.5],[51,"Taiyi",null,"","","2024/12/11",67.5],[52,"Pixtral-12B",13.0,"Nemo-12B","ViT-400M","2024/09/16",67.4],[53,"Ovis1.5-Gemma2-9B",11.4,"Gemma2-9B-It","SigLIP-400M","2024/08/04",67.4],[54,"InternVL2-8B-MPO",8.0,"InternLM2.5-7B","InternViT-300M","2024/11/25",67.4],[55,"Ovis2-2B",2.46,"Qwen2.5-1.5B","AIMv2 Large","2025/02/18",67.4],[56,"RBDash-v1.5",79.0,"Qwen2-72B","CLIP ViT-L/14
InternViT-6B","2024/11/17",67.3],[57,"InternVL2-8B",8.0,"InternLM2.5-7B","InternViT-300M","2024/07/11",67.3],[58,"Gemma3-27B",27.4,"Gemma3-27B","SigLIP-400M","2025/03/19",67.0],[59,"GPT-4.1-nano-20250414",null,"","","2025/04/16",67.0],[60,"VITA-1.5",8.3,"Qwen2-7B","InternViT-300M","2025/01/01",66.9],[61,"InternVL2-8B-MPO-CoT",8.0,"InternLM2.5-7B","InternViT-300M","2024/11/25",66.8],[62,"MMAlaya2",26.0,"InternLM2-20B","InternViT-6B","2024/08/27",66.8],[63,"InternVL2.5-4B-MPO",4.0,"Qwen-2.5-3B","InternViT-300M-v2.5","2024/12/28",66.8],[64,"InternLM-XComposer2.5",8.0,"InternLM2-7B","CLIP ViT-L/14","2024/07/11",66.5],[65,"InternVL-Chat-V1.5",26.0,"InternLM2-20B","InternViT-6B","2024/04/17",66.4],[66,"Aria",25.3,"Aria-MoE","SigLIP-400M","2024/12/05",66.4],[67,"Ovis1.5-Llama3-8B",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/07/29",66.4],[68,"Step-1.5V-mini",null,"","","2024/12/11",66.4],[69,"Idefics3-8B-Llama3",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/08/27",66.2],[70,"SAIL-VL-2B",2.1,"Qwen2.5-1.5B","InternViT-300M","2024/12/25",66.1],[71,"CogVLM2-19B-Chat",19.0,"Llama-3-8B-Instruct","EVA2-CLIP-E","2024/05/31",66.0],[72,"LLaVA-Next-Yi-34B",34.8,"Yi-34B","CLIP ViT-L/14","2024/03/25",65.9],[73,"Llama-3.2-11B-Vision-Instruct",11.0,"Llama-3.1-8B","","2024/10/07",65.8],[74,"MiniCPM-V-2.6",8.0,"Qwen2-7B","SigLIP-400M","2024/08/08",65.7],[75,"LLaVA-OneVision-7B (SI)",8.0,"Qwen2-7B","SigLIP-400M","2024/09/17",65.7],[76,"POINTS-Qwen2.5-7B",8.3,"Qwen-2.5-7B","CLIP ViT-L/14","2024/10/19",65.6],[77,"Eagle-X5-34B-Chat",36.8,"Yi-34B","Clip-448
ConvNeXT-1024
SAM-1024
DET-1024
Pix2Struct-1024","2024/11/29",65.5],[78,"LLaVA-OneVision-7B",8.0,"Qwen2-7B","SigLIP-400M","2024/09/16",65.4],[79,"moonshot-v1-8k",null,"","","2025/03/03",65.3],[80,"InternLM-XComposer2-4KHD",7.0,"InternLM2-7B","CLIP ViT-L/14","2024/06/09",65.2],[81,"Gemma3-12B",12.2,"Gemma3-12B","SigLIP-400M","2025/03/19",65.2],[82,"Cambrian-34B",34.0,"Nous-Hermes-2-Yi-34B","CLIP ViT-L/14","2024/07/18",65.1],[83,"WeMM",7.0,"InternLM2-7B","SigLIP-400M","2024/06/09",65.0],[84,"InternVL3-2B",2.09,"Qwen2.5-1.5B","InternViT-300M-v2.5","2025/04/14",64.8],[85,"Phi-3-Vision",4.2,"Phi-3","CLIP ViT-L/14","2024/05/31",64.2],[86,"POINTS-Yi-1.5-9B",9.5,"Yi-1.5-9B","CLIP ViT-L/14","2024/10/11",64.2],[87,"Vintern-3B-beta",3.7,"Qwen-2.5-3B","InternViT-300M","2024/10/24",64.1],[88,"GPT-4o (0513, detail-low)",null,"","","2024/05/15",64.0],[89,"granite-vision-3.3-2b",2.98,"granite-3.1-2b-instruct","SigLIP2-400M","2025/06/20",63.9],[90,"Ovis1.6-Llama3.2-3B",4.1,"Llama-3.2-3B","SigLIP-400M","2024/10/24",63.7],[91,"InternVL2-4B",4.0,"Phi-3","InternViT-300M","2024/07/11",63.7],[92,"BailingMM-Lite-1203",21.0,"Bailing-20B","SigLIP-400M","2024/12/08",63.7],[93,"OmChat-v2.0-13B",13.0,"Qwen2-7B","InternViT-6B","2024/08/22",63.4],[94,"granite-vision-3.2-2b",2.98,"granite-3.1-2b-instruct","SigLip","2025/06/20",63.2],[95,"XinYuan-VL-2B-Instruct",2.0,"Qwen2-1.5B","QwenViT","2024/09/27",63.0],[96,"Aquila-VL-2B",2.2,"Qwen-2.5-1.5B","SigLIP-400M","2024/10/24",62.8],[97,"Mini-InternVL-Chat-4B-V1.5",4.0,"Phi-3","InternViT-300M","2024/06/10",62.5],[98,"Phi-3.5-Vision",4.0,"Phi-3.5","CLIP ViT-L/14","2024/08/28",62.2],[99,"Yi-Vision",null,"","","2024/08/03",62.1],[100,"Molmo-7B-O",8.0,"Qwen2-7B","CLIP ViT-L/14","2024/10/20",62.1],[101,"BlueLM-V-3B",3.0,"BlueLM-3B","SigLIP-400M","2024/10/30",61.9],[102,"Claude3-Haiku",null,"","","2024/03/28",61.7],[103,"Qwen-VL-Max",null,"QwenLM","","2024/02/02",61.6],[104,"GPT-4o-mini (0718, detail-high)",null,"","","2024/07/20",61.4],[105,"MiniCPM-Llama3-V2.5",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/05/27",61.4],[106,"Ovis2-1B",1.27,"Qwen2.5-0.5B","AIMv2 Large","2025/02/18",61.4],[107,"Qwen2-VL-2B",2.0,"Qwen2-1.5B","QwenViT","2024/09/12",61.2],[108,"InternVL2.5-2B-MPO",2.0,"InternLM2.5-1.8B","InternViT-300M-v2.5","2024/12/28",61.0],[109,"Gemma3-4B",4.3,"Gemma3-4B","SigLIP-400M","2025/03/19",60.7],[110,"MiniMonkey",2.2,"InternLM2-1.8B","InternViT-300M","2024/09/26",60.7],[111,"SmolVLM2",2.25,"SmolLM2-1.7M","SigLIP-400M","2025/03/13",60.5],[112,"grok-2-vision-1212",null,"","","2025/03/03",60.4],[113,"Eagle-X5-13B",15.0,"Vicuna-v1.5-13B","Clip-448
ConvNeXT-1024
SAM-1024
DET-1024
Pix2Struct-1024","2024/09/26",60.2],[114,"Cambrian-13B",13.0,"Vicuna-v1.5-13B","CLIP ViT-L/14","2024/07/29",60.0],[115,"InternVL2-2B",2.0,"InternLM2-1.8B","InternViT-300M","2024/07/11",59.9],[116,"Cambrian-8B",8.0,"Vicuna-v1.5-7B","CLIP ViT-L/14","2024/07/11",59.7],[117,"Llama-3-MixSense-v1.1",8.0,"Llama-3-8B-Instruct","Florence-2-Large-FT","2024/08/21",59.7],[118,"GLM-4v-9B",9.0,"GLM-4-9B","EVA-02-5B","2024/06/14",59.7],[119,"H2OVL-2B",2.2,"H2O-DANUBE2-1.8B","InternViT-300M","2024/10/31",59.5],[120,"Mini-InternVL-Chat-2B-V1.5",2.0,"InternLM2-1.8B","InternViT-300M","2024/06/10",59.1],[121,"InternVL3-1B",0.94,"Qwen2.5-0.5B","InternViT-300M-v2.5","2025/04/14",58.7],[122,"Ross-Qwen2-7B",8.2,"Qwen2-7B","CLIP ViT-L/14","2025/01/17",58.3],[123,"InternVL2.5-1B-MPO",1.0,"Qwen-2.5-0.5B","InternViT-300M-v2.5","2024/12/28",58.3],[124,"InternLM-XComposer2",7.0,"InternLM2-7B","CLIP ViT-L/14","2024/01/26",58.0],[125,"Eagle-X5-7B",9.0,"Vicuna-v1.5-7B","Clip-448
ConvNeXT-1024
SAM-1024
DET-1024
Pix2Struct-1024","2024/09/26",57.5],[126,"SmolVLM-Instruct",2.3,"SmolLM2-1.7B","SigLIP-400M","2025/01/27",57.5],[127,"Falcon2-VLM-11B",11.4,"Falcon2-11B","CLIP ViT-L/14","2024/10/30",57.3],[128,"MolmoE-1B",7.2,"OLMoE-1B-7B-0924","CLIP ViT-L/14","2024/10/21",57.0],[129,"LLaVA-Next-Llama3",8.0,"Llama-3-8B-Instruct","CLIP ViT-L/14","2024/07/29",56.9],[130,"IDEFICS2-8B",8.0,"Mistral-7B","SigLIP-400M","2024/04/26",56.6],[131,"LLaVA-Next-Qwen-32B",33.0,"Qwen-1.5-32B","SigLIP-400M","2024/08/08",56.3],[132,"XGen-MM-Instruct-Interleave-v1.5",4.4,"Phi-3","SigLIP-400M","2024/09/06",55.9],[133,"LLaVA-Next-Vicuna-13B",13.4,"Vicuna-v1.5-13B","CLIP ViT-L/14","2024/03/25",55.6],[134,"XGen-MM-Instruct-DPO-v1.5",4.4,"Phi-3","SigLIP-400M","2024/09/06",55.4],[135,"Bunny-Llama3-8B",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/07/18",54.9],[136,"Monkey-Chat",9.8,"Qwen-7B","ViT-BigHuge","2024/01/16",54.9],[137,"CogVLM-17B-Chat",17.0,"Vicuna-v1.5-7B","EVA2-CLIP-E","2024/01/03",54.6],[138,"InternVL2-1B",1.0,"Qwen2-0.5B","InternViT-300M","2024/07/11",54.5],[139,"Mantis-8B-Idefics2",8.0,"Mistral-7B","SigLIP-400M","2024/08/08",54.0],[140,"Janus-Pro-7B",7.42,"DeepSeek-7B","SigLIP-400M","2025/02/02",53.9],[141,"DeepSeek-VL-7B",7.3,"DeekSeek-7B","SAM-B
SigLIP-L","2024/03/21",53.1],[142,"LLaVA-OneVision-0.5B",1.0,"Qwen2-0.5B","SigLIP-400M","2024/09/16",52.6],[143,"360VL-70B",70.0,"Llama-3-70B-Instruct","CLIP ViT-L/14","2024/05/25",52.3],[144,"Monkey",9.8,"Qwen-7B","ViT-BigHuge","2024/01/11",52.0],[145,"MiniCPM-V-2",2.8,"MiniCPM-2.4B","SigLIP-400M","2024/04/15",51.9],[146,"LLaVA-Next-Vicuna-7B",7.1,"Vicuna-v1.5-7B","CLIP ViT-L/14","2024/03/25",51.6],[147,"LLaVA-Next-Interleave-7B",8.0,"Qwen-1.5-7B","SigLIP-400M","2024/08/08",51.3],[148,"TransCore-M",13.4,"PCITransGPT-13B","CLIP ViT-L/14","2024/04/16",51.1],[149,"InternLM-XComposer2-1.8B",2.0,"InternLM2-1.8B","CLIP ViT-L/14","2024/06/09",50.8],[150,"Slime-8B",8.0,"Llama-3-8B-Instruct","CLIP ViT-L/14","2024/09/14",50.2],[151,"VILA1.5-13B",13.0,"Vicuna-v1.5-13B","SigLIP-400M","2024/08/25",50.2],[152,"PaliGemma-3B-mix-448",3.0,"Gemma-2B","SigLIP-400M","2024/05/17",49.8],[153,"LLaVA-Next-Interleave-7B-DPO",8.0,"Qwen-1.5-7B","SigLIP-400M","2024/07/29",49.4],[154,"LLaVA-Next-Mistral-7B",7.6,"Mistral-7B","CLIP ViT-L/14","2024/03/25",49.3],[155,"Slime-13B",13.0,"Vicuna-v1.5-13B","CLIP ViT-L/14","2024/09/14",47.8],[156,"SmolVLM2-500M",0.51,"SmolLM2-360M","ViT-93M","2025/03/13",47.7],[157,"ShareGPT4V-13B",13.4,"Vicuna-v1.5-13B","CLIP ViT-L/14","2023/12/08",47.7],[158,"SmolVLM-Synthetic",2.3,"SmolLM2-1.7B","SigLIP-400M","2025/01/27",47.6],[159,"H2OVL-800M",0.83,"H2O-DANUBE3-500M","InternViT-300M","2024/10/31",47.6],[160,"LLaVA-InternLM2-20B (QLoRA)",20.2,"InternLM2-20B","CLIP ViT-L/14","2024/01/17",47.6],[161,"Yi-VL-34B",34.6,"Yi-34B","CLIP ViT-H/14","2024/01/25",47.5],[162,"Parrot-7B",8.0,"Qwen2-7B","CLIP ViT-L/14","2024/08/22",47.5],[163,"Slime-7B",7.0,"Vicuna-v1.5-7B","CLIP ViT-L/14","2024/09/14",47.0],[164,"LLaVA-LLaMA-3-8B",8.0,"Llama-3-8B-Instruct","CLIP ViT-L/14","2024/05/07",46.9],[165,"LLaVA-InternLM2-7B (QLoRA)",8.1,"InternLM2-7B","CLIP ViT-L/14","2024/01/17",46.7],[166,"Yi-VL-6B",6.6,"Yi-6B","CLIP ViT-H/14","2024/01/25",46.2],[167,"OmniLMM-12B",12.0,"Zephyr-7B-β","EVA-02-5B","2024/02/07",46.1],[168,"ShareGPT4V-7B",7.2,"Vicuna-v1.5-7B","CLIP ViT-L/14","2023/12/08",46.1],[169,"SmolVLM-Instruct-DPO",2.3,"SmolLM2-1.7B","SigLIP-400M","2025/01/27",46.1],[170,"Qwen-VL-Chat",9.6,"Qwen-7B","ViT-G/16","2023/08/24",46.0],[171,"LLaVA-OneVision-0.5B (SI)",1.0,"Qwen2-0.5B","SigLIP-400M","2024/09/17",45.7],[172,"Llama-3-VILA1.5-8B",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/08/25",45.2],[173,"Emu3_chat",8.49,"","","2025/01/26",44.9],[174,"Mantis-8B-clip-llama3",8.0,"Llama-3-8B-Instruct","CLIP ViT-L/14","2024/08/08",44.8],[175,"LLaVA-InternLM-7B (QLoRA)",7.6,"InternLM-7B","CLIP ViT-L/14","2023/12/28",44.7],[176,"Mantis-8B-siglip-llama3",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/08/08",44.7],[177,"LLaVA-v1.5-13B",13.4,"Vicuna-v1.5-13B","CLIP ViT-L/14","2023/10/05",44.6],[178,"mPLUG-Owl2",8.2,"Llama-2-7B","CLIP ViT-L/14","2023/11/10",44.4],[179,"DeepSeek-VL-1.3B",2.0,"DeekSeek-1B","SAM-B
SigLIP-L","2024/03/21",43.7],[180,"LLaVA-v1.5-13B (QLoRA)",13.4,"Vicuna-v1.5-13B","CLIP ViT-L/14","2023/12/28",43.6],[181,"MiniCPM-V",3.0,"MiniCPM-2.4B","SigLIP-400M","2024/02/07",43.2],[182,"ShareCaptioner",8.0,"InternLM-7B","EVA-G","2024/01/03",42.4],[183,"Emu2_chat",37.0,"Llama-33B","EVA-02-CLIP-E-plus","2024/01/17",42.1],[184,"SmolVLM-500M",0.51,"SmolLM2-360M","ViT-93M","2025/01/27",41.9],[185,"IDEFICS-80B-Instruct",80.0,"Llama-65B","CLIP ViT-H/14","2023/07/25",41.5],[186,"VILA1.5-3B",3.0,"Sheared-LLaMA-2.7B","SigLIP-400M","2024/08/25",41.4],[187,"LLaVA-v1.5-7B",7.2,"Vicuna-v1.5-7B","CLIP ViT-L/14","2023/10/05",41.3],[188,"LLaVA-v1.5-7B (QLoRA)",7.2,"Vicuna-v1.5-7B","CLIP ViT-L/14","2023/12/28",41.1],[189,"Qwen-VL",9.6,"Qwen-7B","ViT-G/16","2023/08/24",40.1],[190,"Chameleon-30B",30.0,"","","2024/07/29",39.4],[191,"Janus-1.3B",2.1,"DeepSeek-1B","SigLIP-400M","2024/10/24",38.5],[192,"Moondream1",1.9,"SigLIP-400M","Phi-1.5","2024/09/26",38.2],[193,"abab6.5s",null,"","","2024/12/11",37.5],[194,"AKI-4B",4.33,"Phi-3.5","SigLIP-400M","2025/03/25",37.2],[195,"IDEFICS-9B-Instruct",9.0,"Llama-7B","CLIP ViT-H/14","2023/07/25",35.4],[196,"XVERSE-V-13B",13.0,"XVERSE-13B","CLIP ViT-L/14","2024/05/10",35.3],[197,"Mantis-8B-Fuyu",8.0,"Fuyu-8B","","2024/09/07",33.6],[198,"SmolVLM2-256M",0.26,"SmolLM2-135M","ViT-93M","2025/03/13",33.0],[199,"MMAlaya",7.8,"Alaya-7B-Chat","EVA-G","2024/01/29",32.9],[200,"LLaVA-v1-7B",7.2,"Llama-7B","CLIP ViT-L/14","2023/04/17",31.2],[201,"VisualGLM",8.0,"ChatGLM 6B","EVA-CLIP","2023/05/17",30.2],[202,"Chameleon-7B",7.0,"","","2024/07/29",29.7],[203,"PandaGPT-13B",14.0,"Vicuna-13B","ImageBind ViT-H/14","2023/05/25",29.6],[204,"InstructBLIP-7B",8.0,"Vicuna-7B","EVA-G","2023/05/11",29.5],[205,"OpenFlamingo v2",9.0,"MPT 7B","CLIP ViT-L/14","2023/06/28",28.7],[206,"Claude3-Sonnet",null,"","","2024/03/28",27.1],[207,"Kosmos2",1.7,"","","2024/10/19",25.3],[208,"MiniGPT-4-v2",8.0,"Llama-2-13B","EVA-G","2023/10/27",23.3],[209,"SmolVLM-256M",0.26,"SmolLM2-135M","ViT-93M","2025/01/27",20.4],[210,"MiniGPT-4-v1-7B",8.0,"Vicuna-7B","EVA-G","2023/04/20",15.2],[211,"InternLM-XComposer",8.0,"InternLM-7B","EVA-G","2023/09/26",3.6]],"metadata":null},"headers":["1","2","3"],"row_count":[1,"dynamic"],"col_count":[3,"dynamic"],"datatype":["number","html","number","html","html","str","number"],"type":"pandas","latex_delimiters":[{"left":"$$","right":"$$","display":true}],"show_label":true,"height":500,"min_width":160,"interactive":false,"visible":true,"elem_classes":[],"wrap":true,"line_breaks":true,"column_widths":[],"name":"dataframe","_selectable":false},"skip_api":false,"component_class_id":"6a51bb3357f2e94c40fb8d4fbe06aa8e","key":null,"api_info":{"properties":{"headers":{"items":{"type":"string"},"title":"Headers","type":"array"},"data":{"items":{"items":{},"type":"array"},"title":"Data","type":"array"},"metadata":{"anyOf":[{"additionalProperties":{"anyOf":[{"items":{},"type":"array"},{"type":"null"}]},"type":"object"},{"type":"null"}],"default":null,"title":"Metadata"}},"required":["headers","data"],"title":"DataframeData","type":"object"},"example_inputs":{"headers":["a","b"],"data":[["foo","bar"]]}},{"id":308,"type":"textbox","props":{"value":"SEEDBench2_Plus","lines":1,"max_lines":20,"label":"SEEDBench2_Plus","show_label":true,"container":true,"min_width":160,"visible":false,"autofocus":false,"autoscroll":true,"elem_classes":[],"type":"text","rtl":false,"show_copy_button":false,"name":"textbox","_selectable":false},"skip_api":false,"component_class_id":"d0491bb0fbd427bdb2a4549c4d1ac869","key":null,"api_info":{"type":"string"},"example_inputs":"Hello!!"},{"id":309,"type":"form","props":{"scale":0,"min_width":0,"name":"form"},"skip_api":true,"component_class_id":"43cda85c6ff7a5dd8f83d29496b014ee","key":null},{"id":310,"type":"form","props":{"scale":0,"min_width":0,"name":"form"},"skip_api":true,"component_class_id":"43cda85c6ff7a5dd8f83d29496b014ee","key":null},{"id":311,"type":"tabitem","props":{"label":"📊 MMT-Bench_VAL Leaderboard","visible":true,"interactive":true,"id":27,"elem_id":"MMT-Bench_VAL","name":"tab"},"skip_api":true,"component_class_id":"18f46968e2b273dc5dbda0fe78433d7e","key":null},{"id":312,"type":"markdown","props":{"value":"## MMT-Bench Validation Evaluation Results\n\n- MMT-Bench comprises 31,325 meticulously curated multi-choice visual questions from various multimodal scenarios such as vehicle driving and embodied navigation, covering 32 core meta-tasks and 162 subtasks in multimodal understanding.\n- MMT-Bench_VAL is the validation set of MMT-Bench. MMT-Bench_ALL includes both validation and test sets. The suffix `MI`, such as `MMT-Bench_VAL_MI`, represents the multi-image version of the dataset with several images input. \nThe defualt version is the single-image version, which concats the multiple images into a single image as input.","show_label":true,"rtl":false,"latex_delimiters":[{"left":"$$","right":"$$","display":true}],"visible":true,"elem_classes":[],"sanitize_html":true,"line_breaks":false,"header_links":false,"show_copy_button":false,"name":"markdown","_selectable":false},"skip_api":false,"component_class_id":"0f35515b9a3362b42bb6721c836157a0","key":null,"api_info":{"type":"string"},"example_inputs":"# Hello!"},{"id":313,"type":"checkboxgroup","props":{"choices":[["Overall","Overall"],["VR","VR"],["Loc","Loc"],["OCR","OCR"],["Count","Count"],["HLN","HLN"],["IR","IR"],["3D","3D"],["VC","VC"],["VG","VG"],["DU","DU"],["AR","AR"],["PLP","PLP"],["I2IT","I2IT"],["RR","RR"],["IQT","IQT"],["Emo","Emo"],["VI","VI"],["MemU","MemU"],["VPU","VPU"],["AND","AND"],["KD","KD"],["VCR","VCR"],["IEJ","IEJ"],["MIA","MIA"],["CIM","CIM"],["TU","TU"],["VP","VP"],["MedU","MedU"],["AUD","AUD"],["DKR","DKR"],["EA","EA"],["GN","GN"],["abstract_visual_recognition","abstract_visual_recognition"],["action_quality_assessment","action_quality_assessment"],["age_gender_race_recognition","age_gender_race_recognition"],["anatomy_identification","anatomy_identification"],["animal_keypoint_detection","animal_keypoint_detection"],["animals_recognition","animals_recognition"],["animated_character_recognition","animated_character_recognition"],["art_design","art_design"],["artwork_emotion_recognition","artwork_emotion_recognition"],["astronomical_recognition","astronomical_recognition"],["attribute_hallucination","attribute_hallucination"],["behavior_anomaly_detection","behavior_anomaly_detection"],["body_emotion_recognition","body_emotion_recognition"],["building_recognition","building_recognition"],["business","business"],["camouflage_object_detection","camouflage_object_detection"],["celebrity_recognition","celebrity_recognition"],["chart_to_table","chart_to_table"],["chart_to_text","chart_to_text"],["chart_vqa","chart_vqa"],["chemical_apparatusn_recognition","chemical_apparatusn_recognition"],["clock_reading","clock_reading"],["clothes_keypoint_detection","clothes_keypoint_detection"],["color_assimilation","color_assimilation"],["color_constancy","color_constancy"],["color_contrast","color_contrast"],["color_recognition","color_recognition"],["counting_by_category","counting_by_category"],["counting_by_reasoning","counting_by_reasoning"],["counting_by_visual_prompting","counting_by_visual_prompting"],["crowd_counting","crowd_counting"],["deepfake_detection","deepfake_detection"],["depth_estimation","depth_estimation"],["disaster_recognition","disaster_recognition"],["disease_diagnose","disease_diagnose"],["doc_vqa","doc_vqa"],["electronic_object_recognition","electronic_object_recognition"],["eqn2latex","eqn2latex"],["exist_hallucination","exist_hallucination"],["facail_expression_change_recognition","facail_expression_change_recognition"],["face_detection","face_detection"],["face_mask_anomaly_dectection","face_mask_anomaly_dectection"],["face_retrieval","face_retrieval"],["facial_expression_recognition","facial_expression_recognition"],["fashion_recognition","fashion_recognition"],["film_and_television_recognition","film_and_television_recognition"],["font_recognition","font_recognition"],["food_recognition","food_recognition"],["furniture_keypoint_detection","furniture_keypoint_detection"],["gaze_estimation","gaze_estimation"],["general_action_recognition","general_action_recognition"],["geometrical_perspective","geometrical_perspective"],["geometrical_relativity","geometrical_relativity"],["gesture_recognition","gesture_recognition"],["google_apps","google_apps"],["gui_general","gui_general"],["gui_install","gui_install"],["handwritten_mathematical_expression_recognition","handwritten_mathematical_expression_recognition"],["handwritten_retrieval","handwritten_retrieval"],["handwritten_text_recognition","handwritten_text_recognition"],["health_medicine","health_medicine"],["helmet_anomaly_detection","helmet_anomaly_detection"],["human_interaction_understanding","human_interaction_understanding"],["human_keypoint_detection","human_keypoint_detection"],["human_object_interaction_recognition","human_object_interaction_recognition"],["humanitites_social_science","humanitites_social_science"],["image2image_retrieval","image2image_retrieval"],["image_based_action_recognition","image_based_action_recognition"],["image_captioning","image_captioning"],["image_captioning_paragraph","image_captioning_paragraph"],["image_colorization","image_colorization"],["image_dense_captioning","image_dense_captioning"],["image_matting","image_matting"],["image_quality_assessment","image_quality_assessment"],["image_season_recognition","image_season_recognition"],["industrial_produce_anomaly_detection","industrial_produce_anomaly_detection"],["instance_captioning","instance_captioning"],["interactive_segmentation","interactive_segmentation"],["jigsaw_puzzle_solving","jigsaw_puzzle_solving"],["landmark_recognition","landmark_recognition"],["lesion_grading","lesion_grading"],["logo_and_brand_recognition","logo_and_brand_recognition"],["lvlm_response_judgement","lvlm_response_judgement"],["medical_modality_recognition","medical_modality_recognition"],["meme_image_understanding","meme_image_understanding"],["meme_vedio_understanding","meme_vedio_understanding"],["mevis","mevis"],["micro_expression_recognition","micro_expression_recognition"],["multiple_image_captioning","multiple_image_captioning"],["multiple_instance_captioning","multiple_instance_captioning"],["multiple_view_image_understanding","multiple_view_image_understanding"],["muscial_instrument_recognition","muscial_instrument_recognition"],["national_flag_recognition","national_flag_recognition"],["navigation","navigation"],["next_img_prediction","next_img_prediction"],["object_detection","object_detection"],["one_shot_detection","one_shot_detection"],["order_hallucination","order_hallucination"],["other_biological_attributes","other_biological_attributes"],["painting_recognition","painting_recognition"],["person_reid","person_reid"],["pixel_localization","pixel_localization"],["pixel_recognition","pixel_recognition"],["plant_recognition","plant_recognition"],["point_tracking","point_tracking"],["polygon_localization","polygon_localization"],["profession_recognition","profession_recognition"],["ravens_progressive_matrices","ravens_progressive_matrices"],["reason_seg","reason_seg"],["referring_detection","referring_detection"],["relation_hallucination","relation_hallucination"],["religious_recognition","religious_recognition"],["remote_sensing_object_detection","remote_sensing_object_detection"],["rock_recognition","rock_recognition"],["rotated_object_detection","rotated_object_detection"],["salient_object_detection_rgb","salient_object_detection_rgb"],["salient_object_detection_rgbd","salient_object_detection_rgbd"],["scene_emotion_recognition","scene_emotion_recognition"],["scene_graph_recognition","scene_graph_recognition"],["scene_recognition","scene_recognition"],["scene_text_recognition","scene_text_recognition"],["science","science"],["screenshot2code","screenshot2code"],["sculpture_recognition","sculpture_recognition"],["shape_recognition","shape_recognition"],["sign_language_recognition","sign_language_recognition"],["single_object_tracking","single_object_tracking"],["sketch2code","sketch2code"],["sketch2image_retrieval","sketch2image_retrieval"],["small_object_detection","small_object_detection"],["social_relation_recognition","social_relation_recognition"],["som_recognition","som_recognition"],["sports_recognition","sports_recognition"],["spot_the_diff","spot_the_diff"],["spot_the_similarity","spot_the_similarity"],["table_structure_recognition","table_structure_recognition"],["tech_engineering","tech_engineering"],["temporal_anticipation","temporal_anticipation"],["temporal_localization","temporal_localization"],["temporal_ordering","temporal_ordering"],["temporal_sequence_understanding","temporal_sequence_understanding"],["text2image_retrieval","text2image_retrieval"],["texture_material_recognition","texture_material_recognition"],["threed_cad_recognition","threed_cad_recognition"],["threed_indoor_recognition","threed_indoor_recognition"],["traffic_anomaly_detection","traffic_anomaly_detection"],["traffic_light_understanding","traffic_light_understanding"],["traffic_participants_understanding","traffic_participants_understanding"],["traffic_sign_understanding","traffic_sign_understanding"],["transparent_object_detection","transparent_object_detection"],["vehicle_keypoint_detection","vehicle_keypoint_detection"],["vehicle_recognition","vehicle_recognition"],["vehicle_retrieval","vehicle_retrieval"],["video_captioning","video_captioning"],["visual_document_information_extraction","visual_document_information_extraction"],["visual_prompt_understanding","visual_prompt_understanding"],["waste_recognition","waste_recognition"],["weapon_recognition","weapon_recognition"],["weather_recognition","weather_recognition"],["web_shopping","web_shopping"],["whoops","whoops"],["writing_poetry_from_image","writing_poetry_from_image"]],"value":["Overall"],"type":"value","label":"MMT-Bench_VAL CheckBoxes","show_label":true,"container":true,"min_width":160,"interactive":true,"visible":true,"elem_classes":[],"name":"checkboxgroup","_selectable":false},"skip_api":false,"component_class_id":"0635a5d3bf87369f1c2c1c69f8a3d0cc","key":null,"api_info":{"items":{"enum":["Overall","VR","Loc","OCR","Count","HLN","IR","3D","VC","VG","DU","AR","PLP","I2IT","RR","IQT","Emo","VI","MemU","VPU","AND","KD","VCR","IEJ","MIA","CIM","TU","VP","MedU","AUD","DKR","EA","GN","abstract_visual_recognition","action_quality_assessment","age_gender_race_recognition","anatomy_identification","animal_keypoint_detection","animals_recognition","animated_character_recognition","art_design","artwork_emotion_recognition","astronomical_recognition","attribute_hallucination","behavior_anomaly_detection","body_emotion_recognition","building_recognition","business","camouflage_object_detection","celebrity_recognition","chart_to_table","chart_to_text","chart_vqa","chemical_apparatusn_recognition","clock_reading","clothes_keypoint_detection","color_assimilation","color_constancy","color_contrast","color_recognition","counting_by_category","counting_by_reasoning","counting_by_visual_prompting","crowd_counting","deepfake_detection","depth_estimation","disaster_recognition","disease_diagnose","doc_vqa","electronic_object_recognition","eqn2latex","exist_hallucination","facail_expression_change_recognition","face_detection","face_mask_anomaly_dectection","face_retrieval","facial_expression_recognition","fashion_recognition","film_and_television_recognition","font_recognition","food_recognition","furniture_keypoint_detection","gaze_estimation","general_action_recognition","geometrical_perspective","geometrical_relativity","gesture_recognition","google_apps","gui_general","gui_install","handwritten_mathematical_expression_recognition","handwritten_retrieval","handwritten_text_recognition","health_medicine","helmet_anomaly_detection","human_interaction_understanding","human_keypoint_detection","human_object_interaction_recognition","humanitites_social_science","image2image_retrieval","image_based_action_recognition","image_captioning","image_captioning_paragraph","image_colorization","image_dense_captioning","image_matting","image_quality_assessment","image_season_recognition","industrial_produce_anomaly_detection","instance_captioning","interactive_segmentation","jigsaw_puzzle_solving","landmark_recognition","lesion_grading","logo_and_brand_recognition","lvlm_response_judgement","medical_modality_recognition","meme_image_understanding","meme_vedio_understanding","mevis","micro_expression_recognition","multiple_image_captioning","multiple_instance_captioning","multiple_view_image_understanding","muscial_instrument_recognition","national_flag_recognition","navigation","next_img_prediction","object_detection","one_shot_detection","order_hallucination","other_biological_attributes","painting_recognition","person_reid","pixel_localization","pixel_recognition","plant_recognition","point_tracking","polygon_localization","profession_recognition","ravens_progressive_matrices","reason_seg","referring_detection","relation_hallucination","religious_recognition","remote_sensing_object_detection","rock_recognition","rotated_object_detection","salient_object_detection_rgb","salient_object_detection_rgbd","scene_emotion_recognition","scene_graph_recognition","scene_recognition","scene_text_recognition","science","screenshot2code","sculpture_recognition","shape_recognition","sign_language_recognition","single_object_tracking","sketch2code","sketch2image_retrieval","small_object_detection","social_relation_recognition","som_recognition","sports_recognition","spot_the_diff","spot_the_similarity","table_structure_recognition","tech_engineering","temporal_anticipation","temporal_localization","temporal_ordering","temporal_sequence_understanding","text2image_retrieval","texture_material_recognition","threed_cad_recognition","threed_indoor_recognition","traffic_anomaly_detection","traffic_light_understanding","traffic_participants_understanding","traffic_sign_understanding","transparent_object_detection","vehicle_keypoint_detection","vehicle_recognition","vehicle_retrieval","video_captioning","visual_document_information_extraction","visual_prompt_understanding","waste_recognition","weapon_recognition","weather_recognition","web_shopping","whoops","writing_poetry_from_image"],"type":"string"},"title":"Checkbox Group","type":"array"},"example_inputs":["Overall"]},{"id":314,"type":"row","props":{"variant":"default","visible":true,"equal_height":true,"show_progress":false,"name":"row"},"skip_api":true,"component_class_id":"b5cf3d15e2293fb5ccc071d7b8d69f64","key":null},{"id":315,"type":"textbox","props":{"value":"Input the Model Name (fuzzy, case insensitive)","lines":1,"max_lines":20,"label":"Model Name","show_label":true,"container":true,"min_width":160,"interactive":true,"visible":true,"autofocus":false,"autoscroll":true,"elem_classes":[],"type":"text","rtl":false,"show_copy_button":false,"name":"textbox","_selectable":false},"skip_api":false,"component_class_id":"d0491bb0fbd427bdb2a4549c4d1ac869","key":null,"api_info":{"type":"string"},"example_inputs":"Hello!!"},{"id":316,"type":"checkboxgroup","props":{"choices":[["<4B","<4B"],["4B-10B","4B-10B"],["10B-20B","10B-20B"],["20B-40B","20B-40B"],[">40B",">40B"],["Unknown","Unknown"]],"value":["<4B","4B-10B","10B-20B","20B-40B",">40B","Unknown"],"type":"value","label":"Model Size","show_label":true,"container":true,"min_width":160,"interactive":true,"visible":true,"elem_classes":[],"name":"checkboxgroup","_selectable":false},"skip_api":false,"component_class_id":"0635a5d3bf87369f1c2c1c69f8a3d0cc","key":null,"api_info":{"items":{"enum":["<4B","4B-10B","10B-20B","20B-40B",">40B","Unknown"],"type":"string"},"title":"Checkbox Group","type":"array"},"example_inputs":["<4B"]},{"id":317,"type":"checkboxgroup","props":{"choices":[["API","API"],["OpenSource","OpenSource"]],"value":["API","OpenSource"],"type":"value","label":"Model Type","show_label":true,"container":true,"min_width":160,"interactive":true,"visible":true,"elem_classes":[],"name":"checkboxgroup","_selectable":false},"skip_api":false,"component_class_id":"0635a5d3bf87369f1c2c1c69f8a3d0cc","key":null,"api_info":{"items":{"enum":["API","OpenSource"],"type":"string"},"title":"Checkbox Group","type":"array"},"example_inputs":["API"]},{"id":318,"type":"form","props":{"scale":3,"min_width":480,"name":"form"},"skip_api":true,"component_class_id":"43cda85c6ff7a5dd8f83d29496b014ee","key":null},{"id":319,"type":"dataframe","props":{"value":{"headers":["Rank","Method","Param (B)","Language Model","Vision Model","Eval Date","Overall"],"data":[[1,"InternVL3-78B",78.4,"Qwen2.5-72B","InternViT-6B-v2.5","2025/04/14",72.6],[2,"InternVL3-38B",38.4,"Qwen2.5-32B","InternViT-6B-v2.5","2025/04/14",71.9],[3,"Ovis2-34B",34.9,"Qwen2.5-32B","AIMv2-1B","2025/02/18",71.2],[4,"Qwen2-VL-72B",73.4,"Qwen2-72B","QwenViT","2024/10/28",71.2],[5,"Qwen-VL-Max-0809",72.0,"Qwen2-72B","QwenViT","2024/09/12",71.2],[6,"GPT-4.1-20250414",null,"","","2025/04/16",71.1],[7,"InternVL2.5-78B-MPO",78.0,"Qwen-2.5-72B","InternViT-6B-v2.5","2024/12/29",70.7],[8,"InternVL3-14B",15.1,"Qwen2.5-14B","InternViT-300M-v2.5","2025/04/14",69.7],[9,"Step-1o",null,"","","2025/01/13",69.6],[10,"Ovis2-16B",16.2,"Qwen2.5-14B","AIMv2 Huge","2025/02/18",69.2],[11,"InternVL2.5-38B-MPO",38.0,"Qwen-2.5-32B","InternViT-6B-v2.5","2024/12/28",69.1],[12,"Qwen2.5-VL-72B",73.4,"Qwen2.5-72B","QwenViT","2025/02/02",69.0],[13,"Taiyi",null,"","","2024/12/11",68.7],[14,"Ovis1.6-Gemma2-27B",28.9,"Gemma2-27B","SigLIP-400M","2024/11/29",68.2],[15,"GPT-4o (0806, detail-high)",null,"","","2024/08/08",67.7],[16,"InternVL2-Llama3-76B",76.0,"Llama-3-70B-Instruct","InternViT-6B","2024/07/19",67.6],[17,"grok-2-vision-1212",null,"","","2025/03/03",67.6],[18,"GPT-4o (0513, detail-high)",null,"","","2024/05/31",67.3],[19,"Ovis2-8B",8.94,"Qwen2.5-7B","AIMv2 Huge","2025/02/18",66.6],[20,"InternVL2-40B",40.0,"Nous-Hermes-2-Yi-34B","InternViT-6B","2024/07/11",66.1],[21,"HunYuan-Standard-Vision",null,"","","2025/01/15",66.1],[22,"GLM-4v-Plus-20250111",null,"","","2025/01/25",66.0],[23,"RBDash-v1.5",79.0,"Qwen2-72B","CLIP ViT-L/14
InternViT-6B","2024/11/17",65.9],[24,"InternVL2.5-26B-MPO",26.0,"InternLM2.5-20B","InternViT-6B-v2.5","2024/12/28",65.7],[25,"abab7-preview",null,"","","2024/12/11",65.6],[26,"GPT-4o (0513, detail-low)",null,"","","2024/05/15",65.6],[27,"NVLM-D-72B",79.4,"Qwen2-72B","InternViT-6B","2024/10/19",65.3],[28,"InternVL3-9B",9.14,"InternLM3-8B","InternViT-300M-v2.5","2025/04/14",65.3],[29,"VARCO-VISION-14B",15.2,"Qwen2.5-14B","SigLIP-400M","2025/01/02",65.3],[30,"Ovis2-4B",4.62,"Qwen2.5-3B","AIMv2 Huge","2025/02/18",65.2],[31,"InternVL3-8B",7.94,"Qwen2.5-7B","InternViT-300M-v2.5","2025/04/14",64.9],[32,"Ovis1.6-Gemma2-9B",10.2,"Gemma2-9B-It","SigLIP-400M","2024/09/19",64.9],[33,"Kimi-VL-A3B-Instruct",16.4,"Moonlight-16B-A3B","MoonViT","2025/04/14",64.8],[34,"MUG-U-7B",7.0,"","","2025/03/19",64.7],[35,"BailingMM-Pro-0120",81.0,"Bailing-80B","SigLIP-400M","2025/01/25",64.2],[36,"GLM-4v-Plus",null,"","","2024/12/11",64.0],[37,"Step-1.5V-mini",null,"","","2024/12/11",63.6],[38,"Qwen2-VL-7B",8.0,"Qwen2-7B","QwenViT","2024/09/12",63.4],[39,"Gemini-1.5-Pro",null,"","","2024/06/10",63.4],[40,"GPT-4.1-mini-20250414",null,"","","2025/04/16",63.4],[41,"Qwen-VL-Plus-0809",null,"","","2024/09/17",63.1],[42,"Yi-Vision",null,"","","2024/08/03",62.9],[43,"Ovis1.5-Gemma2-9B",11.4,"Gemma2-9B-It","SigLIP-400M","2024/08/04",62.8],[44,"GPT-4v (0409, detail-high)",null,"","","2024/05/15",62.7],[45,"Gemini-1.5-Flash",null,"","","2024/09/16",62.6],[46,"InternVL2.5-8B-MPO",8.0,"InternLM2.5-7B","InternViT-300M-v2.5","2024/12/28",62.5],[47,"MiniCPM-o-2.6",8.67,"Qwen2.5-7B","SigLIP-400M","2025/01/21",62.3],[48,"POINTS-Qwen2.5-7B",8.3,"Qwen-2.5-7B","CLIP ViT-L/14","2024/10/19",62.3],[49,"Qwen2.5-VL-7B",8.29,"Qwen2.5-7B","QwenViT","2025/02/02",62.1],[50,"Claude3.5-Sonnet",null,"","","2024/06/24",61.8],[51,"POINTS1.5-Qwen2.5-7B",8.3,"Qwen-2.5-7B","NaViT","2024/12/06",61.8],[52,"Ovis2-2B",2.46,"Qwen2.5-1.5B","AIMv2 Large","2025/02/18",61.7],[53,"InternVL2.5-4B-MPO",4.0,"Qwen-2.5-3B","InternViT-300M-v2.5","2024/12/28",61.6],[54,"Aria",25.3,"Aria-MoE","SigLIP-400M","2024/12/05",61.5],[55,"POINTS-Yi-1.5-9B",9.5,"Yi-1.5-9B","CLIP ViT-L/14","2024/10/11",61.5],[56,"GPT-4o-mini (0718, detail-high)",null,"","","2024/07/20",61.2],[57,"OmChat-v2.0-13B",13.0,"Qwen2-7B","InternViT-6B","2024/08/22",61.0],[58,"Qwen2.5-VL-3B",3.75,"Qwen2.5-3B","QwenViT","2025/02/02",61.0],[59,"Gemma3-27B",27.4,"Gemma3-27B","SigLIP-400M","2025/03/19",60.8],[60,"MiniCPM-V-2.6",8.0,"Qwen2-7B","SigLIP-400M","2024/08/08",60.8],[61,"Ovis1.5-Llama3-8B",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/07/29",60.7],[62,"InternVL2-26B",26.0,"InternLM2-20B","InternViT-6B","2024/07/11",60.4],[63,"Llama-3.2-90B-Vision-Instruct",88.6,"Llama-3.1-70B","","2024/10/19",60.4],[64,"Phi-4-MultiModal",5.57,"Phi-4-Mini","SigLIP-400M","2025/03/13",60.4],[65,"CongRong",null,"","","2024/06/26",60.2],[66,"InternVL2-8B-MPO-CoT",8.0,"InternLM2.5-7B","InternViT-300M","2024/11/25",60.1],[67,"Claude3.7-Sonnet",null,"","","2025/02/27",60.1],[68,"InternVL2-8B-MPO",8.0,"InternLM2.5-7B","InternViT-300M","2024/11/25",60.0],[69,"Eagle-X5-34B-Chat",36.8,"Yi-34B","Clip-448
ConvNeXT-1024
SAM-1024
DET-1024
Pix2Struct-1024","2024/11/29",60.0],[70,"InternVL2-8B",8.0,"InternLM2.5-7B","InternViT-300M","2024/07/11",59.8],[71,"LLaVA-OneVision-7B (SI)",8.0,"Qwen2-7B","SigLIP-400M","2024/09/17",59.7],[72,"Gemma3-12B",12.2,"Gemma3-12B","SigLIP-400M","2025/03/19",59.7],[73,"VITA-1.5",8.3,"Qwen2-7B","InternViT-300M","2025/01/01",59.5],[74,"Pixtral-12B",13.0,"Nemo-12B","ViT-400M","2024/09/16",59.4],[75,"LLaVA-OneVision-7B",8.0,"Qwen2-7B","SigLIP-400M","2024/09/16",59.3],[76,"Ovis1.6-Llama3.2-3B",4.1,"Llama-3.2-3B","SigLIP-400M","2024/10/24",59.2],[77,"BlueLM-V-3B",3.0,"BlueLM-3B","SigLIP-400M","2024/10/30",59.2],[78,"Ross-Qwen2-7B",8.2,"Qwen2-7B","CLIP ViT-L/14","2025/01/17",59.1],[79,"InternVL3-2B",2.09,"Qwen2.5-1.5B","InternViT-300M-v2.5","2025/04/14",59.1],[80,"BailingMM-Lite-1203",21.0,"Bailing-20B","SigLIP-400M","2024/12/08",58.8],[81,"LLaVA-Next-Yi-34B",34.8,"Yi-34B","CLIP ViT-L/14","2024/03/25",58.6],[82,"Idefics3-8B-Llama3",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/08/27",58.4],[83,"Qwen-VL-Max",null,"QwenLM","","2024/02/02",58.3],[84,"360VL-70B",70.0,"Llama-3-70B-Instruct","CLIP ViT-L/14","2024/05/25",58.0],[85,"InternVL-Chat-V1.5",26.0,"InternLM2-20B","InternViT-6B","2024/04/17",57.8],[86,"Mini-InternVL-Chat-4B-V1.5",4.0,"Phi-3","InternViT-300M","2024/06/10",57.8],[87,"MMAlaya2",26.0,"InternLM2-20B","InternViT-6B","2024/08/27",57.6],[88,"MiniCPM-Llama3-V2.5",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/05/27",57.6],[89,"WeMM",7.0,"InternLM2-7B","SigLIP-400M","2024/06/09",57.5],[90,"InternLM-XComposer2.5",8.0,"InternLM2-7B","CLIP ViT-L/14","2024/07/11",57.1],[91,"SAIL-VL-2B",2.1,"Qwen2.5-1.5B","InternViT-300M","2024/12/25",57.1],[92,"Aquila-VL-2B",2.2,"Qwen-2.5-1.5B","SigLIP-400M","2024/10/24",56.8],[93,"IDEFICS2-8B",8.0,"Mistral-7B","SigLIP-400M","2024/04/26",56.8],[94,"LLaVA-Next-Qwen-32B",33.0,"Qwen-1.5-32B","SigLIP-400M","2024/08/08",56.7],[95,"InternLM-XComposer2-4KHD",7.0,"InternLM2-7B","CLIP ViT-L/14","2024/06/09",56.3],[96,"Molmo-7B-D",8.0,"Qwen2-7B","CLIP ViT-L/14","2024/10/12",56.3],[97,"InternVL2-4B",4.0,"Phi-3","InternViT-300M","2024/07/11",55.9],[98,"XGen-MM-Instruct-Interleave-v1.5",4.4,"Phi-3","SigLIP-400M","2024/09/06",55.9],[99,"Vintern-3B-beta",3.7,"Qwen-2.5-3B","InternViT-300M","2024/10/24",55.8],[100,"granite-vision-3.2-2b",2.98,"granite-3.1-2b-instruct","SigLip","2025/06/20",55.7],[101,"InternLM-XComposer2",7.0,"InternLM2-7B","CLIP ViT-L/14","2024/01/26",55.7],[102,"XGen-MM-Instruct-DPO-v1.5",4.4,"Phi-3","SigLIP-400M","2024/09/06",55.5],[103,"Ovis2-1B",1.27,"Qwen2.5-0.5B","AIMv2 Large","2025/02/18",55.5],[104,"XinYuan-VL-2B-Instruct",2.0,"Qwen2-1.5B","QwenViT","2024/09/27",55.4],[105,"OmniLMM-12B",12.0,"Zephyr-7B-β","EVA-02-5B","2024/02/07",55.3],[106,"GPT-4.1-nano-20250414",null,"","","2025/04/16",55.3],[107,"Llama-3-MixSense-v1.1",8.0,"Llama-3-8B-Instruct","Florence-2-Large-FT","2024/08/21",55.2],[108,"Qwen2-VL-2B",2.0,"Qwen2-1.5B","QwenViT","2024/09/12",55.0],[109,"Bunny-Llama3-8B",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/07/18",54.8],[110,"granite-vision-3.3-2b",2.98,"granite-3.1-2b-instruct","SigLIP2-400M","2025/06/20",54.6],[111,"InternVL2.5-2B-MPO",2.0,"InternLM2.5-1.8B","InternViT-300M-v2.5","2024/12/28",54.4],[112,"Mantis-8B-Idefics2",8.0,"Mistral-7B","SigLIP-400M","2024/08/08",54.3],[113,"Phi-3-Vision",4.2,"Phi-3","CLIP ViT-L/14","2024/05/31",54.2],[114,"SmolVLM2",2.25,"SmolLM2-1.7M","SigLIP-400M","2025/03/13",54.2],[115,"TransCore-M",13.4,"PCITransGPT-13B","CLIP ViT-L/14","2024/04/16",54.1],[116,"CogVLM2-19B-Chat",19.0,"Llama-3-8B-Instruct","EVA2-CLIP-E","2024/05/31",54.0],[117,"RekaEdge",null,"","","2024/05/31",53.9],[118,"Gemma3-4B",4.3,"Gemma3-4B","SigLIP-400M","2025/03/19",53.9],[119,"VILA1.5-13B",13.0,"Vicuna-v1.5-13B","SigLIP-400M","2024/08/25",53.8],[120,"Eagle-X5-13B",15.0,"Vicuna-v1.5-13B","Clip-448
ConvNeXT-1024
SAM-1024
DET-1024
Pix2Struct-1024","2024/09/26",53.7],[121,"Phi-3.5-Vision",4.0,"Phi-3.5","CLIP ViT-L/14","2024/08/28",53.6],[122,"MiniCPM-V-2",2.8,"MiniCPM-2.4B","SigLIP-400M","2024/04/15",53.5],[123,"DeepSeek-VL-7B",7.3,"DeekSeek-7B","SAM-B
SigLIP-L","2024/03/21",53.5],[124,"Yi-VL-34B",34.6,"Yi-34B","CLIP ViT-H/14","2024/01/25",53.4],[125,"LLaVA-InternLM2-20B (QLoRA)",20.2,"InternLM2-20B","CLIP ViT-L/14","2024/01/17",53.3],[126,"Monkey-Chat",9.8,"Qwen-7B","ViT-BigHuge","2024/01/16",53.3],[127,"LLaVA-InternLM2-7B (QLoRA)",8.1,"InternLM2-7B","CLIP ViT-L/14","2024/01/17",53.2],[128,"LLaVA-Next-Llama3",8.0,"Llama-3-8B-Instruct","CLIP ViT-L/14","2024/07/29",53.1],[129,"Llama-3.2-11B-Vision-Instruct",11.0,"Llama-3.1-8B","","2024/10/07",53.1],[130,"LLaVA-Next-Interleave-7B",8.0,"Qwen-1.5-7B","SigLIP-400M","2024/08/08",53.0],[131,"LLaVA-Next-Interleave-7B-DPO",8.0,"Qwen-1.5-7B","SigLIP-400M","2024/07/29",52.8],[132,"Yi-VL-6B",6.6,"Yi-6B","CLIP ViT-H/14","2024/01/25",52.8],[133,"Falcon2-VLM-11B",11.4,"Falcon2-11B","CLIP ViT-L/14","2024/10/30",52.7],[134,"InternVL3-1B",0.94,"Qwen2.5-0.5B","InternViT-300M-v2.5","2025/04/14",52.7],[135,"Eagle-X5-7B",9.0,"Vicuna-v1.5-7B","Clip-448
ConvNeXT-1024
SAM-1024
DET-1024
Pix2Struct-1024","2024/09/26",52.6],[136,"Parrot-7B",8.0,"Qwen2-7B","CLIP ViT-L/14","2024/08/22",52.2],[137,"LLaVA-v1.5-13B",13.4,"Vicuna-v1.5-13B","CLIP ViT-L/14","2023/10/05",52.1],[138,"Molmo-7B-O",8.0,"Qwen2-7B","CLIP ViT-L/14","2024/10/20",52.1],[139,"LLaVA-Next-Vicuna-13B",13.4,"Vicuna-v1.5-13B","CLIP ViT-L/14","2024/03/25",52.1],[140,"ShareGPT4V-13B",13.4,"Vicuna-v1.5-13B","CLIP ViT-L/14","2023/12/08",52.0],[141,"RekaFlash",null,"","","2024/05/07",52.0],[142,"LLaVA-OneVision-0.5B",1.0,"Qwen2-0.5B","SigLIP-400M","2024/09/16",51.6],[143,"Mantis-8B-siglip-llama3",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/08/08",51.6],[144,"SmolVLM-Instruct",2.3,"SmolLM2-1.7B","SigLIP-400M","2025/01/27",51.5],[145,"H2OVL-2B",2.2,"H2O-DANUBE2-1.8B","InternViT-300M","2024/10/31",51.3],[146,"ShareGPT4V-7B",7.2,"Vicuna-v1.5-7B","CLIP ViT-L/14","2023/12/08",51.2],[147,"Mantis-8B-clip-llama3",8.0,"Llama-3-8B-Instruct","CLIP ViT-L/14","2024/08/08",51.1],[148,"InternVL2-2B",2.0,"InternLM2-1.8B","InternViT-300M","2024/07/11",50.8],[149,"InternVL2.5-1B-MPO",1.0,"Qwen-2.5-0.5B","InternViT-300M-v2.5","2024/12/28",50.8],[150,"LLaVA-v1.5-13B (QLoRA)",13.4,"Vicuna-v1.5-13B","CLIP ViT-L/14","2023/12/28",50.8],[151,"CogVLM-17B-Chat",17.0,"Vicuna-v1.5-7B","EVA2-CLIP-E","2024/01/03",50.8],[152,"Slime-13B",13.0,"Vicuna-v1.5-13B","CLIP ViT-L/14","2024/09/14",50.7],[153,"MiniMonkey",2.2,"InternLM2-1.8B","InternViT-300M","2024/09/26",50.4],[154,"mPLUG-Owl2",8.2,"Llama-2-7B","CLIP ViT-L/14","2023/11/10",50.4],[155,"Claude3-Haiku",null,"","","2024/03/28",50.4],[156,"Janus-Pro-7B",7.42,"DeepSeek-7B","SigLIP-400M","2025/02/02",50.3],[157,"LLaVA-Next-Vicuna-7B",7.1,"Vicuna-v1.5-7B","CLIP ViT-L/14","2024/03/25",50.3],[158,"LLaVA-Next-Mistral-7B",7.6,"Mistral-7B","CLIP ViT-L/14","2024/03/25",50.3],[159,"Slime-8B",8.0,"Llama-3-8B-Instruct","CLIP ViT-L/14","2024/09/14",50.2],[160,"MiniCPM-V",3.0,"MiniCPM-2.4B","SigLIP-400M","2024/02/07",50.0],[161,"SmolVLM-Instruct-DPO",2.3,"SmolLM2-1.7B","SigLIP-400M","2025/01/27",49.6],[162,"LLaVA-LLaMA-3-8B",8.0,"Llama-3-8B-Instruct","CLIP ViT-L/14","2024/05/07",49.5],[163,"MolmoE-1B",7.2,"OLMoE-1B-7B-0924","CLIP ViT-L/14","2024/10/21",49.3],[164,"Slime-7B",7.0,"Vicuna-v1.5-7B","CLIP ViT-L/14","2024/09/14",49.2],[165,"DeepSeek-VL-1.3B",2.0,"DeekSeek-1B","SAM-B
SigLIP-L","2024/03/21",49.1],[166,"LLaVA-v1.5-7B (QLoRA)",7.2,"Vicuna-v1.5-7B","CLIP ViT-L/14","2023/12/28",49.1],[167,"VILA1.5-3B",3.0,"Sheared-LLaMA-2.7B","SigLIP-400M","2024/08/25",49.0],[168,"Monkey",9.8,"Qwen-7B","ViT-BigHuge","2024/01/11",49.0],[169,"LLaVA-v1.5-7B",7.2,"Vicuna-v1.5-7B","CLIP ViT-L/14","2023/10/05",48.9],[170,"Mini-InternVL-Chat-2B-V1.5",2.0,"InternLM2-1.8B","InternViT-300M","2024/06/10",48.9],[171,"GLM-4v-9B",9.0,"GLM-4-9B","EVA-02-5B","2024/06/14",48.8],[172,"Llama-3-VILA1.5-8B",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/08/25",48.7],[173,"InternLM-XComposer2-1.8B",2.0,"InternLM2-1.8B","CLIP ViT-L/14","2024/06/09",48.6],[174,"LLaVA-OneVision-0.5B (SI)",1.0,"Qwen2-0.5B","SigLIP-400M","2024/09/17",48.3],[175,"LLaVA-InternLM-7B (QLoRA)",7.6,"InternLM-7B","CLIP ViT-L/14","2023/12/28",48.3],[176,"InternVL2-1B",1.0,"Qwen2-0.5B","InternViT-300M","2024/07/11",48.2],[177,"Qwen-VL-Chat",9.6,"Qwen-7B","ViT-G/16","2023/08/24",47.6],[178,"AKI-4B",4.33,"Phi-3.5","SigLIP-400M","2025/03/25",47.6],[179,"ShareCaptioner",8.0,"InternLM-7B","EVA-G","2024/01/03",47.6],[180,"H2OVL-800M",0.83,"H2O-DANUBE3-500M","InternViT-300M","2024/10/31",47.0],[181,"PaliGemma-3B-mix-448",3.0,"Gemma-2B","SigLIP-400M","2024/05/17",46.9],[182,"Janus-1.3B",2.1,"DeepSeek-1B","SigLIP-400M","2024/10/24",46.6],[183,"SmolVLM-Synthetic",2.3,"SmolLM2-1.7B","SigLIP-400M","2025/01/27",46.4],[184,"Moondream1",1.9,"SigLIP-400M","Phi-1.5","2024/09/26",45.4],[185,"IDEFICS-9B-Instruct",9.0,"Llama-7B","CLIP ViT-H/14","2023/07/25",45.3],[186,"SmolVLM2-500M",0.51,"SmolLM2-360M","ViT-93M","2025/03/13",44.7],[187,"Emu3_chat",8.49,"","","2025/01/26",43.4],[188,"Qwen-VL",9.6,"Qwen-7B","ViT-G/16","2023/08/24",42.9],[189,"Mantis-8B-Fuyu",8.0,"Fuyu-8B","","2024/09/07",42.2],[190,"SmolVLM-500M",0.51,"SmolLM2-360M","ViT-93M","2025/01/27",41.9],[191,"SmolVLM2-256M",0.26,"SmolLM2-135M","ViT-93M","2025/03/13",35.8],[192,"abab6.5s",null,"","","2024/12/11",35.3],[193,"InstructBLIP-7B",8.0,"Vicuna-7B","EVA-G","2023/05/11",35.1],[194,"Chameleon-30B",30.0,"","","2024/07/29",32.4],[195,"PandaGPT-13B",14.0,"Vicuna-13B","ImageBind ViT-H/14","2023/05/25",32.4],[196,"VisualGLM",8.0,"ChatGLM 6B","EVA-CLIP","2023/05/17",30.6],[197,"SmolVLM-256M",0.26,"SmolLM2-135M","ViT-93M","2025/01/27",30.4],[198,"XVERSE-V-13B",13.0,"XVERSE-13B","CLIP ViT-L/14","2024/05/10",29.3],[199,"OpenFlamingo v2",9.0,"MPT 7B","CLIP ViT-L/14","2023/06/28",28.6],[200,"LLaVA-v1-7B",7.2,"Llama-7B","CLIP ViT-L/14","2023/04/17",27.7],[201,"Kosmos2",1.7,"","","2024/10/19",25.5],[202,"Chameleon-7B",7.0,"","","2024/07/29",23.9],[203,"MiniGPT-4-v2",8.0,"Llama-2-13B","EVA-G","2023/10/27",22.1],[204,"MiniGPT-4-v1-7B",8.0,"Vicuna-7B","EVA-G","2023/04/20",16.5],[205,"Claude3-Sonnet",null,"","","2024/03/28",10.2],[206,"moonshot-v1-8k",null,"","","2025/03/03",7.2],[207,"InternLM-XComposer",8.0,"InternLM-7B","EVA-G","2023/09/26",3.2]],"metadata":null},"headers":["1","2","3"],"row_count":[1,"dynamic"],"col_count":[3,"dynamic"],"datatype":["number","html","number","html","html","str","number"],"type":"pandas","latex_delimiters":[{"left":"$$","right":"$$","display":true}],"show_label":true,"height":500,"min_width":160,"interactive":false,"visible":true,"elem_classes":[],"wrap":true,"line_breaks":true,"column_widths":[],"name":"dataframe","_selectable":false},"skip_api":false,"component_class_id":"6a51bb3357f2e94c40fb8d4fbe06aa8e","key":null,"api_info":{"properties":{"headers":{"items":{"type":"string"},"title":"Headers","type":"array"},"data":{"items":{"items":{},"type":"array"},"title":"Data","type":"array"},"metadata":{"anyOf":[{"additionalProperties":{"anyOf":[{"items":{},"type":"array"},{"type":"null"}]},"type":"object"},{"type":"null"}],"default":null,"title":"Metadata"}},"required":["headers","data"],"title":"DataframeData","type":"object"},"example_inputs":{"headers":["a","b"],"data":[["foo","bar"]]}},{"id":320,"type":"textbox","props":{"value":"MMT-Bench_VAL","lines":1,"max_lines":20,"label":"MMT-Bench_VAL","show_label":true,"container":true,"min_width":160,"visible":false,"autofocus":false,"autoscroll":true,"elem_classes":[],"type":"text","rtl":false,"show_copy_button":false,"name":"textbox","_selectable":false},"skip_api":false,"component_class_id":"d0491bb0fbd427bdb2a4549c4d1ac869","key":null,"api_info":{"type":"string"},"example_inputs":"Hello!!"},{"id":321,"type":"form","props":{"scale":0,"min_width":0,"name":"form"},"skip_api":true,"component_class_id":"43cda85c6ff7a5dd8f83d29496b014ee","key":null},{"id":322,"type":"form","props":{"scale":0,"min_width":0,"name":"form"},"skip_api":true,"component_class_id":"43cda85c6ff7a5dd8f83d29496b014ee","key":null},{"id":323,"type":"tabitem","props":{"label":"📊 BLINK Leaderboard","visible":true,"interactive":true,"id":28,"elem_id":"BLINK","name":"tab"},"skip_api":true,"component_class_id":"18f46968e2b273dc5dbda0fe78433d7e","key":null},{"id":324,"type":"markdown","props":{"value":"## BLINK Test Evaluation Results\n\n- BLINK is a benchmark containing 14 visual perception tasks that can be solved by humans “within a blink”, but pose significant challenges for current multimodal large language models (LLMs).\n- We evaluate BLINK on the test set of the benchmark, which contains 1901 visual questions in multi-choice format. ","show_label":true,"rtl":false,"latex_delimiters":[{"left":"$$","right":"$$","display":true}],"visible":true,"elem_classes":[],"sanitize_html":true,"line_breaks":false,"header_links":false,"show_copy_button":false,"name":"markdown","_selectable":false},"skip_api":false,"component_class_id":"0f35515b9a3362b42bb6721c836157a0","key":null,"api_info":{"type":"string"},"example_inputs":"# Hello!"},{"id":325,"type":"checkboxgroup","props":{"choices":[["Overall","Overall"],["Art_Style","Art_Style"],["Counting","Counting"],["Forensic_Detection","Forensic_Detection"],["Functional_Correspondence","Functional_Correspondence"],["IQ_Test","IQ_Test"],["Jigsaw","Jigsaw"],["Multi-view_Reasoning","Multi-view_Reasoning"],["Object_Localization","Object_Localization"],["Relative_Depth","Relative_Depth"],["Relative_Reflectance","Relative_Reflectance"],["Semantic_Correspondence","Semantic_Correspondence"],["Spatial_Relation","Spatial_Relation"],["Visual_Correspondence","Visual_Correspondence"],["Visual_Similarity","Visual_Similarity"]],"value":["Overall"],"type":"value","label":"BLINK CheckBoxes","show_label":true,"container":true,"min_width":160,"interactive":true,"visible":true,"elem_classes":[],"name":"checkboxgroup","_selectable":false},"skip_api":false,"component_class_id":"0635a5d3bf87369f1c2c1c69f8a3d0cc","key":null,"api_info":{"items":{"enum":["Overall","Art_Style","Counting","Forensic_Detection","Functional_Correspondence","IQ_Test","Jigsaw","Multi-view_Reasoning","Object_Localization","Relative_Depth","Relative_Reflectance","Semantic_Correspondence","Spatial_Relation","Visual_Correspondence","Visual_Similarity"],"type":"string"},"title":"Checkbox Group","type":"array"},"example_inputs":["Overall"]},{"id":326,"type":"row","props":{"variant":"default","visible":true,"equal_height":true,"show_progress":false,"name":"row"},"skip_api":true,"component_class_id":"b5cf3d15e2293fb5ccc071d7b8d69f64","key":null},{"id":327,"type":"textbox","props":{"value":"Input the Model Name (fuzzy, case insensitive)","lines":1,"max_lines":20,"label":"Model Name","show_label":true,"container":true,"min_width":160,"interactive":true,"visible":true,"autofocus":false,"autoscroll":true,"elem_classes":[],"type":"text","rtl":false,"show_copy_button":false,"name":"textbox","_selectable":false},"skip_api":false,"component_class_id":"d0491bb0fbd427bdb2a4549c4d1ac869","key":null,"api_info":{"type":"string"},"example_inputs":"Hello!!"},{"id":328,"type":"checkboxgroup","props":{"choices":[["<4B","<4B"],["4B-10B","4B-10B"],["10B-20B","10B-20B"],["20B-40B","20B-40B"],[">40B",">40B"],["Unknown","Unknown"]],"value":["<4B","4B-10B","10B-20B","20B-40B",">40B","Unknown"],"type":"value","label":"Model Size","show_label":true,"container":true,"min_width":160,"interactive":true,"visible":true,"elem_classes":[],"name":"checkboxgroup","_selectable":false},"skip_api":false,"component_class_id":"0635a5d3bf87369f1c2c1c69f8a3d0cc","key":null,"api_info":{"items":{"enum":["<4B","4B-10B","10B-20B","20B-40B",">40B","Unknown"],"type":"string"},"title":"Checkbox Group","type":"array"},"example_inputs":["<4B"]},{"id":329,"type":"checkboxgroup","props":{"choices":[["API","API"],["OpenSource","OpenSource"]],"value":["API","OpenSource"],"type":"value","label":"Model Type","show_label":true,"container":true,"min_width":160,"interactive":true,"visible":true,"elem_classes":[],"name":"checkboxgroup","_selectable":false},"skip_api":false,"component_class_id":"0635a5d3bf87369f1c2c1c69f8a3d0cc","key":null,"api_info":{"items":{"enum":["API","OpenSource"],"type":"string"},"title":"Checkbox Group","type":"array"},"example_inputs":["API"]},{"id":330,"type":"form","props":{"scale":3,"min_width":480,"name":"form"},"skip_api":true,"component_class_id":"43cda85c6ff7a5dd8f83d29496b014ee","key":null},{"id":331,"type":"dataframe","props":{"value":{"headers":["Rank","Method","Param (B)","Language Model","Vision Model","Eval Date","Overall"],"data":[[1,"GPT-4.1-20250414",null,"","","2025/04/16",68.5],[2,"GPT-4o (0513, detail-high)",null,"","","2024/05/31",68.0],[3,"InternVL3-78B",78.4,"Qwen2.5-72B","InternViT-6B-v2.5","2025/04/14",66.4],[4,"InternVL2.5-78B-MPO",78.0,"Qwen-2.5-72B","InternViT-6B-v2.5","2024/12/29",65.7],[5,"Step-1o",null,"","","2025/01/13",65.4],[6,"Taiyi",null,"","","2024/12/11",64.7],[7,"GPT-4o (0806, detail-high)",null,"","","2024/08/08",64.7],[8,"GPT-4o (0513, detail-low)",null,"","","2024/05/15",64.2],[9,"InternVL3-38B",38.4,"Qwen2.5-32B","InternViT-6B-v2.5","2025/04/14",64.2],[10,"InternVL2.5-78B",78.0,"Qwen-2.5-72B","InternViT-6B-v2.5","2024/12/10",63.8],[11,"Qwen2.5-VL-72B",73.4,"Qwen2.5-72B","QwenViT","2025/02/02",63.2],[12,"InternVL2.5-38B-MPO",38.0,"Qwen-2.5-32B","InternViT-6B-v2.5","2024/12/28",63.2],[13,"InternVL2.5-26B-MPO",26.0,"InternLM2.5-20B","InternViT-6B-v2.5","2024/12/28",62.6],[14,"Qwen2-VL-72B",73.4,"Qwen2-72B","QwenViT","2024/10/28",60.5],[15,"Qwen-VL-Max-0809",72.0,"Qwen2-72B","QwenViT","2024/09/12",60.1],[16,"Ovis2-34B",34.9,"Qwen2.5-32B","AIMv2-1B","2025/02/18",60.1],[17,"InternVL3-14B",15.1,"Qwen2.5-14B","InternViT-300M-v2.5","2025/04/14",59.9],[18,"GLM-4v-Plus-20250111",null,"","","2025/01/25",59.5],[19,"Gemini-1.5-Pro",null,"","","2024/06/10",59.1],[20,"GPT-4.1-mini-20250414",null,"","","2025/04/16",59.0],[21,"Ovis2-16B",16.2,"Qwen2.5-14B","AIMv2 Huge","2025/02/18",59.0],[22,"Phi-3.5-Vision",4.0,"Phi-3.5","CLIP ViT-L/14","2024/08/28",58.3],[23,"GPT-4v (0409, detail-high)",null,"","","2024/05/15",58.3],[24,"Gemini-1.5-Flash",null,"","","2024/09/16",57.7],[25,"InternVL2-Llama3-76B",76.0,"Llama-3-70B-Instruct","InternViT-6B","2024/07/19",57.5],[26,"InternVL2-26B",26.0,"InternLM2-20B","InternViT-6B","2024/07/11",56.9],[27,"Yi-Vision",null,"","","2024/08/03",56.7],[28,"Claude3.7-Sonnet",null,"","","2025/02/27",56.6],[29,"InternVL2.5-8B-MPO",8.0,"InternLM2.5-7B","InternViT-300M-v2.5","2024/12/28",56.6],[30,"Kimi-VL-A3B-Instruct",16.4,"Moonlight-16B-A3B","MoonViT","2025/04/14",56.4],[31,"moonshot-v1-8k",null,"","","2025/03/03",55.8],[32,"InternVL3-8B",7.94,"Qwen2.5-7B","InternViT-300M-v2.5","2025/04/14",55.4],[33,"HunYuan-Standard-Vision",null,"","","2025/01/15",55.4],[34,"Qwen2.5-VL-7B",8.29,"Qwen2.5-7B","QwenViT","2025/02/02",55.3],[35,"MiniCPM-V-2.6",8.0,"Qwen2-7B","SigLIP-400M","2024/08/08",55.2],[36,"Ovis2-8B",8.94,"Qwen2.5-7B","AIMv2 Huge","2025/02/18",54.3],[37,"MiniCPM-o-2.6",8.67,"Qwen2.5-7B","SigLIP-400M","2025/01/21",53.9],[38,"abab7-preview",null,"","","2024/12/11",53.8],[39,"Qwen2-VL-7B",8.0,"Qwen2-7B","QwenViT","2024/09/12",53.8],[40,"grok-2-vision-1212",null,"","","2025/03/03",53.7],[41,"GPT-4o-mini (0718, detail-high)",null,"","","2024/07/20",53.6],[42,"Gemma3-27B",27.4,"Gemma3-27B","SigLIP-400M","2025/03/19",53.5],[43,"InternVL3-2B",2.09,"Qwen2.5-1.5B","InternViT-300M-v2.5","2025/04/14",53.1],[44,"Ovis2-4B",4.62,"Qwen2.5-3B","AIMv2 Huge","2025/02/18",53.0],[45,"LLaVA-OneVision-7B",8.0,"Qwen2-7B","SigLIP-400M","2024/09/16",53.0],[46,"Aria",25.3,"Aria-MoE","SigLIP-400M","2024/12/05",52.9],[47,"Qwen-VL-Plus-0809",null,"","","2024/09/17",52.9],[48,"InternVL2-8B-MPO-CoT",8.0,"InternLM2.5-7B","InternViT-300M","2024/11/25",51.9],[49,"Step-1.5V-mini",null,"","","2024/12/11",51.8],[50,"LLaVA-Next-Interleave-7B",8.0,"Qwen-1.5-7B","SigLIP-400M","2024/08/08",51.3],[51,"InternVL2-8B",8.0,"InternLM2.5-7B","InternViT-300M","2024/07/11",50.9],[52,"InternVL2.5-4B-MPO",4.0,"Qwen-2.5-3B","InternViT-300M-v2.5","2024/12/28",50.6],[53,"InternVL2-8B-MPO",8.0,"InternLM2.5-7B","InternViT-300M","2024/11/25",50.4],[54,"Pixtral-12B",13.0,"Nemo-12B","ViT-400M","2024/09/16",50.4],[55,"Gemma3-12B",12.2,"Gemma3-12B","SigLIP-400M","2025/03/19",50.3],[56,"VARCO-VISION-14B",15.2,"Qwen2.5-14B","SigLIP-400M","2025/01/02",50.3],[57,"Idefics3-8B-Llama3",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/08/27",50.3],[58,"Mantis-8B-Idefics2",8.0,"Mistral-7B","SigLIP-400M","2024/08/08",50.1],[59,"Molmo-7B-D",8.0,"Qwen2-7B","CLIP ViT-L/14","2024/10/12",49.7],[60,"LLaVA-Next-Interleave-7B-DPO",8.0,"Qwen-1.5-7B","SigLIP-400M","2024/07/29",49.5],[61,"Qwen2.5-VL-3B",3.75,"Qwen2.5-3B","QwenViT","2025/02/02",49.1],[62,"InternLM-XComposer2-4KHD",7.0,"InternLM2-7B","CLIP ViT-L/14","2024/06/09",48.9],[63,"MUG-U-7B",7.0,"","","2025/03/19",48.6],[64,"Ovis1.6-Gemma2-9B",10.2,"Gemma2-9B-It","SigLIP-400M","2024/09/19",48.5],[65,"VILA1.5-13B",13.0,"Vicuna-v1.5-13B","SigLIP-400M","2024/08/25",48.1],[66,"Ovis1.6-Gemma2-27B",28.9,"Gemma2-27B","SigLIP-400M","2024/11/29",48.0],[67,"NVLM-D-72B",79.4,"Qwen2-72B","InternViT-6B","2024/10/19",48.0],[68,"Llama-3.2-90B-Vision-Instruct",88.6,"Llama-3.1-70B","","2024/10/19",48.0],[69,"Ovis2-2B",2.46,"Qwen2.5-1.5B","AIMv2 Large","2025/02/18",47.9],[70,"InternLM-XComposer2",7.0,"InternLM2-7B","CLIP ViT-L/14","2024/01/26",47.5],[71,"Mantis-8B-siglip-llama3",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/08/08",47.1],[72,"Mantis-8B-clip-llama3",8.0,"Llama-3-8B-Instruct","CLIP ViT-L/14","2024/08/08",47.1],[73,"RBDash-v1.5",79.0,"Qwen2-72B","CLIP ViT-L/14
InternViT-6B","2024/11/17",47.0],[74,"InternVL-Chat-V1.5",26.0,"InternLM2-20B","InternViT-6B","2024/04/17",46.6],[75,"SAIL-VL-2B",2.1,"Qwen2.5-1.5B","InternViT-300M","2024/12/25",46.4],[76,"H2OVL-2B",2.2,"H2O-DANUBE2-1.8B","InternViT-300M","2024/10/31",46.4],[77,"granite-vision-3.2-2b",2.98,"granite-3.1-2b-instruct","SigLip","2025/06/20",46.2],[78,"MMAlaya2",26.0,"InternLM2-20B","InternViT-6B","2024/08/27",46.1],[79,"360VL-70B",70.0,"Llama-3-70B-Instruct","CLIP ViT-L/14","2024/05/25",46.1],[80,"LLaVA-OneVision-7B (SI)",8.0,"Qwen2-7B","SigLIP-400M","2024/09/17",46.1],[81,"Molmo-7B-O",8.0,"Qwen2-7B","CLIP ViT-L/14","2024/10/20",45.8],[82,"XGen-MM-Instruct-Interleave-v1.5",4.4,"Phi-3","SigLIP-400M","2024/09/06",45.8],[83,"InternVL2-4B",4.0,"Phi-3","InternViT-300M","2024/07/11",45.8],[84,"IDEFICS2-8B",8.0,"Mistral-7B","SigLIP-400M","2024/04/26",45.6],[85,"Ross-Qwen2-7B",8.2,"Qwen2-7B","CLIP ViT-L/14","2025/01/17",45.3],[86,"GPT-4.1-nano-20250414",null,"","","2025/04/16",45.2],[87,"Llama-3-MixSense-v1.1",8.0,"Llama-3-8B-Instruct","Florence-2-Large-FT","2024/08/21",45.2],[88,"Qwen2-VL-2B",2.0,"Qwen2-1.5B","QwenViT","2024/09/12",45.2],[89,"BailingMM-Lite-1203",21.0,"Bailing-20B","SigLIP-400M","2024/12/08",45.1],[90,"VITA-1.5",8.3,"Qwen2-7B","InternViT-300M","2025/01/01",45.0],[91,"POINTS-Yi-1.5-9B",9.5,"Yi-1.5-9B","CLIP ViT-L/14","2024/10/11",45.0],[92,"Cambrian-8B",8.0,"Vicuna-v1.5-7B","CLIP ViT-L/14","2024/07/11",44.9],[93,"OmChat-v2.0-13B",13.0,"Qwen2-7B","InternViT-6B","2024/08/22",44.7],[94,"POINTS1.5-Qwen2.5-7B",8.3,"Qwen-2.5-7B","NaViT","2024/12/06",44.0],[95,"Ovis2-1B",1.27,"Qwen2.5-0.5B","AIMv2 Large","2025/02/18",44.0],[96,"XGen-MM-Instruct-DPO-v1.5",4.4,"Phi-3","SigLIP-400M","2024/09/06",43.9],[97,"Gemma3-4B",4.3,"Gemma3-4B","SigLIP-400M","2025/03/19",43.9],[98,"POINTS-Qwen2.5-7B",8.3,"Qwen-2.5-7B","CLIP ViT-L/14","2024/10/19",43.9],[99,"Ovis1.6-Llama3.2-3B",4.1,"Llama-3.2-3B","SigLIP-400M","2024/10/24",43.8],[100,"InternVL2.5-2B-MPO",2.0,"InternLM2.5-1.8B","InternViT-300M-v2.5","2024/12/28",43.8],[101,"SmolVLM-Instruct-DPO",2.3,"SmolLM2-1.7B","SigLIP-400M","2025/01/27",43.6],[102,"Qwen-VL-Max",null,"QwenLM","","2024/02/02",43.6],[103,"Vintern-3B-beta",3.7,"Qwen-2.5-3B","InternViT-300M","2024/10/24",43.5],[104,"MiniMonkey",2.2,"InternLM2-1.8B","InternViT-300M","2024/09/26",43.5],[105,"LLaVA-LLaMA-3-8B",8.0,"Llama-3-8B-Instruct","CLIP ViT-L/14","2024/05/07",43.5],[106,"Ovis1.5-Gemma2-9B",11.4,"Gemma2-9B-It","SigLIP-400M","2024/08/04",43.3],[107,"Phi-3-Vision",4.2,"Phi-3","CLIP ViT-L/14","2024/05/31",43.3],[108,"Cambrian-13B",13.0,"Vicuna-v1.5-13B","CLIP ViT-L/14","2024/07/29",43.1],[109,"InternVL3-1B",0.94,"Qwen2.5-0.5B","InternViT-300M-v2.5","2025/04/14",43.0],[110,"SmolVLM-Instruct",2.3,"SmolLM2-1.7B","SigLIP-400M","2025/01/27",42.8],[111,"InternVL2-2B",2.0,"InternLM2-1.8B","InternViT-300M","2024/07/11",42.8],[112,"TransCore-M",13.4,"PCITransGPT-13B","CLIP ViT-L/14","2024/04/16",42.7],[113,"XinYuan-VL-2B-Instruct",2.0,"Qwen2-1.5B","QwenViT","2024/09/27",42.7],[114,"Emu3_chat",8.49,"","","2025/01/26",42.7],[115,"SmolVLM2",2.25,"SmolLM2-1.7M","SigLIP-400M","2025/03/13",42.3],[116,"Phi-4-MultiModal",5.57,"Phi-4-Mini","SigLIP-400M","2025/03/13",42.1],[117,"LLaVA-Next-Qwen-32B",33.0,"Qwen-1.5-32B","SigLIP-400M","2024/08/08",42.1],[118,"Falcon2-VLM-11B",11.4,"Falcon2-11B","CLIP ViT-L/14","2024/10/30",42.1],[119,"LLaVA-v1.5-7B (QLoRA)",7.2,"Vicuna-v1.5-7B","CLIP ViT-L/14","2023/12/28",41.8],[120,"LLaVA-Next-Mistral-7B",7.6,"Mistral-7B","CLIP ViT-L/14","2024/03/25",41.7],[121,"granite-vision-3.3-2b",2.98,"granite-3.1-2b-instruct","SigLIP2-400M","2025/06/20",41.6],[122,"Bunny-Llama3-8B",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/07/18",41.6],[123,"LLaVA-Next-Vicuna-7B",7.1,"Vicuna-v1.5-7B","CLIP ViT-L/14","2024/03/25",41.6],[124,"ShareGPT4V-13B",13.4,"Vicuna-v1.5-13B","CLIP ViT-L/14","2023/12/08",41.6],[125,"InternLM-XComposer2-1.8B",2.0,"InternLM2-1.8B","CLIP ViT-L/14","2024/06/09",41.5],[126,"LLaVA-v1.5-13B (QLoRA)",13.4,"Vicuna-v1.5-13B","CLIP ViT-L/14","2023/12/28",41.3],[127,"Monkey-Chat",9.8,"Qwen-7B","ViT-BigHuge","2024/01/16",41.2],[128,"MiniCPM-V-2",2.8,"MiniCPM-2.4B","SigLIP-400M","2024/04/15",41.2],[129,"LLaVA-Next-Vicuna-13B",13.4,"Vicuna-v1.5-13B","CLIP ViT-L/14","2024/03/25",41.2],[130,"LLaVA-InternLM-7B (QLoRA)",7.6,"InternLM-7B","CLIP ViT-L/14","2023/12/28",41.1],[131,"RekaEdge",null,"","","2024/05/31",41.1],[132,"InternVL2.5-1B-MPO",1.0,"Qwen-2.5-0.5B","InternViT-300M-v2.5","2024/12/28",41.0],[133,"ShareGPT4V-7B",7.2,"Vicuna-v1.5-7B","CLIP ViT-L/14","2023/12/08",40.9],[134,"DeepSeek-VL-7B",7.3,"DeekSeek-7B","SAM-B
SigLIP-L","2024/03/21",40.9],[135,"LLaVA-v1.5-13B",13.4,"Vicuna-v1.5-13B","CLIP ViT-L/14","2023/10/05",40.9],[136,"Slime-13B",13.0,"Vicuna-v1.5-13B","CLIP ViT-L/14","2024/09/14",40.8],[137,"PaliGemma-3B-mix-448",3.0,"Gemma-2B","SigLIP-400M","2024/05/17",40.7],[138,"MolmoE-1B",7.2,"OLMoE-1B-7B-0924","CLIP ViT-L/14","2024/10/21",40.7],[139,"SmolVLM2-500M",0.51,"SmolLM2-360M","ViT-93M","2025/03/13",40.7],[140,"LLaVA-Next-Llama3",8.0,"Llama-3-8B-Instruct","CLIP ViT-L/14","2024/07/29",40.7],[141,"MiniCPM-V",3.0,"MiniCPM-2.4B","SigLIP-400M","2024/02/07",40.6],[142,"BailingMM-Pro-0120",81.0,"Bailing-80B","SigLIP-400M","2025/01/25",40.5],[143,"Moondream1",1.9,"SigLIP-400M","Phi-1.5","2024/09/26",40.3],[144,"H2OVL-800M",0.83,"H2O-DANUBE3-500M","InternViT-300M","2024/10/31",40.2],[145,"Janus-1.3B",2.1,"DeepSeek-1B","SigLIP-400M","2024/10/24",40.2],[146,"LLaVA-OneVision-0.5B",1.0,"Qwen2-0.5B","SigLIP-400M","2024/09/16",40.1],[147,"Parrot-7B",8.0,"Qwen2-7B","CLIP ViT-L/14","2024/08/22",39.9],[148,"SmolVLM2-256M",0.26,"SmolLM2-135M","ViT-93M","2025/03/13",39.8],[149,"Llama-3.2-11B-Vision-Instruct",11.0,"Llama-3.1-8B","","2024/10/07",39.8],[150,"SmolVLM-500M",0.51,"SmolLM2-360M","ViT-93M","2025/01/27",39.8],[151,"Ovis1.5-Llama3-8B",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/07/29",39.8],[152,"LLaVA-v1.5-7B",7.2,"Vicuna-v1.5-7B","CLIP ViT-L/14","2023/10/05",39.7],[153,"AKI-4B",4.33,"Phi-3.5","SigLIP-400M","2025/03/25",39.7],[154,"VILA1.5-3B",3.0,"Sheared-LLaMA-2.7B","SigLIP-400M","2024/08/25",39.7],[155,"DeepSeek-VL-1.3B",2.0,"DeekSeek-1B","SAM-B
SigLIP-L","2024/03/21",39.7],[156,"Llama-3-VILA1.5-8B",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/08/25",39.5],[157,"Claude3-Sonnet",null,"","","2024/03/28",39.3],[158,"SmolVLM-256M",0.26,"SmolLM2-135M","ViT-93M","2025/01/27",39.1],[159,"Slime-8B",8.0,"Llama-3-8B-Instruct","CLIP ViT-L/14","2024/09/14",38.8],[160,"Janus-Pro-7B",7.42,"DeepSeek-7B","SigLIP-400M","2025/02/02",38.7],[161,"Slime-7B",7.0,"Vicuna-v1.5-7B","CLIP ViT-L/14","2024/09/14",38.7],[162,"SmolVLM-Synthetic",2.3,"SmolLM2-1.7B","SigLIP-400M","2025/01/27",38.5],[163,"LLaVA-OneVision-0.5B (SI)",1.0,"Qwen2-0.5B","SigLIP-400M","2024/09/17",38.5],[164,"InternVL2-1B",1.0,"Qwen2-0.5B","InternViT-300M","2024/07/11",38.3],[165,"IDEFICS-9B-Instruct",9.0,"Llama-7B","CLIP ViT-H/14","2023/07/25",38.3],[166,"Mantis-8B-Fuyu",8.0,"Fuyu-8B","","2024/09/07",38.2],[167,"Monkey",9.8,"Qwen-7B","ViT-BigHuge","2024/01/11",37.7],[168,"Claude3-Haiku",null,"","","2024/03/28",37.5],[169,"Kosmos2",1.7,"","","2024/10/19",34.4],[170,"Aquila-VL-2B",2.2,"Qwen-2.5-1.5B","SigLIP-400M","2024/10/24",34.1],[171,"RekaFlash",null,"","","2024/05/07",31.9],[172,"Eagle-X5-34B-Chat",36.8,"Yi-34B","Clip-448
ConvNeXT-1024
SAM-1024
DET-1024
Pix2Struct-1024","2024/11/29",30.4],[173,"Claude3.5-Sonnet",null,"","","2024/06/24",28.2],[174,"Qwen-VL-Chat",9.6,"Qwen-7B","ViT-G/16","2023/08/24",28.2],[175,"Qwen-VL",9.6,"Qwen-7B","ViT-G/16","2023/08/24",27.9],[176,"Eagle-X5-7B",9.0,"Vicuna-v1.5-7B","Clip-448
ConvNeXT-1024
SAM-1024
DET-1024
Pix2Struct-1024","2024/09/26",22.4],[177,"BlueLM-V-3B",3.0,"BlueLM-3B","SigLIP-400M","2024/10/30",22.1],[178,"Eagle-X5-13B",15.0,"Vicuna-v1.5-13B","Clip-448
ConvNeXT-1024
SAM-1024
DET-1024
Pix2Struct-1024","2024/09/26",21.8],[179,"Chameleon-30B",30.0,"","","2024/07/29",21.3],[180,"InternLM-XComposer",8.0,"InternLM-7B","EVA-G","2023/09/26",17.8],[181,"Chameleon-7B",7.0,"","","2024/07/29",16.6],[182,"abab6.5s",null,"","","2024/12/11",14.1]],"metadata":null},"headers":["1","2","3"],"row_count":[1,"dynamic"],"col_count":[3,"dynamic"],"datatype":["number","html","number","html","html","str","number"],"type":"pandas","latex_delimiters":[{"left":"$$","right":"$$","display":true}],"show_label":true,"height":500,"min_width":160,"interactive":false,"visible":true,"elem_classes":[],"wrap":true,"line_breaks":true,"column_widths":[],"name":"dataframe","_selectable":false},"skip_api":false,"component_class_id":"6a51bb3357f2e94c40fb8d4fbe06aa8e","key":null,"api_info":{"properties":{"headers":{"items":{"type":"string"},"title":"Headers","type":"array"},"data":{"items":{"items":{},"type":"array"},"title":"Data","type":"array"},"metadata":{"anyOf":[{"additionalProperties":{"anyOf":[{"items":{},"type":"array"},{"type":"null"}]},"type":"object"},{"type":"null"}],"default":null,"title":"Metadata"}},"required":["headers","data"],"title":"DataframeData","type":"object"},"example_inputs":{"headers":["a","b"],"data":[["foo","bar"]]}},{"id":332,"type":"textbox","props":{"value":"BLINK","lines":1,"max_lines":20,"label":"BLINK","show_label":true,"container":true,"min_width":160,"visible":false,"autofocus":false,"autoscroll":true,"elem_classes":[],"type":"text","rtl":false,"show_copy_button":false,"name":"textbox","_selectable":false},"skip_api":false,"component_class_id":"d0491bb0fbd427bdb2a4549c4d1ac869","key":null,"api_info":{"type":"string"},"example_inputs":"Hello!!"},{"id":333,"type":"form","props":{"scale":0,"min_width":0,"name":"form"},"skip_api":true,"component_class_id":"43cda85c6ff7a5dd8f83d29496b014ee","key":null},{"id":334,"type":"form","props":{"scale":0,"min_width":0,"name":"form"},"skip_api":true,"component_class_id":"43cda85c6ff7a5dd8f83d29496b014ee","key":null},{"id":335,"type":"tabitem","props":{"label":"📊 QBench Leaderboard","visible":true,"interactive":true,"id":29,"elem_id":"QBench","name":"tab"},"skip_api":true,"component_class_id":"18f46968e2b273dc5dbda0fe78433d7e","key":null},{"id":336,"type":"checkboxgroup","props":{"choices":[["Overall","Overall"],["type_0_concern_0","type_0_concern_0"],["type_0_concern_1","type_0_concern_1"],["type_0_concern_2","type_0_concern_2"],["type_0_concern_3","type_0_concern_3"],["type_1_concern_0","type_1_concern_0"],["type_1_concern_1","type_1_concern_1"],["type_1_concern_2","type_1_concern_2"],["type_1_concern_3","type_1_concern_3"],["type_2_concern_0","type_2_concern_0"],["type_2_concern_1","type_2_concern_1"],["type_2_concern_2","type_2_concern_2"],["type_2_concern_3","type_2_concern_3"]],"value":["Overall"],"type":"value","label":"QBench CheckBoxes","show_label":true,"container":true,"min_width":160,"interactive":true,"visible":true,"elem_classes":[],"name":"checkboxgroup","_selectable":false},"skip_api":false,"component_class_id":"0635a5d3bf87369f1c2c1c69f8a3d0cc","key":null,"api_info":{"items":{"enum":["Overall","type_0_concern_0","type_0_concern_1","type_0_concern_2","type_0_concern_3","type_1_concern_0","type_1_concern_1","type_1_concern_2","type_1_concern_3","type_2_concern_0","type_2_concern_1","type_2_concern_2","type_2_concern_3"],"type":"string"},"title":"Checkbox Group","type":"array"},"example_inputs":["Overall"]},{"id":337,"type":"row","props":{"variant":"default","visible":true,"equal_height":true,"show_progress":false,"name":"row"},"skip_api":true,"component_class_id":"b5cf3d15e2293fb5ccc071d7b8d69f64","key":null},{"id":338,"type":"textbox","props":{"value":"Input the Model Name (fuzzy, case insensitive)","lines":1,"max_lines":20,"label":"Model Name","show_label":true,"container":true,"min_width":160,"interactive":true,"visible":true,"autofocus":false,"autoscroll":true,"elem_classes":[],"type":"text","rtl":false,"show_copy_button":false,"name":"textbox","_selectable":false},"skip_api":false,"component_class_id":"d0491bb0fbd427bdb2a4549c4d1ac869","key":null,"api_info":{"type":"string"},"example_inputs":"Hello!!"},{"id":339,"type":"checkboxgroup","props":{"choices":[["<4B","<4B"],["4B-10B","4B-10B"],["10B-20B","10B-20B"],["20B-40B","20B-40B"],[">40B",">40B"],["Unknown","Unknown"]],"value":["<4B","4B-10B","10B-20B","20B-40B",">40B","Unknown"],"type":"value","label":"Model Size","show_label":true,"container":true,"min_width":160,"interactive":true,"visible":true,"elem_classes":[],"name":"checkboxgroup","_selectable":false},"skip_api":false,"component_class_id":"0635a5d3bf87369f1c2c1c69f8a3d0cc","key":null,"api_info":{"items":{"enum":["<4B","4B-10B","10B-20B","20B-40B",">40B","Unknown"],"type":"string"},"title":"Checkbox Group","type":"array"},"example_inputs":["<4B"]},{"id":340,"type":"checkboxgroup","props":{"choices":[["API","API"],["OpenSource","OpenSource"]],"value":["API","OpenSource"],"type":"value","label":"Model Type","show_label":true,"container":true,"min_width":160,"interactive":true,"visible":true,"elem_classes":[],"name":"checkboxgroup","_selectable":false},"skip_api":false,"component_class_id":"0635a5d3bf87369f1c2c1c69f8a3d0cc","key":null,"api_info":{"items":{"enum":["API","OpenSource"],"type":"string"},"title":"Checkbox Group","type":"array"},"example_inputs":["API"]},{"id":341,"type":"form","props":{"scale":3,"min_width":480,"name":"form"},"skip_api":true,"component_class_id":"43cda85c6ff7a5dd8f83d29496b014ee","key":null},{"id":342,"type":"dataframe","props":{"value":{"headers":["Rank","Method","Param (B)","Language Model","Vision Model","Eval Date","Overall"],"data":[[1,"Step-1o",null,"","","2025/01/13",80.5],[2,"Qwen2-VL-72B",73.4,"Qwen2-72B","QwenViT","2024/10/28",80.3],[3,"GPT-4.1-mini-20250414",null,"","","2025/04/16",80.0],[4,"Qwen2.5-VL-72B",73.4,"Qwen2.5-72B","QwenViT","2025/02/02",80.0],[5,"Ovis2-34B",34.9,"Qwen2.5-32B","AIMv2-1B","2025/02/18",79.8],[6,"GPT-4.1-20250414",null,"","","2025/04/16",79.7],[7,"Ovis2-16B",16.2,"Qwen2.5-14B","AIMv2 Huge","2025/02/18",79.5],[8,"Qwen-VL-Max-0809",72.0,"Qwen2-72B","QwenViT","2024/09/12",79.4],[9,"LLaVA-OneVision-7B",8.0,"Qwen2-7B","SigLIP-400M","2024/09/16",78.9],[10,"Ovis2-8B",8.94,"Qwen2.5-7B","AIMv2 Huge","2025/02/18",78.9],[11,"GPT-4o (0513, detail-high)",null,"","","2024/05/31",78.9],[12,"InternVL3-78B",78.4,"Qwen2.5-72B","InternViT-6B-v2.5","2025/04/14",78.8],[13,"MiniCPM-o-2.6",8.67,"Qwen2.5-7B","SigLIP-400M","2025/01/21",78.7],[14,"GPT-4o (0806, detail-high)",null,"","","2024/08/08",78.6],[15,"RBDash-v1.5",79.0,"Qwen2-72B","CLIP ViT-L/14
InternViT-6B","2024/11/17",78.5],[16,"GPT-4o (0513, detail-low)",null,"","","2024/05/15",78.4],[17,"InternVL3-38B",38.4,"Qwen2.5-32B","InternViT-6B-v2.5","2025/04/14",78.3],[18,"BailingMM-Pro-0120",81.0,"Bailing-80B","SigLIP-400M","2025/01/25",78.2],[19,"Ovis2-4B",4.62,"Qwen2.5-3B","AIMv2 Huge","2025/02/18",78.1],[20,"Phi-4-MultiModal",5.57,"Phi-4-Mini","SigLIP-400M","2025/03/13",77.7],[21,"GLM-4v-Plus-20250111",null,"","","2025/01/25",77.7],[22,"Ovis1.6-Gemma2-27B",28.9,"Gemma2-27B","SigLIP-400M","2024/11/29",77.7],[23,"Qwen2.5-VL-7B",8.29,"Qwen2.5-7B","QwenViT","2025/02/02",77.7],[24,"InternVL2.5-78B-MPO",78.0,"Qwen-2.5-72B","InternViT-6B-v2.5","2024/12/29",77.5],[25,"moonshot-v1-8k",null,"","","2025/03/03",77.5],[26,"BlueLM-V-3B",3.0,"BlueLM-3B","SigLIP-400M","2024/10/30",77.3],[27,"POINTS-Qwen2.5-7B",8.3,"Qwen-2.5-7B","CLIP ViT-L/14","2024/10/19",77.2],[28,"abab7-preview",null,"","","2024/12/11",77.0],[29,"Kimi-VL-A3B-Instruct",16.4,"Moonlight-16B-A3B","MoonViT","2025/04/14",76.9],[30,"MUG-U-7B",7.0,"","","2025/03/19",76.9],[31,"Qwen2-VL-7B",8.0,"Qwen2-7B","QwenViT","2024/09/12",76.9],[32,"Qwen-VL-Plus-0809",null,"","","2024/09/17",76.8],[33,"Taiyi",null,"","","2024/12/11",76.8],[34,"InternVL3-14B",15.1,"Qwen2.5-14B","InternViT-300M-v2.5","2025/04/14",76.7],[35,"Ovis1.6-Gemma2-9B",10.2,"Gemma2-9B-It","SigLIP-400M","2024/09/19",76.7],[36,"Ovis1.5-Gemma2-9B",11.4,"Gemma2-9B-It","SigLIP-400M","2024/08/04",76.7],[37,"MiniCPM-V-2.6",8.0,"Qwen2-7B","SigLIP-400M","2024/08/08",76.5],[38,"InternVL2-Llama3-76B",76.0,"Llama-3-70B-Instruct","InternViT-6B","2024/07/19",76.4],[39,"Mantis-8B-Idefics2",8.0,"Mistral-7B","SigLIP-400M","2024/08/08",76.3],[40,"Ovis2-2B",2.46,"Qwen2.5-1.5B","AIMv2 Large","2025/02/18",76.2],[41,"InternVL2.5-38B-MPO",38.0,"Qwen-2.5-32B","InternViT-6B-v2.5","2024/12/28",76.1],[42,"LLaVA-Next-Interleave-7B-DPO",8.0,"Qwen-1.5-7B","SigLIP-400M","2024/07/29",76.1],[43,"POINTS-Yi-1.5-9B",9.5,"Yi-1.5-9B","CLIP ViT-L/14","2024/10/11",76.0],[44,"InternVL2.5-26B-MPO",26.0,"InternLM2.5-20B","InternViT-6B-v2.5","2024/12/28",76.0],[45,"Ovis1.5-Llama3-8B",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/07/29",76.0],[46,"InternVL3-8B",7.94,"Qwen2.5-7B","InternViT-300M-v2.5","2025/04/14",75.9],[47,"Ovis1.6-Llama3.2-3B",4.1,"Llama-3.2-3B","SigLIP-400M","2024/10/24",75.8],[48,"GPT-4v (0409, detail-high)",null,"","","2024/05/15",75.7],[49,"InternVL2-40B",40.0,"Nous-Hermes-2-Yi-34B","InternViT-6B","2024/07/11",75.5],[50,"Aria",25.3,"Aria-MoE","SigLIP-400M","2024/12/05",75.3],[51,"HunYuan-Standard-Vision",null,"","","2025/01/15",75.2],[52,"POINTS1.5-Qwen2.5-7B",8.3,"Qwen-2.5-7B","NaViT","2024/12/06",75.2],[53,"Qwen2.5-VL-3B",3.75,"Qwen2.5-3B","QwenViT","2025/02/02",74.9],[54,"GPT-4.1-nano-20250414",null,"","","2025/04/16",74.8],[55,"VARCO-VISION-14B",15.2,"Qwen2.5-14B","SigLIP-400M","2025/01/02",74.7],[56,"Gemini-1.5-Pro",null,"","","2024/06/10",74.7],[57,"LLaVA-OneVision-7B (SI)",8.0,"Qwen2-7B","SigLIP-400M","2024/09/17",74.7],[58,"Aquila-VL-2B",2.2,"Qwen-2.5-1.5B","SigLIP-400M","2024/10/24",74.2],[59,"Step-1.5V-mini",null,"","","2024/12/11",74.0],[60,"Molmo-7B-D",8.0,"Qwen2-7B","CLIP ViT-L/14","2024/10/12",74.0],[61,"granite-vision-3.2-2b",2.98,"granite-3.1-2b-instruct","SigLip","2025/06/20",74.0],[62,"Qwen2-VL-2B",2.0,"Qwen2-1.5B","QwenViT","2024/09/12",73.9],[63,"InternVL2.5-8B-MPO",8.0,"InternLM2.5-7B","InternViT-300M-v2.5","2024/12/28",73.8],[64,"Gemini-1.5-Flash",null,"","","2024/09/16",73.7],[65,"Pixtral-12B",13.0,"Nemo-12B","ViT-400M","2024/09/16",73.4],[66,"H2OVL-2B",2.2,"H2O-DANUBE2-1.8B","InternViT-300M","2024/10/31",73.4],[67,"GLM-4v-9B",9.0,"GLM-4-9B","EVA-02-5B","2024/06/14",73.3],[68,"Gemma3-12B",12.2,"Gemma3-12B","SigLIP-400M","2025/03/19",73.3],[69,"InternVL2-26B",26.0,"InternLM2-20B","InternViT-6B","2024/07/11",73.2],[70,"LLaVA-Next-Interleave-7B",8.0,"Qwen-1.5-7B","SigLIP-400M","2024/08/08",73.1],[71,"granite-vision-3.3-2b",2.98,"granite-3.1-2b-instruct","SigLIP2-400M","2025/06/20",73.0],[72,"MMAlaya2",26.0,"InternLM2-20B","InternViT-6B","2024/08/27",72.8],[73,"SAIL-VL-2B",2.1,"Qwen2.5-1.5B","InternViT-300M","2024/12/25",72.8],[74,"InternVL-Chat-V1.5",26.0,"InternLM2-20B","InternViT-6B","2024/04/17",72.5],[75,"Cambrian-34B",34.0,"Nous-Hermes-2-Yi-34B","CLIP ViT-L/14","2024/07/18",72.4],[76,"BailingMM-Lite-1203",21.0,"Bailing-20B","SigLIP-400M","2024/12/08",72.4],[77,"WeMM",7.0,"InternLM2-7B","SigLIP-400M","2024/06/09",72.3],[78,"grok-2-vision-1212",null,"","","2025/03/03",72.1],[79,"Gemma3-27B",27.4,"Gemma3-27B","SigLIP-400M","2025/03/19",72.0],[80,"MiniCPM-Llama3-V2.5",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/05/27",71.8],[81,"NVLM-D-72B",79.4,"Qwen2-72B","InternViT-6B","2024/10/19",71.6],[82,"InternVL2.5-4B-MPO",4.0,"Qwen-2.5-3B","InternViT-300M-v2.5","2024/12/28",71.5],[83,"InternVL3-2B",2.09,"Qwen2.5-1.5B","InternViT-300M-v2.5","2025/04/14",71.5],[84,"Ovis2-1B",1.27,"Qwen2.5-0.5B","AIMv2 Large","2025/02/18",71.3],[85,"InternLM-XComposer2",7.0,"InternLM2-7B","CLIP ViT-L/14","2024/01/26",71.2],[86,"VITA-1.5",8.3,"Qwen2-7B","InternViT-300M","2025/01/01",71.0],[87,"SmolVLM2",2.25,"SmolLM2-1.7M","SigLIP-400M","2025/03/13",71.0],[88,"XinYuan-VL-2B-Instruct",2.0,"Qwen2-1.5B","QwenViT","2024/09/27",71.0],[89,"Mantis-8B-siglip-llama3",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/08/08",70.9],[90,"Ross-Qwen2-7B",8.2,"Qwen2-7B","CLIP ViT-L/14","2025/01/17",70.7],[91,"Bunny-Llama3-8B",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/07/18",70.7],[92,"Cambrian-8B",8.0,"Vicuna-v1.5-7B","CLIP ViT-L/14","2024/07/11",70.6],[93,"InternVL2-8B-MPO",8.0,"InternLM2.5-7B","InternViT-300M","2024/11/25",70.4],[94,"Cambrian-13B",13.0,"Vicuna-v1.5-13B","CLIP ViT-L/14","2024/07/29",69.8],[95,"InternVL2-8B",8.0,"InternLM2.5-7B","InternViT-300M","2024/07/11",69.8],[96,"InternVL2.5-2B-MPO",2.0,"InternLM2.5-1.8B","InternViT-300M-v2.5","2024/12/28",69.8],[97,"InternVL2-8B-MPO-CoT",8.0,"InternLM2.5-7B","InternViT-300M","2024/11/25",69.7],[98,"Mantis-8B-clip-llama3",8.0,"Llama-3-8B-Instruct","CLIP ViT-L/14","2024/08/08",69.6],[99,"Yi-VL-34B",34.6,"Yi-34B","CLIP ViT-H/14","2024/01/25",69.0],[100,"IDEFICS2-8B",8.0,"Mistral-7B","SigLIP-400M","2024/04/26",68.7],[101,"Eagle-X5-34B-Chat",36.8,"Yi-34B","Clip-448
ConvNeXT-1024
SAM-1024
DET-1024
Pix2Struct-1024","2024/11/29",68.4],[102,"CogVLM2-19B-Chat",19.0,"Llama-3-8B-Instruct","EVA2-CLIP-E","2024/05/31",68.4],[103,"Mini-InternVL-Chat-4B-V1.5",4.0,"Phi-3","InternViT-300M","2024/06/10",68.3],[104,"Llama-3.2-11B-Vision-Instruct",11.0,"Llama-3.1-8B","","2024/10/07",68.3],[105,"DeepSeek-VL-7B",7.3,"DeekSeek-7B","SAM-B
SigLIP-L","2024/03/21",68.1],[106,"Molmo-7B-O",8.0,"Qwen2-7B","CLIP ViT-L/14","2024/10/20",68.0],[107,"Phi-3-Vision",4.2,"Phi-3","CLIP ViT-L/14","2024/05/31",67.7],[108,"Eagle-X5-7B",9.0,"Vicuna-v1.5-7B","Clip-448
ConvNeXT-1024
SAM-1024
DET-1024
Pix2Struct-1024","2024/09/26",67.7],[109,"360VL-70B",70.0,"Llama-3-70B-Instruct","CLIP ViT-L/14","2024/05/25",67.6],[110,"InternVL2-4B",4.0,"Phi-3","InternViT-300M","2024/07/11",67.5],[111,"Janus-Pro-7B",7.42,"DeepSeek-7B","SigLIP-400M","2025/02/02",67.4],[112,"Eagle-X5-13B",15.0,"Vicuna-v1.5-13B","Clip-448
ConvNeXT-1024
SAM-1024
DET-1024
Pix2Struct-1024","2024/09/26",67.4],[113,"Slime-8B",8.0,"Llama-3-8B-Instruct","CLIP ViT-L/14","2024/09/14",67.2],[114,"Mantis-8B-Fuyu",8.0,"Fuyu-8B","","2024/09/07",67.0],[115,"MiniCPM-V-2",2.8,"MiniCPM-2.4B","SigLIP-400M","2024/04/15",67.0],[116,"Emu3_chat",8.49,"","","2025/01/26",66.4],[117,"Yi-VL-6B",6.6,"Yi-6B","CLIP ViT-H/14","2024/01/25",66.3],[118,"LLaVA-Next-Llama3",8.0,"Llama-3-8B-Instruct","CLIP ViT-L/14","2024/07/29",66.2],[119,"Vintern-3B-beta",3.7,"Qwen-2.5-3B","InternViT-300M","2024/10/24",65.5],[120,"AKI-4B",4.33,"Phi-3.5","SigLIP-400M","2025/03/25",65.2],[121,"MiniMonkey",2.2,"InternLM2-1.8B","InternViT-300M","2024/09/26",65.2],[122,"Gemma3-4B",4.3,"Gemma3-4B","SigLIP-400M","2025/03/19",65.0],[123,"MolmoE-1B",7.2,"OLMoE-1B-7B-0924","CLIP ViT-L/14","2024/10/21",64.9],[124,"LLaVA-Next-Vicuna-13B",13.4,"Vicuna-v1.5-13B","CLIP ViT-L/14","2024/03/25",64.6],[125,"LLaVA-Next-Vicuna-7B",7.1,"Vicuna-v1.5-7B","CLIP ViT-L/14","2024/03/25",64.3],[126,"InternVL2-2B",2.0,"InternLM2-1.8B","InternViT-300M","2024/07/11",64.3],[127,"Falcon2-VLM-11B",11.4,"Falcon2-11B","CLIP ViT-L/14","2024/10/30",64.2],[128,"Slime-13B",13.0,"Vicuna-v1.5-13B","CLIP ViT-L/14","2024/09/14",64.1],[129,"InternLM-XComposer2-1.8B",2.0,"InternLM2-1.8B","CLIP ViT-L/14","2024/06/09",64.1],[130,"Mini-InternVL-Chat-2B-V1.5",2.0,"InternLM2-1.8B","InternViT-300M","2024/06/10",63.5],[131,"InternVL3-1B",0.94,"Qwen2.5-0.5B","InternViT-300M-v2.5","2025/04/14",63.5],[132,"Monkey-Chat",9.8,"Qwen-7B","ViT-BigHuge","2024/01/16",63.4],[133,"InternVL2.5-1B-MPO",1.0,"Qwen-2.5-0.5B","InternViT-300M-v2.5","2024/12/28",63.3],[134,"PaliGemma-3B-mix-448",3.0,"Gemma-2B","SigLIP-400M","2024/05/17",63.3],[135,"LLaVA-Next-Mistral-7B",7.6,"Mistral-7B","CLIP ViT-L/14","2024/03/25",63.2],[136,"CogVLM-17B-Chat",17.0,"Vicuna-v1.5-7B","EVA2-CLIP-E","2024/01/03",62.6],[137,"LLaVA-OneVision-0.5B",1.0,"Qwen2-0.5B","SigLIP-400M","2024/09/16",62.5],[138,"H2OVL-800M",0.83,"H2O-DANUBE3-500M","InternViT-300M","2024/10/31",62.1],[139,"TransCore-M",13.4,"PCITransGPT-13B","CLIP ViT-L/14","2024/04/16",62.0],[140,"LLaVA-v1.5-13B",13.4,"Vicuna-v1.5-13B","CLIP ViT-L/14","2023/10/05",60.9],[141,"Slime-7B",7.0,"Vicuna-v1.5-7B","CLIP ViT-L/14","2024/09/14",60.6],[142,"Qwen-VL-Chat",9.6,"Qwen-7B","ViT-G/16","2023/08/24",60.3],[143,"DeepSeek-VL-1.3B",2.0,"DeekSeek-1B","SAM-B
SigLIP-L","2024/03/21",59.6],[144,"SmolVLM-Instruct",2.3,"SmolLM2-1.7B","SigLIP-400M","2025/01/27",59.5],[145,"SmolVLM-Instruct-DPO",2.3,"SmolLM2-1.7B","SigLIP-400M","2025/01/27",58.9],[146,"Moondream1",1.9,"SigLIP-400M","Phi-1.5","2024/09/26",58.8],[147,"LLaVA-v1.5-7B",7.2,"Vicuna-v1.5-7B","CLIP ViT-L/14","2023/10/05",58.6],[148,"InternVL2-1B",1.0,"Qwen2-0.5B","InternViT-300M","2024/07/11",57.8],[149,"Monkey",9.8,"Qwen-7B","ViT-BigHuge","2024/01/11",56.6],[150,"SmolVLM2-500M",0.51,"SmolLM2-360M","ViT-93M","2025/03/13",56.5],[151,"Janus-1.3B",2.1,"DeepSeek-1B","SigLIP-400M","2024/10/24",54.0],[152,"LLaVA-OneVision-0.5B (SI)",1.0,"Qwen2-0.5B","SigLIP-400M","2024/09/17",53.4],[153,"abab6.5s",null,"","","2024/12/11",50.8],[154,"SmolVLM-500M",0.51,"SmolLM2-360M","ViT-93M","2025/01/27",49.8],[155,"SmolVLM-Synthetic",2.3,"SmolLM2-1.7B","SigLIP-400M","2025/01/27",47.5],[156,"Qwen-VL",9.6,"Qwen-7B","ViT-G/16","2023/08/24",46.0],[157,"SmolVLM2-256M",0.26,"SmolLM2-135M","ViT-93M","2025/03/13",42.4],[158,"SmolVLM-256M",0.26,"SmolLM2-135M","ViT-93M","2025/01/27",41.9],[159,"Claude3.7-Sonnet",null,"","","2025/02/27",40.5],[160,"Kosmos2",1.7,"","","2024/10/19",37.2]],"metadata":null},"headers":["1","2","3"],"row_count":[1,"dynamic"],"col_count":[3,"dynamic"],"datatype":["number","html","number","html","html","str","number"],"type":"pandas","latex_delimiters":[{"left":"$$","right":"$$","display":true}],"show_label":true,"height":500,"min_width":160,"interactive":false,"visible":true,"elem_classes":[],"wrap":true,"line_breaks":true,"column_widths":[],"name":"dataframe","_selectable":false},"skip_api":false,"component_class_id":"6a51bb3357f2e94c40fb8d4fbe06aa8e","key":null,"api_info":{"properties":{"headers":{"items":{"type":"string"},"title":"Headers","type":"array"},"data":{"items":{"items":{},"type":"array"},"title":"Data","type":"array"},"metadata":{"anyOf":[{"additionalProperties":{"anyOf":[{"items":{},"type":"array"},{"type":"null"}]},"type":"object"},{"type":"null"}],"default":null,"title":"Metadata"}},"required":["headers","data"],"title":"DataframeData","type":"object"},"example_inputs":{"headers":["a","b"],"data":[["foo","bar"]]}},{"id":343,"type":"textbox","props":{"value":"QBench","lines":1,"max_lines":20,"label":"QBench","show_label":true,"container":true,"min_width":160,"visible":false,"autofocus":false,"autoscroll":true,"elem_classes":[],"type":"text","rtl":false,"show_copy_button":false,"name":"textbox","_selectable":false},"skip_api":false,"component_class_id":"d0491bb0fbd427bdb2a4549c4d1ac869","key":null,"api_info":{"type":"string"},"example_inputs":"Hello!!"},{"id":344,"type":"form","props":{"scale":0,"min_width":0,"name":"form"},"skip_api":true,"component_class_id":"43cda85c6ff7a5dd8f83d29496b014ee","key":null},{"id":345,"type":"form","props":{"scale":0,"min_width":0,"name":"form"},"skip_api":true,"component_class_id":"43cda85c6ff7a5dd8f83d29496b014ee","key":null},{"id":346,"type":"tabitem","props":{"label":"📊 ABench Leaderboard","visible":true,"interactive":true,"id":30,"elem_id":"ABench","name":"tab"},"skip_api":true,"component_class_id":"18f46968e2b273dc5dbda0fe78433d7e","key":null},{"id":347,"type":"checkboxgroup","props":{"choices":[["Overall","Overall"],["part1 -> bag_of_words -> attribute","part1 -> bag_of_words -> attribute"],["part1 -> bag_of_words -> composition -> arrangement","part1 -> bag_of_words -> composition -> arrangement"],["part1 -> bag_of_words -> composition -> occlusion","part1 -> bag_of_words -> composition -> occlusion"],["part1 -> bag_of_words -> composition -> orientation","part1 -> bag_of_words -> composition -> orientation"],["part1 -> bag_of_words -> composition -> size","part1 -> bag_of_words -> composition -> size"],["part1 -> bag_of_words -> counting","part1 -> bag_of_words -> counting"],["part1 -> bag_of_words -> noun_as_adjective","part1 -> bag_of_words -> noun_as_adjective"],["part1 -> basic_recognition -> major","part1 -> basic_recognition -> major"],["part1 -> basic_recognition -> minor","part1 -> basic_recognition -> minor"],["part1 -> outside_knowledge -> contradiction overcome","part1 -> outside_knowledge -> contradiction overcome"],["part1 -> outside_knowledge -> specific-terms -> company","part1 -> outside_knowledge -> specific-terms -> company"],["part1 -> outside_knowledge -> specific-terms -> creature","part1 -> outside_knowledge -> specific-terms -> creature"],["part1 -> outside_knowledge -> specific-terms -> daily","part1 -> outside_knowledge -> specific-terms -> daily"],["part1 -> outside_knowledge -> specific-terms -> food","part1 -> outside_knowledge -> specific-terms -> food"],["part1 -> outside_knowledge -> specific-terms -> geography","part1 -> outside_knowledge -> specific-terms -> geography"],["part1 -> outside_knowledge -> specific-terms -> material","part1 -> outside_knowledge -> specific-terms -> material"],["part1 -> outside_knowledge -> specific-terms -> science","part1 -> outside_knowledge -> specific-terms -> science"],["part1 -> outside_knowledge -> specific-terms -> sports","part1 -> outside_knowledge -> specific-terms -> sports"],["part1 -> outside_knowledge -> specific-terms -> style -> abstract","part1 -> outside_knowledge -> specific-terms -> style -> abstract"],["part1 -> outside_knowledge -> specific-terms -> style -> art","part1 -> outside_knowledge -> specific-terms -> style -> art"],["part1 -> outside_knowledge -> specific-terms -> style -> art_deco","part1 -> outside_knowledge -> specific-terms -> style -> art_deco"],["part1 -> outside_knowledge -> specific-terms -> style -> cubism","part1 -> outside_knowledge -> specific-terms -> style -> cubism"],["part1 -> outside_knowledge -> specific-terms -> style -> dadaism","part1 -> outside_knowledge -> specific-terms -> style -> dadaism"],["part1 -> outside_knowledge -> specific-terms -> style -> deco","part1 -> outside_knowledge -> specific-terms -> style -> deco"],["part1 -> outside_knowledge -> specific-terms -> style -> expressionism","part1 -> outside_knowledge -> specific-terms -> style -> expressionism"],["part1 -> outside_knowledge -> specific-terms -> style -> fauvism","part1 -> outside_knowledge -> specific-terms -> style -> fauvism"],["part1 -> outside_knowledge -> specific-terms -> style -> futurism","part1 -> outside_knowledge -> specific-terms -> style -> futurism"],["part1 -> outside_knowledge -> specific-terms -> style -> minimalism","part1 -> outside_knowledge -> specific-terms -> style -> minimalism"],["part1 -> outside_knowledge -> specific-terms -> style -> pop","part1 -> outside_knowledge -> specific-terms -> style -> pop"],["part1 -> outside_knowledge -> specific-terms -> style -> psychedelic","part1 -> outside_knowledge -> specific-terms -> style -> psychedelic"],["part1 -> outside_knowledge -> specific-terms -> style -> steampunk","part1 -> outside_knowledge -> specific-terms -> style -> steampunk"],["part1 -> outside_knowledge -> specific-terms -> style -> surrealism","part1 -> outside_knowledge -> specific-terms -> style -> surrealism"],["part1 -> outside_knowledge -> specific-terms -> style -> victorian","part1 -> outside_knowledge -> specific-terms -> style -> victorian"],["part1 -> outside_knowledge -> specific-terms -> vehicle","part1 -> outside_knowledge -> specific-terms -> vehicle"],["part1 -> outside_knowledge -> specific-terms -> weather","part1 -> outside_knowledge -> specific-terms -> weather"],["part2 -> aesthetic","part2 -> aesthetic"],["part2 -> generative","part2 -> generative"],["part2 -> technical","part2 -> technical"]],"value":["Overall"],"type":"value","label":"ABench CheckBoxes","show_label":true,"container":true,"min_width":160,"interactive":true,"visible":true,"elem_classes":[],"name":"checkboxgroup","_selectable":false},"skip_api":false,"component_class_id":"0635a5d3bf87369f1c2c1c69f8a3d0cc","key":null,"api_info":{"items":{"enum":["Overall","part1 -> bag_of_words -> attribute","part1 -> bag_of_words -> composition -> arrangement","part1 -> bag_of_words -> composition -> occlusion","part1 -> bag_of_words -> composition -> orientation","part1 -> bag_of_words -> composition -> size","part1 -> bag_of_words -> counting","part1 -> bag_of_words -> noun_as_adjective","part1 -> basic_recognition -> major","part1 -> basic_recognition -> minor","part1 -> outside_knowledge -> contradiction overcome","part1 -> outside_knowledge -> specific-terms -> company","part1 -> outside_knowledge -> specific-terms -> creature","part1 -> outside_knowledge -> specific-terms -> daily","part1 -> outside_knowledge -> specific-terms -> food","part1 -> outside_knowledge -> specific-terms -> geography","part1 -> outside_knowledge -> specific-terms -> material","part1 -> outside_knowledge -> specific-terms -> science","part1 -> outside_knowledge -> specific-terms -> sports","part1 -> outside_knowledge -> specific-terms -> style -> abstract","part1 -> outside_knowledge -> specific-terms -> style -> art","part1 -> outside_knowledge -> specific-terms -> style -> art_deco","part1 -> outside_knowledge -> specific-terms -> style -> cubism","part1 -> outside_knowledge -> specific-terms -> style -> dadaism","part1 -> outside_knowledge -> specific-terms -> style -> deco","part1 -> outside_knowledge -> specific-terms -> style -> expressionism","part1 -> outside_knowledge -> specific-terms -> style -> fauvism","part1 -> outside_knowledge -> specific-terms -> style -> futurism","part1 -> outside_knowledge -> specific-terms -> style -> minimalism","part1 -> outside_knowledge -> specific-terms -> style -> pop","part1 -> outside_knowledge -> specific-terms -> style -> psychedelic","part1 -> outside_knowledge -> specific-terms -> style -> steampunk","part1 -> outside_knowledge -> specific-terms -> style -> surrealism","part1 -> outside_knowledge -> specific-terms -> style -> victorian","part1 -> outside_knowledge -> specific-terms -> vehicle","part1 -> outside_knowledge -> specific-terms -> weather","part2 -> aesthetic","part2 -> generative","part2 -> technical"],"type":"string"},"title":"Checkbox Group","type":"array"},"example_inputs":["Overall"]},{"id":348,"type":"row","props":{"variant":"default","visible":true,"equal_height":true,"show_progress":false,"name":"row"},"skip_api":true,"component_class_id":"b5cf3d15e2293fb5ccc071d7b8d69f64","key":null},{"id":349,"type":"textbox","props":{"value":"Input the Model Name (fuzzy, case insensitive)","lines":1,"max_lines":20,"label":"Model Name","show_label":true,"container":true,"min_width":160,"interactive":true,"visible":true,"autofocus":false,"autoscroll":true,"elem_classes":[],"type":"text","rtl":false,"show_copy_button":false,"name":"textbox","_selectable":false},"skip_api":false,"component_class_id":"d0491bb0fbd427bdb2a4549c4d1ac869","key":null,"api_info":{"type":"string"},"example_inputs":"Hello!!"},{"id":350,"type":"checkboxgroup","props":{"choices":[["<4B","<4B"],["4B-10B","4B-10B"],["10B-20B","10B-20B"],["20B-40B","20B-40B"],[">40B",">40B"],["Unknown","Unknown"]],"value":["<4B","4B-10B","10B-20B","20B-40B",">40B","Unknown"],"type":"value","label":"Model Size","show_label":true,"container":true,"min_width":160,"interactive":true,"visible":true,"elem_classes":[],"name":"checkboxgroup","_selectable":false},"skip_api":false,"component_class_id":"0635a5d3bf87369f1c2c1c69f8a3d0cc","key":null,"api_info":{"items":{"enum":["<4B","4B-10B","10B-20B","20B-40B",">40B","Unknown"],"type":"string"},"title":"Checkbox Group","type":"array"},"example_inputs":["<4B"]},{"id":351,"type":"checkboxgroup","props":{"choices":[["API","API"],["OpenSource","OpenSource"]],"value":["API","OpenSource"],"type":"value","label":"Model Type","show_label":true,"container":true,"min_width":160,"interactive":true,"visible":true,"elem_classes":[],"name":"checkboxgroup","_selectable":false},"skip_api":false,"component_class_id":"0635a5d3bf87369f1c2c1c69f8a3d0cc","key":null,"api_info":{"items":{"enum":["API","OpenSource"],"type":"string"},"title":"Checkbox Group","type":"array"},"example_inputs":["API"]},{"id":352,"type":"form","props":{"scale":3,"min_width":480,"name":"form"},"skip_api":true,"component_class_id":"43cda85c6ff7a5dd8f83d29496b014ee","key":null},{"id":353,"type":"dataframe","props":{"value":{"headers":["Rank","Method","Param (B)","Language Model","Vision Model","Eval Date","Overall"],"data":[[1,"Qwen2.5-VL-72B",73.4,"Qwen2.5-72B","QwenViT","2025/02/02",81.0],[2,"GPT-4.1-20250414",null,"","","2025/04/16",79.6],[3,"Ovis2-16B",16.2,"Qwen2.5-14B","AIMv2 Huge","2025/02/18",79.4],[4,"InternVL2.5-26B-MPO",26.0,"InternLM2.5-20B","InternViT-6B-v2.5","2024/12/28",79.4],[5,"RBDash-v1.5",79.0,"Qwen2-72B","CLIP ViT-L/14
InternViT-6B","2024/11/17",79.4],[6,"Qwen2-VL-72B",73.4,"Qwen2-72B","QwenViT","2024/10/28",79.4],[7,"InternVL2.5-78B-MPO",78.0,"Qwen-2.5-72B","InternViT-6B-v2.5","2024/12/29",79.3],[8,"GPT-4o (0513, detail-high)",null,"","","2024/05/31",79.2],[9,"GPT-4o (0806, detail-high)",null,"","","2024/08/08",79.1],[10,"Qwen-VL-Max-0809",72.0,"Qwen2-72B","QwenViT","2024/09/12",78.9],[11,"InternVL3-78B",78.4,"Qwen2.5-72B","InternViT-6B-v2.5","2025/04/14",78.9],[12,"Taiyi",null,"","","2024/12/11",78.8],[13,"GPT-4o (0513, detail-low)",null,"","","2024/05/15",78.8],[14,"Ovis2-34B",34.9,"Qwen2.5-32B","AIMv2-1B","2025/02/18",78.7],[15,"InternVL2.5-38B-MPO",38.0,"Qwen-2.5-32B","InternViT-6B-v2.5","2024/12/28",78.6],[16,"MUG-U-7B",7.0,"","","2025/03/19",78.5],[17,"Step-1o",null,"","","2025/01/13",78.4],[18,"BlueLM-V-3B",3.0,"BlueLM-3B","SigLIP-400M","2024/10/30",77.7],[19,"Ovis2-4B",4.62,"Qwen2.5-3B","AIMv2 Huge","2025/02/18",77.5],[20,"MiniCPM-o-2.6",8.67,"Qwen2.5-7B","SigLIP-400M","2025/01/21",77.5],[21,"GPT-4.1-mini-20250414",null,"","","2025/04/16",77.4],[22,"InternVL3-38B",38.4,"Qwen2.5-32B","InternViT-6B-v2.5","2025/04/14",77.1],[23,"InternVL2.5-8B-MPO",8.0,"InternLM2.5-7B","InternViT-300M-v2.5","2024/12/28",77.0],[24,"Ovis2-2B",2.46,"Qwen2.5-1.5B","AIMv2 Large","2025/02/18",76.6],[25,"Ovis1.6-Gemma2-27B",28.9,"Gemma2-27B","SigLIP-400M","2024/11/29",76.5],[26,"Qwen2-VL-7B",8.0,"Qwen2-7B","QwenViT","2024/09/12",76.4],[27,"Ovis2-8B",8.94,"Qwen2.5-7B","AIMv2 Huge","2025/02/18",76.4],[28,"grok-2-vision-1212",null,"","","2025/03/03",76.3],[29,"InternVL3-14B",15.1,"Qwen2.5-14B","InternViT-300M-v2.5","2025/04/14",76.3],[30,"InternVL3-8B",7.94,"Qwen2.5-7B","InternViT-300M-v2.5","2025/04/14",76.3],[31,"Gemma3-27B",27.4,"Gemma3-27B","SigLIP-400M","2025/03/19",76.3],[32,"Kimi-VL-A3B-Instruct",16.4,"Moonlight-16B-A3B","MoonViT","2025/04/14",76.1],[33,"POINTS-Qwen2.5-7B",8.3,"Qwen-2.5-7B","CLIP ViT-L/14","2024/10/19",76.1],[34,"POINTS1.5-Qwen2.5-7B",8.3,"Qwen-2.5-7B","NaViT","2024/12/06",76.1],[35,"InternVL2.5-4B-MPO",4.0,"Qwen-2.5-3B","InternViT-300M-v2.5","2024/12/28",75.9],[36,"BailingMM-Pro-0120",81.0,"Bailing-80B","SigLIP-400M","2025/01/25",75.8],[37,"HunYuan-Standard-Vision",null,"","","2025/01/15",75.7],[38,"Qwen2.5-VL-7B",8.29,"Qwen2.5-7B","QwenViT","2025/02/02",75.7],[39,"Qwen-VL-Plus-0809",null,"","","2024/09/17",75.4],[40,"Aquila-VL-2B",2.2,"Qwen-2.5-1.5B","SigLIP-400M","2024/10/24",75.4],[41,"Gemini-1.5-Pro",null,"","","2024/06/10",75.4],[42,"abab7-preview",null,"","","2024/12/11",75.4],[43,"Phi-4-MultiModal",5.57,"Phi-4-Mini","SigLIP-400M","2025/03/13",75.4],[44,"Ovis1.6-Llama3.2-3B",4.1,"Llama-3.2-3B","SigLIP-400M","2024/10/24",75.2],[45,"InternVL2-40B",40.0,"Nous-Hermes-2-Yi-34B","InternViT-6B","2024/07/11",75.2],[46,"LLaVA-OneVision-7B",8.0,"Qwen2-7B","SigLIP-400M","2024/09/16",75.2],[47,"Ovis1.5-Llama3-8B",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/07/29",75.1],[48,"POINTS-Yi-1.5-9B",9.5,"Yi-1.5-9B","CLIP ViT-L/14","2024/10/11",75.0],[49,"GLM-4v-Plus-20250111",null,"","","2025/01/25",74.9],[50,"Qwen2.5-VL-3B",3.75,"Qwen2.5-3B","QwenViT","2025/02/02",74.9],[51,"MiniCPM-V-2.6",8.0,"Qwen2-7B","SigLIP-400M","2024/08/08",74.6],[52,"SAIL-VL-2B",2.1,"Qwen2.5-1.5B","InternViT-300M","2024/12/25",74.5],[53,"VARCO-VISION-14B",15.2,"Qwen2.5-14B","SigLIP-400M","2025/01/02",74.4],[54,"Ovis1.6-Gemma2-9B",10.2,"Gemma2-9B-It","SigLIP-400M","2024/09/19",74.4],[55,"moonshot-v1-8k",null,"","","2025/03/03",74.3],[56,"InternVL2-26B",26.0,"InternLM2-20B","InternViT-6B","2024/07/11",74.3],[57,"Ross-Qwen2-7B",8.2,"Qwen2-7B","CLIP ViT-L/14","2025/01/17",74.2],[58,"InternVL3-2B",2.09,"Qwen2.5-1.5B","InternViT-300M-v2.5","2025/04/14",74.2],[59,"GLM-4v-9B",9.0,"GLM-4-9B","EVA-02-5B","2024/06/14",74.0],[60,"InternVL2-Llama3-76B",76.0,"Llama-3-70B-Instruct","InternViT-6B","2024/07/19",73.9],[61,"SmolVLM2",2.25,"SmolLM2-1.7M","SigLIP-400M","2025/03/13",73.8],[62,"Molmo-7B-D",8.0,"Qwen2-7B","CLIP ViT-L/14","2024/10/12",73.8],[63,"Eagle-X5-34B-Chat",36.8,"Yi-34B","Clip-448
ConvNeXT-1024
SAM-1024
DET-1024
Pix2Struct-1024","2024/11/29",73.7],[64,"Gemini-1.5-Flash",null,"","","2024/09/16",73.6],[65,"LLaVA-OneVision-7B (SI)",8.0,"Qwen2-7B","SigLIP-400M","2024/09/17",73.5],[66,"Ovis1.5-Gemma2-9B",11.4,"Gemma2-9B-It","SigLIP-400M","2024/08/04",73.5],[67,"MiniCPM-Llama3-V2.5",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/05/27",73.3],[68,"Pixtral-12B",13.0,"Nemo-12B","ViT-400M","2024/09/16",73.1],[69,"InternVL2-8B",8.0,"InternLM2.5-7B","InternViT-300M","2024/07/11",72.9],[70,"GPT-4.1-nano-20250414",null,"","","2025/04/16",72.9],[71,"Mantis-8B-Idefics2",8.0,"Mistral-7B","SigLIP-400M","2024/08/08",72.9],[72,"WeMM",7.0,"InternLM2-7B","SigLIP-400M","2024/06/09",72.7],[73,"granite-vision-3.3-2b",2.98,"granite-3.1-2b-instruct","SigLIP2-400M","2025/06/20",72.6],[74,"Bunny-Llama3-8B",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/07/18",72.6],[75,"XinYuan-VL-2B-Instruct",2.0,"Qwen2-1.5B","QwenViT","2024/09/27",72.6],[76,"InternVL2-8B-MPO",8.0,"InternLM2.5-7B","InternViT-300M","2024/11/25",72.4],[77,"granite-vision-3.2-2b",2.98,"granite-3.1-2b-instruct","SigLip","2025/06/20",72.4],[78,"CogVLM2-19B-Chat",19.0,"Llama-3-8B-Instruct","EVA2-CLIP-E","2024/05/31",72.3],[79,"Cambrian-34B",34.0,"Nous-Hermes-2-Yi-34B","CLIP ViT-L/14","2024/07/18",72.3],[80,"NVLM-D-72B",79.4,"Qwen2-72B","InternViT-6B","2024/10/19",72.1],[81,"InternVL2-8B-MPO-CoT",8.0,"InternLM2.5-7B","InternViT-300M","2024/11/25",71.9],[82,"InternVL-Chat-V1.5",26.0,"InternLM2-20B","InternViT-6B","2024/04/17",71.7],[83,"Vintern-3B-beta",3.7,"Qwen-2.5-3B","InternViT-300M","2024/10/24",71.7],[84,"MMAlaya2",26.0,"InternLM2-20B","InternViT-6B","2024/08/27",71.5],[85,"Step-1.5V-mini",null,"","","2024/12/11",71.4],[86,"Qwen2-VL-2B",2.0,"Qwen2-1.5B","QwenViT","2024/09/12",71.3],[87,"Ovis2-1B",1.27,"Qwen2.5-0.5B","AIMv2 Large","2025/02/18",71.3],[88,"Aria",25.3,"Aria-MoE","SigLIP-400M","2024/12/05",71.3],[89,"Mantis-8B-siglip-llama3",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/08/08",71.1],[90,"InternVL2.5-2B-MPO",2.0,"InternLM2.5-1.8B","InternViT-300M-v2.5","2024/12/28",71.1],[91,"Eagle-X5-13B",15.0,"Vicuna-v1.5-13B","Clip-448
ConvNeXT-1024
SAM-1024
DET-1024
Pix2Struct-1024","2024/09/26",70.8],[92,"H2OVL-2B",2.2,"H2O-DANUBE2-1.8B","InternViT-300M","2024/10/31",70.7],[93,"Claude3.7-Sonnet",null,"","","2025/02/27",70.7],[94,"Mantis-8B-clip-llama3",8.0,"Llama-3-8B-Instruct","CLIP ViT-L/14","2024/08/08",70.7],[95,"InternVL2-4B",4.0,"Phi-3","InternViT-300M","2024/07/11",70.6],[96,"IDEFICS2-8B",8.0,"Mistral-7B","SigLIP-400M","2024/04/26",70.5],[97,"Slime-8B",8.0,"Llama-3-8B-Instruct","CLIP ViT-L/14","2024/09/14",70.5],[98,"GPT-4v (0409, detail-high)",null,"","","2024/05/15",70.4],[99,"TransCore-M",13.4,"PCITransGPT-13B","CLIP ViT-L/14","2024/04/16",70.4],[100,"VITA-1.5",8.3,"Qwen2-7B","InternViT-300M","2025/01/01",70.3],[101,"BailingMM-Lite-1203",21.0,"Bailing-20B","SigLIP-400M","2024/12/08",70.3],[102,"Gemma3-12B",12.2,"Gemma3-12B","SigLIP-400M","2025/03/19",70.3],[103,"360VL-70B",70.0,"Llama-3-70B-Instruct","CLIP ViT-L/14","2024/05/25",70.3],[104,"LLaVA-Next-Interleave-7B-DPO",8.0,"Qwen-1.5-7B","SigLIP-400M","2024/07/29",70.2],[105,"Yi-VL-34B",34.6,"Yi-34B","CLIP ViT-H/14","2024/01/25",70.0],[106,"Yi-VL-6B",6.6,"Yi-6B","CLIP ViT-H/14","2024/01/25",69.8],[107,"InternLM-XComposer2",7.0,"InternLM2-7B","CLIP ViT-L/14","2024/01/26",69.7],[108,"LLaVA-Next-Llama3",8.0,"Llama-3-8B-Instruct","CLIP ViT-L/14","2024/07/29",69.7],[109,"Mini-InternVL-Chat-4B-V1.5",4.0,"Phi-3","InternViT-300M","2024/06/10",69.6],[110,"Llama-3.2-11B-Vision-Instruct",11.0,"Llama-3.1-8B","","2024/10/07",69.2],[111,"DeepSeek-VL-7B",7.3,"DeekSeek-7B","SAM-B
SigLIP-L","2024/03/21",69.1],[112,"InternVL3-1B",0.94,"Qwen2.5-0.5B","InternViT-300M-v2.5","2025/04/14",68.9],[113,"LLaVA-Next-Interleave-7B",8.0,"Qwen-1.5-7B","SigLIP-400M","2024/08/08",68.9],[114,"Cambrian-8B",8.0,"Vicuna-v1.5-7B","CLIP ViT-L/14","2024/07/11",68.6],[115,"Janus-Pro-7B",7.42,"DeepSeek-7B","SigLIP-400M","2025/02/02",68.4],[116,"Eagle-X5-7B",9.0,"Vicuna-v1.5-7B","Clip-448
ConvNeXT-1024
SAM-1024
DET-1024
Pix2Struct-1024","2024/09/26",68.4],[117,"LLaVA-Next-Mistral-7B",7.6,"Mistral-7B","CLIP ViT-L/14","2024/03/25",68.3],[118,"Phi-3-Vision",4.2,"Phi-3","CLIP ViT-L/14","2024/05/31",68.2],[119,"MiniCPM-V-2",2.8,"MiniCPM-2.4B","SigLIP-400M","2024/04/15",68.0],[120,"LLaVA-OneVision-0.5B",1.0,"Qwen2-0.5B","SigLIP-400M","2024/09/16",67.6],[121,"InternVL2.5-1B-MPO",1.0,"Qwen-2.5-0.5B","InternViT-300M-v2.5","2024/12/28",67.5],[122,"Cambrian-13B",13.0,"Vicuna-v1.5-13B","CLIP ViT-L/14","2024/07/29",67.3],[123,"Gemma3-4B",4.3,"Gemma3-4B","SigLIP-400M","2025/03/19",67.0],[124,"CogVLM-17B-Chat",17.0,"Vicuna-v1.5-7B","EVA2-CLIP-E","2024/01/03",66.9],[125,"Slime-7B",7.0,"Vicuna-v1.5-7B","CLIP ViT-L/14","2024/09/14",66.2],[126,"Mini-InternVL-Chat-2B-V1.5",2.0,"InternLM2-1.8B","InternViT-300M","2024/06/10",66.1],[127,"Molmo-7B-O",8.0,"Qwen2-7B","CLIP ViT-L/14","2024/10/20",66.0],[128,"LLaVA-Next-Vicuna-7B",7.1,"Vicuna-v1.5-7B","CLIP ViT-L/14","2024/03/25",65.8],[129,"LLaVA-v1.5-7B",7.2,"Vicuna-v1.5-7B","CLIP ViT-L/14","2023/10/05",65.6],[130,"MiniMonkey",2.2,"InternLM2-1.8B","InternViT-300M","2024/09/26",65.1],[131,"SmolVLM-Instruct",2.3,"SmolLM2-1.7B","SigLIP-400M","2025/01/27",65.0],[132,"LLaVA-v1.5-13B",13.4,"Vicuna-v1.5-13B","CLIP ViT-L/14","2023/10/05",64.8],[133,"SmolVLM-Instruct-DPO",2.3,"SmolLM2-1.7B","SigLIP-400M","2025/01/27",64.7],[134,"LLaVA-Next-Vicuna-13B",13.4,"Vicuna-v1.5-13B","CLIP ViT-L/14","2024/03/25",64.3],[135,"InternVL2-2B",2.0,"InternLM2-1.8B","InternViT-300M","2024/07/11",64.2],[136,"InternVL2-1B",1.0,"Qwen2-0.5B","InternViT-300M","2024/07/11",64.0],[137,"InternLM-XComposer2-1.8B",2.0,"InternLM2-1.8B","CLIP ViT-L/14","2024/06/09",63.9],[138,"Falcon2-VLM-11B",11.4,"Falcon2-11B","CLIP ViT-L/14","2024/10/30",63.5],[139,"MolmoE-1B",7.2,"OLMoE-1B-7B-0924","CLIP ViT-L/14","2024/10/21",63.3],[140,"Monkey-Chat",9.8,"Qwen-7B","ViT-BigHuge","2024/01/16",63.2],[141,"Qwen-VL-Chat",9.6,"Qwen-7B","ViT-G/16","2023/08/24",63.1],[142,"H2OVL-800M",0.83,"H2O-DANUBE3-500M","InternViT-300M","2024/10/31",63.1],[143,"Slime-13B",13.0,"Vicuna-v1.5-13B","CLIP ViT-L/14","2024/09/14",63.0],[144,"DeepSeek-VL-1.3B",2.0,"DeekSeek-1B","SAM-B
SigLIP-L","2024/03/21",62.8],[145,"AKI-4B",4.33,"Phi-3.5","SigLIP-400M","2025/03/25",62.4],[146,"Monkey",9.8,"Qwen-7B","ViT-BigHuge","2024/01/11",61.9],[147,"Emu3_chat",8.49,"","","2025/01/26",61.2],[148,"SmolVLM2-500M",0.51,"SmolLM2-360M","ViT-93M","2025/03/13",61.2],[149,"abab6.5s",null,"","","2024/12/11",61.2],[150,"Mantis-8B-Fuyu",8.0,"Fuyu-8B","","2024/09/07",60.3],[151,"PaliGemma-3B-mix-448",3.0,"Gemma-2B","SigLIP-400M","2024/05/17",59.8],[152,"Moondream1",1.9,"SigLIP-400M","Phi-1.5","2024/09/26",59.6],[153,"Janus-1.3B",2.1,"DeepSeek-1B","SigLIP-400M","2024/10/24",59.1],[154,"SmolVLM-Synthetic",2.3,"SmolLM2-1.7B","SigLIP-400M","2025/01/27",58.9],[155,"LLaVA-OneVision-0.5B (SI)",1.0,"Qwen2-0.5B","SigLIP-400M","2024/09/17",58.8],[156,"SmolVLM-500M",0.51,"SmolLM2-360M","ViT-93M","2025/01/27",54.7],[157,"Qwen-VL",9.6,"Qwen-7B","ViT-G/16","2023/08/24",52.2],[158,"SmolVLM2-256M",0.26,"SmolLM2-135M","ViT-93M","2025/03/13",45.3],[159,"SmolVLM-256M",0.26,"SmolLM2-135M","ViT-93M","2025/01/27",36.1],[160,"Kosmos2",1.7,"","","2024/10/19",33.2]],"metadata":null},"headers":["1","2","3"],"row_count":[1,"dynamic"],"col_count":[3,"dynamic"],"datatype":["number","html","number","html","html","str","number"],"type":"pandas","latex_delimiters":[{"left":"$$","right":"$$","display":true}],"show_label":true,"height":500,"min_width":160,"interactive":false,"visible":true,"elem_classes":[],"wrap":true,"line_breaks":true,"column_widths":[],"name":"dataframe","_selectable":false},"skip_api":false,"component_class_id":"6a51bb3357f2e94c40fb8d4fbe06aa8e","key":null,"api_info":{"properties":{"headers":{"items":{"type":"string"},"title":"Headers","type":"array"},"data":{"items":{"items":{},"type":"array"},"title":"Data","type":"array"},"metadata":{"anyOf":[{"additionalProperties":{"anyOf":[{"items":{},"type":"array"},{"type":"null"}]},"type":"object"},{"type":"null"}],"default":null,"title":"Metadata"}},"required":["headers","data"],"title":"DataframeData","type":"object"},"example_inputs":{"headers":["a","b"],"data":[["foo","bar"]]}},{"id":354,"type":"textbox","props":{"value":"ABench","lines":1,"max_lines":20,"label":"ABench","show_label":true,"container":true,"min_width":160,"visible":false,"autofocus":false,"autoscroll":true,"elem_classes":[],"type":"text","rtl":false,"show_copy_button":false,"name":"textbox","_selectable":false},"skip_api":false,"component_class_id":"d0491bb0fbd427bdb2a4549c4d1ac869","key":null,"api_info":{"type":"string"},"example_inputs":"Hello!!"},{"id":355,"type":"form","props":{"scale":0,"min_width":0,"name":"form"},"skip_api":true,"component_class_id":"43cda85c6ff7a5dd8f83d29496b014ee","key":null},{"id":356,"type":"form","props":{"scale":0,"min_width":0,"name":"form"},"skip_api":true,"component_class_id":"43cda85c6ff7a5dd8f83d29496b014ee","key":null},{"id":357,"type":"tabitem","props":{"label":"📊 MTVQA Leaderboard","visible":true,"interactive":true,"id":31,"elem_id":"MTVQA","name":"tab"},"skip_api":true,"component_class_id":"18f46968e2b273dc5dbda0fe78433d7e","key":null},{"id":358,"type":"checkboxgroup","props":{"choices":[["Overall","Overall"],["AR","AR"],["DE","DE"],["FR","FR"],["IT","IT"],["JA","JA"],["KR","KR"],["RU","RU"],["TH","TH"],["VI","VI"]],"value":["Overall"],"type":"value","label":"MTVQA CheckBoxes","show_label":true,"container":true,"min_width":160,"interactive":true,"visible":true,"elem_classes":[],"name":"checkboxgroup","_selectable":false},"skip_api":false,"component_class_id":"0635a5d3bf87369f1c2c1c69f8a3d0cc","key":null,"api_info":{"items":{"enum":["Overall","AR","DE","FR","IT","JA","KR","RU","TH","VI"],"type":"string"},"title":"Checkbox Group","type":"array"},"example_inputs":["Overall"]},{"id":359,"type":"row","props":{"variant":"default","visible":true,"equal_height":true,"show_progress":false,"name":"row"},"skip_api":true,"component_class_id":"b5cf3d15e2293fb5ccc071d7b8d69f64","key":null},{"id":360,"type":"textbox","props":{"value":"Input the Model Name (fuzzy, case insensitive)","lines":1,"max_lines":20,"label":"Model Name","show_label":true,"container":true,"min_width":160,"interactive":true,"visible":true,"autofocus":false,"autoscroll":true,"elem_classes":[],"type":"text","rtl":false,"show_copy_button":false,"name":"textbox","_selectable":false},"skip_api":false,"component_class_id":"d0491bb0fbd427bdb2a4549c4d1ac869","key":null,"api_info":{"type":"string"},"example_inputs":"Hello!!"},{"id":361,"type":"checkboxgroup","props":{"choices":[["<4B","<4B"],["4B-10B","4B-10B"],["10B-20B","10B-20B"],["20B-40B","20B-40B"],[">40B",">40B"],["Unknown","Unknown"]],"value":["<4B","4B-10B","10B-20B","20B-40B",">40B","Unknown"],"type":"value","label":"Model Size","show_label":true,"container":true,"min_width":160,"interactive":true,"visible":true,"elem_classes":[],"name":"checkboxgroup","_selectable":false},"skip_api":false,"component_class_id":"0635a5d3bf87369f1c2c1c69f8a3d0cc","key":null,"api_info":{"items":{"enum":["<4B","4B-10B","10B-20B","20B-40B",">40B","Unknown"],"type":"string"},"title":"Checkbox Group","type":"array"},"example_inputs":["<4B"]},{"id":362,"type":"checkboxgroup","props":{"choices":[["API","API"],["OpenSource","OpenSource"]],"value":["API","OpenSource"],"type":"value","label":"Model Type","show_label":true,"container":true,"min_width":160,"interactive":true,"visible":true,"elem_classes":[],"name":"checkboxgroup","_selectable":false},"skip_api":false,"component_class_id":"0635a5d3bf87369f1c2c1c69f8a3d0cc","key":null,"api_info":{"items":{"enum":["API","OpenSource"],"type":"string"},"title":"Checkbox Group","type":"array"},"example_inputs":["API"]},{"id":363,"type":"form","props":{"scale":3,"min_width":480,"name":"form"},"skip_api":true,"component_class_id":"43cda85c6ff7a5dd8f83d29496b014ee","key":null},{"id":364,"type":"dataframe","props":{"value":{"headers":["Rank","Method","Param (B)","Language Model","Vision Model","Eval Date","Overall"],"data":[[1,"GPT-4.1-mini-20250414",null,"","","2025/04/16",36.8],[2,"GPT-4.1-20250414",null,"","","2025/04/16",34.1],[3,"BlueLM-V-3B",3.0,"BlueLM-3B","SigLIP-400M","2024/10/30",32.7],[4,"InternVL3-78B",78.4,"Qwen2.5-72B","InternViT-6B-v2.5","2025/04/14",32.5],[5,"InternVL3-38B",38.4,"Qwen2.5-32B","InternViT-6B-v2.5","2025/04/14",32.4],[6,"InternVL2.5-78B-MPO",78.0,"Qwen-2.5-72B","InternViT-6B-v2.5","2024/12/29",32.1],[7,"Gemini-1.5-Pro",null,"","","2024/06/10",32.0],[8,"Qwen2.5-VL-72B",73.4,"Qwen2.5-72B","QwenViT","2025/02/02",31.5],[9,"InternVL2.5-38B-MPO",38.0,"Qwen-2.5-32B","InternViT-6B-v2.5","2024/12/28",31.2],[10,"GPT-4o (0513, detail-high)",null,"","","2024/05/31",31.2],[11,"InternVL3-14B",15.1,"Qwen2.5-14B","InternViT-300M-v2.5","2025/04/14",31.1],[12,"GPT-4o (0806, detail-high)",null,"","","2024/08/08",31.0],[13,"Claude3.7-Sonnet",null,"","","2025/02/27",30.6],[14,"Ovis2-34B",34.9,"Qwen2.5-32B","AIMv2-1B","2025/02/18",30.6],[15,"Gemini-1.5-Flash",null,"","","2024/09/16",30.5],[16,"InternVL3-8B",7.94,"Qwen2.5-7B","InternViT-300M-v2.5","2025/04/14",30.4],[17,"Ovis2-16B",16.2,"Qwen2.5-14B","AIMv2 Huge","2025/02/18",30.3],[18,"Ovis2-8B",8.94,"Qwen2.5-7B","AIMv2 Huge","2025/02/18",29.7],[19,"Qwen2-VL-72B",73.4,"Qwen2-72B","QwenViT","2024/10/28",29.6],[20,"Ovis2-4B",4.62,"Qwen2.5-3B","AIMv2 Huge","2025/02/18",29.4],[21,"Qwen-VL-Max-0809",72.0,"Qwen2-72B","QwenViT","2024/09/12",29.2],[22,"Qwen2.5-VL-7B",8.29,"Qwen2.5-7B","QwenViT","2025/02/02",29.0],[23,"Gemma3-27B",27.4,"Gemma3-27B","SigLIP-400M","2025/03/19",28.9],[24,"InternVL2.5-26B-MPO",26.0,"InternLM2.5-20B","InternViT-6B-v2.5","2024/12/28",28.7],[25,"BailingMM-Pro-0120",81.0,"Bailing-80B","SigLIP-400M","2025/01/25",28.1],[26,"InternVL2.5-4B-MPO",4.0,"Qwen-2.5-3B","InternViT-300M-v2.5","2024/12/28",28.0],[27,"GPT-4.1-nano-20250414",null,"","","2025/04/16",27.6],[28,"Step-1o",null,"","","2025/01/13",27.4],[29,"InternVL2.5-8B-MPO",8.0,"InternLM2.5-7B","InternViT-300M-v2.5","2024/12/28",27.2],[30,"InternVL3-2B",2.09,"Qwen2.5-1.5B","InternViT-300M-v2.5","2025/04/14",26.7],[31,"Ovis1.6-Gemma2-27B",28.9,"Gemma2-27B","SigLIP-400M","2024/11/29",26.5],[32,"GPT-4o (0513, detail-low)",null,"","","2024/05/15",26.4],[33,"MUG-U-7B",7.0,"","","2025/03/19",26.3],[34,"abab7-preview",null,"","","2024/12/11",26.1],[35,"Qwen2-VL-7B",8.0,"Qwen2-7B","QwenViT","2024/09/12",25.8],[36,"Qwen-VL-Plus-0809",null,"","","2024/09/17",25.8],[37,"Ovis2-2B",2.46,"Qwen2.5-1.5B","AIMv2 Large","2025/02/18",25.6],[38,"GLM-4v-Plus-20250111",null,"","","2025/01/25",25.6],[39,"Kimi-VL-A3B-Instruct",16.4,"Moonlight-16B-A3B","MoonViT","2025/04/14",24.1],[40,"Gemma3-12B",12.2,"Gemma3-12B","SigLIP-400M","2025/03/19",23.8],[41,"Qwen2.5-VL-3B",3.75,"Qwen2.5-3B","QwenViT","2025/02/02",23.8],[42,"Ovis2-1B",1.27,"Qwen2.5-0.5B","AIMv2 Large","2025/02/18",23.7],[43,"HunYuan-Standard-Vision",null,"","","2025/01/15",23.4],[44,"Taiyi",null,"","","2024/12/11",23.4],[45,"Vintern-3B-beta",3.7,"Qwen-2.5-3B","InternViT-300M","2024/10/24",23.4],[46,"MiniCPM-o-2.6",8.67,"Qwen2.5-7B","SigLIP-400M","2025/01/21",23.1],[47,"InternVL2-Llama3-76B",76.0,"Llama-3-70B-Instruct","InternViT-6B","2024/07/19",22.8],[48,"GLM-4v-9B",9.0,"GLM-4-9B","EVA-02-5B","2024/06/14",22.8],[49,"grok-2-vision-1212",null,"","","2025/03/03",22.6],[50,"InternVL2.5-2B-MPO",2.0,"InternLM2.5-1.8B","InternViT-300M-v2.5","2024/12/28",22.6],[51,"InternVL3-1B",0.94,"Qwen2.5-0.5B","InternViT-300M-v2.5","2025/04/14",22.4],[52,"Gemma3-4B",4.3,"Gemma3-4B","SigLIP-400M","2025/03/19",22.1],[53,"InternVL2-8B-MPO-CoT",8.0,"InternLM2.5-7B","InternViT-300M","2024/11/25",22.1],[54,"VARCO-VISION-14B",15.2,"Qwen2.5-14B","SigLIP-400M","2025/01/02",21.8],[55,"InternVL2.5-1B-MPO",1.0,"Qwen-2.5-0.5B","InternViT-300M-v2.5","2024/12/28",21.7],[56,"Ovis1.6-Llama3.2-3B",4.1,"Llama-3.2-3B","SigLIP-400M","2024/10/24",21.1],[57,"Qwen2-VL-2B",2.0,"Qwen2-1.5B","QwenViT","2024/09/12",20.8],[58,"InternVL2-40B",40.0,"Nous-Hermes-2-Yi-34B","InternViT-6B","2024/07/11",20.4],[59,"Pixtral-12B",13.0,"Nemo-12B","ViT-400M","2024/09/16",20.2],[60,"SAIL-VL-2B",2.1,"Qwen2.5-1.5B","InternViT-300M","2024/12/25",20.2],[61,"InternVL2-8B-MPO",8.0,"InternLM2.5-7B","InternViT-300M","2024/11/25",20.1],[62,"moonshot-v1-8k",null,"","","2025/03/03",20.0],[63,"Step-1.5V-mini",null,"","","2024/12/11",19.8],[64,"NVLM-D-72B",79.4,"Qwen2-72B","InternViT-6B","2024/10/19",19.6],[65,"Ovis1.6-Gemma2-9B",10.2,"Gemma2-9B-It","SigLIP-400M","2024/09/19",19.2],[66,"InternVL2-8B",8.0,"InternLM2.5-7B","InternViT-300M","2024/07/11",18.1],[67,"InternVL2-26B",26.0,"InternLM2-20B","InternViT-6B","2024/07/11",17.7],[68,"InternVL-Chat-V1.5",26.0,"InternLM2-20B","InternViT-6B","2024/04/17",17.4],[69,"Ovis1.5-Llama3-8B",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/07/29",17.3],[70,"MMAlaya2",26.0,"InternLM2-20B","InternViT-6B","2024/08/27",17.0],[71,"MiniCPM-V-2.6",8.0,"Qwen2-7B","SigLIP-400M","2024/08/08",17.0],[72,"granite-vision-3.3-2b",2.98,"granite-3.1-2b-instruct","SigLIP2-400M","2025/06/20",17.0],[73,"abab6.5s",null,"","","2024/12/11",16.9],[74,"XinYuan-VL-2B-Instruct",2.0,"Qwen2-1.5B","QwenViT","2024/09/27",16.6],[75,"POINTS1.5-Qwen2.5-7B",8.3,"Qwen-2.5-7B","NaViT","2024/12/06",16.6],[76,"Cambrian-13B",13.0,"Vicuna-v1.5-13B","CLIP ViT-L/14","2024/07/29",16.3],[77,"MiniCPM-Llama3-V2.5",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/05/27",16.3],[78,"VITA-1.5",8.3,"Qwen2-7B","InternViT-300M","2025/01/01",16.3],[79,"Eagle-X5-34B-Chat",36.8,"Yi-34B","Clip-448
ConvNeXT-1024
SAM-1024
DET-1024
Pix2Struct-1024","2024/11/29",16.2],[80,"Cambrian-34B",34.0,"Nous-Hermes-2-Yi-34B","CLIP ViT-L/14","2024/07/18",16.2],[81,"LLaVA-OneVision-7B (SI)",8.0,"Qwen2-7B","SigLIP-400M","2024/09/17",15.9],[82,"InternVL2-4B",4.0,"Phi-3","InternViT-300M","2024/07/11",15.5],[83,"Eagle-X5-13B",15.0,"Vicuna-v1.5-13B","Clip-448
ConvNeXT-1024
SAM-1024
DET-1024
Pix2Struct-1024","2024/09/26",15.3],[84,"Llama-3.2-11B-Vision-Instruct",11.0,"Llama-3.1-8B","","2024/10/07",15.3],[85,"Ovis1.5-Gemma2-9B",11.4,"Gemma2-9B-It","SigLIP-400M","2024/08/04",15.3],[86,"Phi-4-MultiModal",5.57,"Phi-4-Mini","SigLIP-400M","2025/03/13",14.3],[87,"granite-vision-3.2-2b",2.98,"granite-3.1-2b-instruct","SigLip","2025/06/20",14.2],[88,"Cambrian-8B",8.0,"Vicuna-v1.5-7B","CLIP ViT-L/14","2024/07/11",14.2],[89,"Molmo-7B-O",8.0,"Qwen2-7B","CLIP ViT-L/14","2024/10/20",14.1],[90,"LLaVA-OneVision-7B",8.0,"Qwen2-7B","SigLIP-400M","2024/09/16",14.0],[91,"Phi-3-Vision",4.2,"Phi-3","CLIP ViT-L/14","2024/05/31",13.9],[92,"LLaVA-Next-Llama3",8.0,"Llama-3-8B-Instruct","CLIP ViT-L/14","2024/07/29",13.5],[93,"Mini-InternVL-Chat-4B-V1.5",4.0,"Phi-3","InternViT-300M","2024/06/10",13.5],[94,"POINTS-Qwen2.5-7B",8.3,"Qwen-2.5-7B","CLIP ViT-L/14","2024/10/19",13.4],[95,"SmolVLM2",2.25,"SmolLM2-1.7M","SigLIP-400M","2025/03/13",13.4],[96,"Molmo-7B-D",8.0,"Qwen2-7B","CLIP ViT-L/14","2024/10/12",13.1],[97,"Aquila-VL-2B",2.2,"Qwen-2.5-1.5B","SigLIP-400M","2024/10/24",13.1],[98,"LLaVA-Next-Vicuna-13B",13.4,"Vicuna-v1.5-13B","CLIP ViT-L/14","2024/03/25",13.1],[99,"Bunny-Llama3-8B",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/07/18",13.1],[100,"Eagle-X5-7B",9.0,"Vicuna-v1.5-7B","Clip-448
ConvNeXT-1024
SAM-1024
DET-1024
Pix2Struct-1024","2024/09/26",13.0],[101,"BailingMM-Lite-1203",21.0,"Bailing-20B","SigLIP-400M","2024/12/08",13.0],[102,"InternVL2-1B",1.0,"Qwen2-0.5B","InternViT-300M","2024/07/11",12.6],[103,"Qwen-VL-Chat",9.6,"Qwen-7B","ViT-G/16","2023/08/24",12.5],[104,"LLaVA-Next-Vicuna-7B",7.1,"Vicuna-v1.5-7B","CLIP ViT-L/14","2024/03/25",12.3],[105,"Ross-Qwen2-7B",8.2,"Qwen2-7B","CLIP ViT-L/14","2025/01/17",12.3],[106,"WeMM",7.0,"InternLM2-7B","SigLIP-400M","2024/06/09",12.3],[107,"InternLM-XComposer2",7.0,"InternLM2-7B","CLIP ViT-L/14","2024/01/26",12.2],[108,"LLaVA-Next-Mistral-7B",7.6,"Mistral-7B","CLIP ViT-L/14","2024/03/25",11.7],[109,"MiniMonkey",2.2,"InternLM2-1.8B","InternViT-300M","2024/09/26",11.6],[110,"POINTS-Yi-1.5-9B",9.5,"Yi-1.5-9B","CLIP ViT-L/14","2024/10/11",11.6],[111,"H2OVL-2B",2.2,"H2O-DANUBE2-1.8B","InternViT-300M","2024/10/31",11.4],[112,"Monkey",9.8,"Qwen-7B","ViT-BigHuge","2024/01/11",11.1],[113,"Monkey-Chat",9.8,"Qwen-7B","ViT-BigHuge","2024/01/16",10.9],[114,"InternVL2-2B",2.0,"InternLM2-1.8B","InternViT-300M","2024/07/11",10.9],[115,"IDEFICS2-8B",8.0,"Mistral-7B","SigLIP-400M","2024/04/26",10.8],[116,"Qwen-VL",9.6,"Qwen-7B","ViT-G/16","2023/08/24",10.7],[117,"Janus-Pro-7B",7.42,"DeepSeek-7B","SigLIP-400M","2025/02/02",10.4],[118,"SmolVLM-Instruct",2.3,"SmolLM2-1.7B","SigLIP-400M","2025/01/27",10.0],[119,"LLaVA-OneVision-0.5B (SI)",1.0,"Qwen2-0.5B","SigLIP-400M","2024/09/17",10.0],[120,"Mini-InternVL-Chat-2B-V1.5",2.0,"InternLM2-1.8B","InternViT-300M","2024/06/10",10.0],[121,"TransCore-M",13.4,"PCITransGPT-13B","CLIP ViT-L/14","2024/04/16",9.6],[122,"360VL-70B",70.0,"Llama-3-70B-Instruct","CLIP ViT-L/14","2024/05/25",9.6],[123,"MolmoE-1B",7.2,"OLMoE-1B-7B-0924","CLIP ViT-L/14","2024/10/21",9.4],[124,"MiniCPM-V-2",2.8,"MiniCPM-2.4B","SigLIP-400M","2024/04/15",9.3],[125,"PaliGemma-3B-mix-448",3.0,"Gemma-2B","SigLIP-400M","2024/05/17",9.2],[126,"CogVLM-17B-Chat",17.0,"Vicuna-v1.5-7B","EVA2-CLIP-E","2024/01/03",9.2],[127,"H2OVL-800M",0.83,"H2O-DANUBE3-500M","InternViT-300M","2024/10/31",9.1],[128,"LLaVA-OneVision-0.5B",1.0,"Qwen2-0.5B","SigLIP-400M","2024/09/16",8.6],[129,"Falcon2-VLM-11B",11.4,"Falcon2-11B","CLIP ViT-L/14","2024/10/30",8.3],[130,"Slime-7B",7.0,"Vicuna-v1.5-7B","CLIP ViT-L/14","2024/09/14",7.7],[131,"Slime-13B",13.0,"Vicuna-v1.5-13B","CLIP ViT-L/14","2024/09/14",7.7],[132,"SmolVLM2-500M",0.51,"SmolLM2-360M","ViT-93M","2025/03/13",7.7],[133,"Mantis-8B-Idefics2",8.0,"Mistral-7B","SigLIP-400M","2024/08/08",7.6],[134,"DeepSeek-VL-7B",7.3,"DeekSeek-7B","SAM-B
SigLIP-L","2024/03/21",7.6],[135,"XGen-MM-Instruct-Interleave-v1.5",4.4,"Phi-3","SigLIP-400M","2024/09/06",7.5],[136,"Yi-VL-6B",6.6,"Yi-6B","CLIP ViT-H/14","2024/01/25",7.4],[137,"SmolVLM-Instruct-DPO",2.3,"SmolLM2-1.7B","SigLIP-400M","2025/01/27",7.2],[138,"XGen-MM-Instruct-DPO-v1.5",4.4,"Phi-3","SigLIP-400M","2024/09/06",7.0],[139,"Yi-VL-34B",34.6,"Yi-34B","CLIP ViT-H/14","2024/01/25",7.0],[140,"SmolVLM-Synthetic",2.3,"SmolLM2-1.7B","SigLIP-400M","2025/01/27",7.0],[141,"InternLM-XComposer2-1.8B",2.0,"InternLM2-1.8B","CLIP ViT-L/14","2024/06/09",7.0],[142,"LLaVA-v1.5-13B",13.4,"Vicuna-v1.5-13B","CLIP ViT-L/14","2023/10/05",6.8],[143,"Slime-8B",8.0,"Llama-3-8B-Instruct","CLIP ViT-L/14","2024/09/14",6.8],[144,"SmolVLM-500M",0.51,"SmolLM2-360M","ViT-93M","2025/01/27",6.5],[145,"LLaVA-Next-Interleave-7B-DPO",8.0,"Qwen-1.5-7B","SigLIP-400M","2024/07/29",6.4],[146,"Janus-1.3B",2.1,"DeepSeek-1B","SigLIP-400M","2024/10/24",6.3],[147,"LLaVA-Next-Interleave-7B",8.0,"Qwen-1.5-7B","SigLIP-400M","2024/08/08",6.0],[148,"LLaVA-v1.5-7B",7.2,"Vicuna-v1.5-7B","CLIP ViT-L/14","2023/10/05",6.0],[149,"Emu3_chat",8.49,"","","2025/01/26",5.7],[150,"Mantis-8B-Fuyu",8.0,"Fuyu-8B","","2024/09/07",5.3],[151,"SmolVLM2-256M",0.26,"SmolLM2-135M","ViT-93M","2025/03/13",4.9],[152,"Mantis-8B-siglip-llama3",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/08/08",4.6],[153,"SmolVLM-256M",0.26,"SmolLM2-135M","ViT-93M","2025/01/27",4.2],[154,"Mantis-8B-clip-llama3",8.0,"Llama-3-8B-Instruct","CLIP ViT-L/14","2024/08/08",3.5],[155,"AKI-4B",4.33,"Phi-3.5","SigLIP-400M","2025/03/25",2.3],[156,"Kosmos2",1.7,"","","2024/10/19",2.0],[157,"Moondream1",1.9,"SigLIP-400M","Phi-1.5","2024/09/26",1.4]],"metadata":null},"headers":["1","2","3"],"row_count":[1,"dynamic"],"col_count":[3,"dynamic"],"datatype":["number","html","number","html","html","str","number"],"type":"pandas","latex_delimiters":[{"left":"$$","right":"$$","display":true}],"show_label":true,"height":500,"min_width":160,"interactive":false,"visible":true,"elem_classes":[],"wrap":true,"line_breaks":true,"column_widths":[],"name":"dataframe","_selectable":false},"skip_api":false,"component_class_id":"6a51bb3357f2e94c40fb8d4fbe06aa8e","key":null,"api_info":{"properties":{"headers":{"items":{"type":"string"},"title":"Headers","type":"array"},"data":{"items":{"items":{},"type":"array"},"title":"Data","type":"array"},"metadata":{"anyOf":[{"additionalProperties":{"anyOf":[{"items":{},"type":"array"},{"type":"null"}]},"type":"object"},{"type":"null"}],"default":null,"title":"Metadata"}},"required":["headers","data"],"title":"DataframeData","type":"object"},"example_inputs":{"headers":["a","b"],"data":[["foo","bar"]]}},{"id":365,"type":"textbox","props":{"value":"MTVQA","lines":1,"max_lines":20,"label":"MTVQA","show_label":true,"container":true,"min_width":160,"visible":false,"autofocus":false,"autoscroll":true,"elem_classes":[],"type":"text","rtl":false,"show_copy_button":false,"name":"textbox","_selectable":false},"skip_api":false,"component_class_id":"d0491bb0fbd427bdb2a4549c4d1ac869","key":null,"api_info":{"type":"string"},"example_inputs":"Hello!!"},{"id":366,"type":"form","props":{"scale":0,"min_width":0,"name":"form"},"skip_api":true,"component_class_id":"43cda85c6ff7a5dd8f83d29496b014ee","key":null},{"id":367,"type":"form","props":{"scale":0,"min_width":0,"name":"form"},"skip_api":true,"component_class_id":"43cda85c6ff7a5dd8f83d29496b014ee","key":null},{"id":368,"type":"tabitem","props":{"label":"📊 VCR Leaderboard","visible":true,"interactive":true,"id":32,"elem_id":"VCR","name":"tab"},"skip_api":true,"component_class_id":"18f46968e2b273dc5dbda0fe78433d7e","key":null},{"id":369,"type":"markdown","props":{"value":"## VCR Evaluation Results\n\n- VCR challenges models to restore partially obscured text within images, leveraging pixel-level hints and contextual cues. Unlike traditional text-based tasks, VCR necessitates a synergistic understanding of visual image (VI), string text (ST), and text embedded in image (TEI). Our dataset is crafted using a pipeline that generates synthetic images from image-caption pairs with adjustable caption visibility, allowing for varied difficulty levels. \n- We report the Jaccard / Exact Match score for VCR, evaluated on the 500 samples subsets of each track in VCR with VLMEvalKit.\n- The evaluation results are officially provided by the VCR authors, thanks Tianyu Zhang for his help.","show_label":true,"rtl":false,"latex_delimiters":[{"left":"$$","right":"$$","display":true}],"visible":true,"elem_classes":[],"sanitize_html":true,"line_breaks":false,"header_links":false,"show_copy_button":false,"name":"markdown","_selectable":false},"skip_api":false,"component_class_id":"0f35515b9a3362b42bb6721c836157a0","key":null,"api_info":{"type":"string"},"example_inputs":"# Hello!"},{"id":370,"type":"checkboxgroup","props":{"choices":[["Overall-Jaccard","Overall-Jaccard"],["Overall-EM","Overall-EM"],["EN_EASY-Jaccard","EN_EASY-Jaccard"],["EN_EASY-EM","EN_EASY-EM"],["EN_HARD-Jaccard","EN_HARD-Jaccard"],["EN_HARD-EM","EN_HARD-EM"],["ZH_EASY-Jaccard","ZH_EASY-Jaccard"],["ZH_EASY-EM","ZH_EASY-EM"],["ZH_HARD-Jaccard","ZH_HARD-Jaccard"],["ZH_HARD-EM","ZH_HARD-EM"]],"value":["Overall-Jaccard","Overall-EM"],"type":"value","label":"VCR CheckBoxes","show_label":true,"container":true,"min_width":160,"interactive":true,"visible":true,"elem_classes":[],"name":"checkboxgroup","_selectable":false},"skip_api":false,"component_class_id":"0635a5d3bf87369f1c2c1c69f8a3d0cc","key":null,"api_info":{"items":{"enum":["Overall-Jaccard","Overall-EM","EN_EASY-Jaccard","EN_EASY-EM","EN_HARD-Jaccard","EN_HARD-EM","ZH_EASY-Jaccard","ZH_EASY-EM","ZH_HARD-Jaccard","ZH_HARD-EM"],"type":"string"},"title":"Checkbox Group","type":"array"},"example_inputs":["Overall-Jaccard"]},{"id":371,"type":"row","props":{"variant":"default","visible":true,"equal_height":true,"show_progress":false,"name":"row"},"skip_api":true,"component_class_id":"b5cf3d15e2293fb5ccc071d7b8d69f64","key":null},{"id":372,"type":"textbox","props":{"value":"Input the Model Name (fuzzy, case insensitive)","lines":1,"max_lines":20,"label":"Model Name","show_label":true,"container":true,"min_width":160,"interactive":true,"visible":true,"autofocus":false,"autoscroll":true,"elem_classes":[],"type":"text","rtl":false,"show_copy_button":false,"name":"textbox","_selectable":false},"skip_api":false,"component_class_id":"d0491bb0fbd427bdb2a4549c4d1ac869","key":null,"api_info":{"type":"string"},"example_inputs":"Hello!!"},{"id":373,"type":"checkboxgroup","props":{"choices":[["<4B","<4B"],["4B-10B","4B-10B"],["10B-20B","10B-20B"],["20B-40B","20B-40B"],[">40B",">40B"],["Unknown","Unknown"]],"value":["<4B","4B-10B","10B-20B","20B-40B",">40B","Unknown"],"type":"value","label":"Model Size","show_label":true,"container":true,"min_width":160,"interactive":true,"visible":true,"elem_classes":[],"name":"checkboxgroup","_selectable":false},"skip_api":false,"component_class_id":"0635a5d3bf87369f1c2c1c69f8a3d0cc","key":null,"api_info":{"items":{"enum":["<4B","4B-10B","10B-20B","20B-40B",">40B","Unknown"],"type":"string"},"title":"Checkbox Group","type":"array"},"example_inputs":["<4B"]},{"id":374,"type":"checkboxgroup","props":{"choices":[["API","API"],["OpenSource","OpenSource"]],"value":["API","OpenSource"],"type":"value","label":"Model Type","show_label":true,"container":true,"min_width":160,"interactive":true,"visible":true,"elem_classes":[],"name":"checkboxgroup","_selectable":false},"skip_api":false,"component_class_id":"0635a5d3bf87369f1c2c1c69f8a3d0cc","key":null,"api_info":{"items":{"enum":["API","OpenSource"],"type":"string"},"title":"Checkbox Group","type":"array"},"example_inputs":["API"]},{"id":375,"type":"form","props":{"scale":3,"min_width":480,"name":"form"},"skip_api":true,"component_class_id":"43cda85c6ff7a5dd8f83d29496b014ee","key":null},{"id":376,"type":"dataframe","props":{"value":{"headers":["Rank","Method","Param (B)","Language Model","Vision Model","Eval Date","Overall-Jaccard","Overall-EM"],"data":[[1,"Cambrian-13B",13.0,"Vicuna-v1.5-13B","CLIP ViT-L/14","2024/07/29",null,null],[2,"Cambrian-8B",8.0,"Vicuna-v1.5-7B","CLIP ViT-L/14","2024/07/11",null,null],[3,"Qwen-VL",9.6,"Qwen-7B","ViT-G/16","2023/08/24",null,null],[4,"Claude3-Opus",null,"","","2024/03/28",null,null],[5,"Phi-3-Vision",4.2,"Phi-3","CLIP ViT-L/14","2024/05/31",null,null],[6,"CogVLM2-19B-Chat",19.0,"Llama-3-8B-Instruct","EVA2-CLIP-E","2024/05/31",null,null],[7,"IDEFICS2-8B",8.0,"Mistral-7B","SigLIP-400M","2024/04/26",null,null],[8,"GPT-4v (0409, detail-low)",null,"","","2024/05/15",null,null],[9,"Qwen2-VL-7B",8.0,"Qwen2-7B","QwenViT","2024/09/12",75.6,61.5],[10,"Qwen2-VL-2B",2.0,"Qwen2-1.5B","QwenViT","2024/09/12",61.3,46.5],[11,"GPT-4o (0513, detail-low)",null,"","","2024/05/15",51.8,39.7],[12,"GLM-4v-9B",9.0,"GLM-4-9B","EVA-02-5B","2024/06/14",49.8,26.6],[13,"InternVL2-Llama3-76B",76.0,"Llama-3-70B-Instruct","InternViT-6B","2024/07/19",48.3,30.4],[14,"InternVL2-40B",40.0,"Nous-Hermes-2-Yi-34B","InternViT-6B","2024/07/11",47.5,30.5],[15,"GPT-4o-mini (0718, detail-high)",null,"","","2024/07/20",42.0,34.7],[16,"InternVL2-26B",26.0,"InternLM2-20B","InternViT-6B","2024/07/11",38.8,22.7],[17,"Gemini-1.5-Pro",null,"","","2024/06/10",38.1,23.2],[18,"Claude3.5-Sonnet",null,"","","2024/06/24",35.6,26.7],[19,"CogVLM-17B-Chat",17.0,"Vicuna-v1.5-7B","EVA2-CLIP-E","2024/01/03",35.3,26.6],[20,"Cambrian-34B",34.0,"Nous-Hermes-2-Yi-34B","CLIP ViT-L/14","2024/07/18",35.1,26.0],[21,"MiniCPM-V-2.6",8.0,"Qwen2-7B","SigLIP-400M","2024/08/08",33.7,21.9],[22,"InternVL2-2B",2.0,"InternLM2-1.8B","InternViT-300M","2024/07/11",29.0,11.4],[23,"InternVL2-8B",8.0,"InternLM2.5-7B","InternViT-300M","2024/07/11",28.6,12.0],[24,"InternVL2-1B",1.0,"Qwen2-0.5B","InternViT-300M","2024/07/11",26.1,7.7],[25,"InternLM-XComposer2",7.0,"InternLM2-7B","CLIP ViT-L/14","2024/01/26",26.0,11.8],[26,"InternVL-Chat-V1.5",26.0,"InternLM2-20B","InternViT-6B","2024/04/17",25.7,5.4],[27,"InternLM-XComposer2.5",8.0,"InternLM2-7B","CLIP ViT-L/14","2024/07/11",25.1,10.9],[28,"Ovis1.5-Gemma2-9B",11.4,"Gemma2-9B-It","SigLIP-400M","2024/08/04",24.6,10.9],[29,"Ovis1.5-Llama3-8B",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/07/29",24.2,13.8],[30,"Monkey-Chat",9.8,"Qwen-7B","ViT-BigHuge","2024/01/16",23.1,12.2],[31,"MiniCPM-Llama3-V2.5",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/05/27",22.4,9.8],[32,"InternVL2-4B",4.0,"Phi-3","InternViT-300M","2024/07/11",22.1,12.1],[33,"DeepSeek-VL-7B",7.3,"DeekSeek-7B","SAM-B
SigLIP-L","2024/03/21",21.2,9.6],[34,"Qwen-VL-Chat",9.6,"Qwen-7B","ViT-G/16","2023/08/24",21.1,11.8],[35,"LLaVA-Next-Llama3",8.0,"Llama-3-8B-Instruct","CLIP ViT-L/14","2024/07/29",19.7,6.3],[36,"360VL-70B",70.0,"Llama-3-70B-Instruct","CLIP ViT-L/14","2024/05/25",19.2,6.1],[37,"OmniLMM-12B",12.0,"Zephyr-7B-β","EVA-02-5B","2024/02/07",19.0,10.2],[38,"LLaVA-Next-Mistral-7B",7.6,"Mistral-7B","CLIP ViT-L/14","2024/03/25",18.3,9.2],[39,"Phi-3.5-Vision",4.0,"Phi-3.5","CLIP ViT-L/14","2024/08/28",18.1,9.3],[40,"LLaVA-Next-Vicuna-13B",13.4,"Vicuna-v1.5-13B","CLIP ViT-L/14","2024/03/25",18.1,8.1],[41,"DeepSeek-VL-1.3B",2.0,"DeekSeek-1B","SAM-B
SigLIP-L","2024/03/21",17.4,5.6],[42,"LLaVA-Next-Vicuna-7B",7.1,"Vicuna-v1.5-7B","CLIP ViT-L/14","2024/03/25",16.7,6.6],[43,"PaliGemma-3B-mix-448",3.0,"Gemma-2B","SigLIP-400M","2024/05/17",16.3,5.7],[44,"LLaVA-Next-Qwen-32B",33.0,"Qwen-1.5-32B","SigLIP-400M","2024/08/08",13.2,3.9],[45,"InternLM-XComposer2-4KHD",7.0,"InternLM2-7B","CLIP ViT-L/14","2024/06/09",12.9,1.4],[46,"LLaVA-Next-Interleave-7B",8.0,"Qwen-1.5-7B","SigLIP-400M","2024/08/08",12.4,2.4],[47,"LLaVA-Next-Interleave-7B-DPO",8.0,"Qwen-1.5-7B","SigLIP-400M","2024/07/29",11.8,1.8],[48,"LLaVA-v1.5-7B",7.2,"Vicuna-v1.5-7B","CLIP ViT-L/14","2023/10/05",10.4,1.3],[49,"MiniCPM-V",3.0,"MiniCPM-2.4B","SigLIP-400M","2024/02/07",6.4,0.1],[50,"Mantis-8B-Idefics2",8.0,"Mistral-7B","SigLIP-400M","2024/08/08",6.0,1.0],[51,"Mantis-8B-Fuyu",8.0,"Fuyu-8B","","2024/09/07",5.1,0.3],[52,"Mantis-8B-siglip-llama3",8.0,"Llama-3-8B-Instruct","SigLIP-400M","2024/08/08",4.8,0.3],[53,"Yi-VL-34B",34.6,"Yi-34B","CLIP ViT-H/14","2024/01/25",4.8,0.2],[54,"Yi-VL-6B",6.6,"Yi-6B","CLIP ViT-H/14","2024/01/25",4.7,0.3],[55,"Chameleon-7B",7.0,"","","2024/07/29",3.3,0.0],[56,"Chameleon-30B",30.0,"","","2024/07/29",0.3,0.0]],"metadata":null},"headers":["1","2","3"],"row_count":[1,"dynamic"],"col_count":[3,"dynamic"],"datatype":["number","html","number","html","html","str","number","number"],"type":"pandas","latex_delimiters":[{"left":"$$","right":"$$","display":true}],"show_label":true,"height":500,"min_width":160,"interactive":false,"visible":true,"elem_classes":[],"wrap":true,"line_breaks":true,"column_widths":[],"name":"dataframe","_selectable":false},"skip_api":false,"component_class_id":"6a51bb3357f2e94c40fb8d4fbe06aa8e","key":null,"api_info":{"properties":{"headers":{"items":{"type":"string"},"title":"Headers","type":"array"},"data":{"items":{"items":{},"type":"array"},"title":"Data","type":"array"},"metadata":{"anyOf":[{"additionalProperties":{"anyOf":[{"items":{},"type":"array"},{"type":"null"}]},"type":"object"},{"type":"null"}],"default":null,"title":"Metadata"}},"required":["headers","data"],"title":"DataframeData","type":"object"},"example_inputs":{"headers":["a","b"],"data":[["foo","bar"]]}},{"id":377,"type":"textbox","props":{"value":"VCR","lines":1,"max_lines":20,"label":"VCR","show_label":true,"container":true,"min_width":160,"visible":false,"autofocus":false,"autoscroll":true,"elem_classes":[],"type":"text","rtl":false,"show_copy_button":false,"name":"textbox","_selectable":false},"skip_api":false,"component_class_id":"d0491bb0fbd427bdb2a4549c4d1ac869","key":null,"api_info":{"type":"string"},"example_inputs":"Hello!!"},{"id":378,"type":"form","props":{"scale":0,"min_width":0,"name":"form"},"skip_api":true,"component_class_id":"43cda85c6ff7a5dd8f83d29496b014ee","key":null},{"id":379,"type":"form","props":{"scale":0,"min_width":0,"name":"form"},"skip_api":true,"component_class_id":"43cda85c6ff7a5dd8f83d29496b014ee","key":null},{"id":380,"type":"row","props":{"variant":"default","visible":true,"equal_height":true,"show_progress":false,"name":"row"},"skip_api":true,"component_class_id":"b5cf3d15e2293fb5ccc071d7b8d69f64","key":null},{"id":381,"type":"accordion","props":{"label":"Citation","open":false,"visible":true,"name":"accordion"},"skip_api":true,"component_class_id":"b49c1903c3591b866d0adab5a2f6e48b","key":null},{"id":382,"type":"textbox","props":{"value":"@inproceedings{duan2024vlmevalkit,\n title={Vlmevalkit: An open-source toolkit for evaluating large multi-modality models},\n author={Duan, Haodong and Yang, Junming and Qiao, Yuxuan and Fang, Xinyu and Chen, Lin and Liu, Yuan and Dong, Xiaoyi and Zang, Yuhang and Zhang, Pan and Wang, Jiaqi and others},\n booktitle={Proceedings of the 32nd ACM International Conference on Multimedia},\n pages={11198--11201},\n year={2024}\n}","lines":1,"max_lines":20,"label":"Copy the following snippet to cite these results","show_label":true,"container":true,"min_width":160,"visible":true,"elem_id":"citation-button","autofocus":false,"autoscroll":true,"elem_classes":[],"type":"text","rtl":false,"show_copy_button":false,"name":"textbox","_selectable":false},"skip_api":false,"component_class_id":"d0491bb0fbd427bdb2a4549c4d1ac869","key":null,"api_info":{"type":"string"},"example_inputs":"Hello!!"},{"id":383,"type":"form","props":{"scale":0,"min_width":0,"name":"form"},"skip_api":true,"component_class_id":"43cda85c6ff7a5dd8f83d29496b014ee","key":null}],"css":null,"connect_heartbeat":false,"js":null,"head":"\n\n","title":"Open VLM Leaderboard","space_id":"opencompass/open_vlm_leaderboard","enable_queue":true,"show_error":false,"show_api":true,"is_colab":false,"max_file_size":null,"stylesheets":["https://fonts.googleapis.com/css2?family=Source+Sans+Pro:wght@400;600&display=swap","https://fonts.googleapis.com/css2?family=IBM+Plex+Mono:wght@400;600&display=swap"],"theme":"default","protocol":"sse_v3","body_css":{"body_background_fill":"white","body_text_color":"#1f2937","body_background_fill_dark":"#0b0f19","body_text_color_dark":"#f3f4f6"},"fill_height":false,"fill_width":false,"theme_hash":"aa3cf5a76ff4ff3d05b407358c4a85aa7a55a3f5751b53d49cba0b8d49a6c148","layout":{"id":0,"children":[{"id":1},{"id":2,"children":[{"id":3,"children":[{"id":4},{"id":12,"children":[{"id":5}]},{"id":6,"children":[{"id":10,"children":[{"id":7},{"id":8},{"id":9}]}]},{"id":11}]},{"id":13,"children":[{"id":14}]},{"id":15,"children":[{"id":16},{"id":25,"children":[{"id":17}]},{"id":18,"children":[{"id":22,"children":[{"id":19},{"id":20},{"id":21}]}]},{"id":23},{"id":26,"children":[{"id":24}]}]},{"id":27,"children":[{"id":28},{"id":37,"children":[{"id":29}]},{"id":30,"children":[{"id":34,"children":[{"id":31},{"id":32},{"id":33}]}]},{"id":35},{"id":38,"children":[{"id":36}]}]},{"id":39,"children":[{"id":40},{"id":49,"children":[{"id":41}]},{"id":42,"children":[{"id":46,"children":[{"id":43},{"id":44},{"id":45}]}]},{"id":47},{"id":50,"children":[{"id":48}]}]},{"id":51,"children":[{"id":52},{"id":61,"children":[{"id":53}]},{"id":54,"children":[{"id":58,"children":[{"id":55},{"id":56},{"id":57}]}]},{"id":59},{"id":62,"children":[{"id":60}]}]},{"id":63,"children":[{"id":72,"children":[{"id":64}]},{"id":65,"children":[{"id":69,"children":[{"id":66},{"id":67},{"id":68}]}]},{"id":70},{"id":73,"children":[{"id":71}]}]},{"id":74,"children":[{"id":83,"children":[{"id":75}]},{"id":76,"children":[{"id":80,"children":[{"id":77},{"id":78},{"id":79}]}]},{"id":81},{"id":84,"children":[{"id":82}]}]},{"id":85,"children":[{"id":94,"children":[{"id":86}]},{"id":87,"children":[{"id":91,"children":[{"id":88},{"id":89},{"id":90}]}]},{"id":92},{"id":95,"children":[{"id":93}]}]},{"id":96,"children":[{"id":97},{"id":106,"children":[{"id":98}]},{"id":99,"children":[{"id":103,"children":[{"id":100},{"id":101},{"id":102}]}]},{"id":104},{"id":107,"children":[{"id":105}]}]},{"id":108,"children":[{"id":109},{"id":118,"children":[{"id":110}]},{"id":111,"children":[{"id":115,"children":[{"id":112},{"id":113},{"id":114}]}]},{"id":116},{"id":119,"children":[{"id":117}]}]},{"id":120,"children":[{"id":121},{"id":130,"children":[{"id":122}]},{"id":123,"children":[{"id":127,"children":[{"id":124},{"id":125},{"id":126}]}]},{"id":128},{"id":131,"children":[{"id":129}]}]},{"id":132,"children":[{"id":133},{"id":142,"children":[{"id":134}]},{"id":135,"children":[{"id":139,"children":[{"id":136},{"id":137},{"id":138}]}]},{"id":140},{"id":143,"children":[{"id":141}]}]},{"id":144,"children":[{"id":145},{"id":154,"children":[{"id":146}]},{"id":147,"children":[{"id":151,"children":[{"id":148},{"id":149},{"id":150}]}]},{"id":152},{"id":155,"children":[{"id":153}]}]},{"id":156,"children":[{"id":165,"children":[{"id":157}]},{"id":158,"children":[{"id":162,"children":[{"id":159},{"id":160},{"id":161}]}]},{"id":163},{"id":166,"children":[{"id":164}]}]},{"id":167,"children":[{"id":168},{"id":177,"children":[{"id":169}]},{"id":170,"children":[{"id":174,"children":[{"id":171},{"id":172},{"id":173}]}]},{"id":175},{"id":178,"children":[{"id":176}]}]},{"id":179,"children":[{"id":180},{"id":189,"children":[{"id":181}]},{"id":182,"children":[{"id":186,"children":[{"id":183},{"id":184},{"id":185}]}]},{"id":187},{"id":190,"children":[{"id":188}]}]},{"id":191,"children":[{"id":192},{"id":201,"children":[{"id":193}]},{"id":194,"children":[{"id":198,"children":[{"id":195},{"id":196},{"id":197}]}]},{"id":199},{"id":202,"children":[{"id":200}]}]},{"id":203,"children":[{"id":204},{"id":213,"children":[{"id":205}]},{"id":206,"children":[{"id":210,"children":[{"id":207},{"id":208},{"id":209}]}]},{"id":211},{"id":214,"children":[{"id":212}]}]},{"id":215,"children":[{"id":216},{"id":225,"children":[{"id":217}]},{"id":218,"children":[{"id":222,"children":[{"id":219},{"id":220},{"id":221}]}]},{"id":223},{"id":226,"children":[{"id":224}]}]},{"id":227,"children":[{"id":228},{"id":237,"children":[{"id":229}]},{"id":230,"children":[{"id":234,"children":[{"id":231},{"id":232},{"id":233}]}]},{"id":235},{"id":238,"children":[{"id":236}]}]},{"id":239,"children":[{"id":240},{"id":249,"children":[{"id":241}]},{"id":242,"children":[{"id":246,"children":[{"id":243},{"id":244},{"id":245}]}]},{"id":247},{"id":250,"children":[{"id":248}]}]},{"id":251,"children":[{"id":252},{"id":261,"children":[{"id":253}]},{"id":254,"children":[{"id":258,"children":[{"id":255},{"id":256},{"id":257}]}]},{"id":259},{"id":262,"children":[{"id":260}]}]},{"id":263,"children":[{"id":264},{"id":273,"children":[{"id":265}]},{"id":266,"children":[{"id":270,"children":[{"id":267},{"id":268},{"id":269}]}]},{"id":271},{"id":274,"children":[{"id":272}]}]},{"id":275,"children":[{"id":276},{"id":285,"children":[{"id":277}]},{"id":278,"children":[{"id":282,"children":[{"id":279},{"id":280},{"id":281}]}]},{"id":283},{"id":286,"children":[{"id":284}]}]},{"id":287,"children":[{"id":288},{"id":297,"children":[{"id":289}]},{"id":290,"children":[{"id":294,"children":[{"id":291},{"id":292},{"id":293}]}]},{"id":295},{"id":298,"children":[{"id":296}]}]},{"id":299,"children":[{"id":300},{"id":309,"children":[{"id":301}]},{"id":302,"children":[{"id":306,"children":[{"id":303},{"id":304},{"id":305}]}]},{"id":307},{"id":310,"children":[{"id":308}]}]},{"id":311,"children":[{"id":312},{"id":321,"children":[{"id":313}]},{"id":314,"children":[{"id":318,"children":[{"id":315},{"id":316},{"id":317}]}]},{"id":319},{"id":322,"children":[{"id":320}]}]},{"id":323,"children":[{"id":324},{"id":333,"children":[{"id":325}]},{"id":326,"children":[{"id":330,"children":[{"id":327},{"id":328},{"id":329}]}]},{"id":331},{"id":334,"children":[{"id":332}]}]},{"id":335,"children":[{"id":344,"children":[{"id":336}]},{"id":337,"children":[{"id":341,"children":[{"id":338},{"id":339},{"id":340}]}]},{"id":342},{"id":345,"children":[{"id":343}]}]},{"id":346,"children":[{"id":355,"children":[{"id":347}]},{"id":348,"children":[{"id":352,"children":[{"id":349},{"id":350},{"id":351}]}]},{"id":353},{"id":356,"children":[{"id":354}]}]},{"id":357,"children":[{"id":366,"children":[{"id":358}]},{"id":359,"children":[{"id":363,"children":[{"id":360},{"id":361},{"id":362}]}]},{"id":364},{"id":367,"children":[{"id":365}]}]},{"id":368,"children":[{"id":369},{"id":378,"children":[{"id":370}]},{"id":371,"children":[{"id":375,"children":[{"id":372},{"id":373},{"id":374}]}]},{"id":376},{"id":379,"children":[{"id":377}]}]}]},{"id":380,"children":[{"id":381,"children":[{"id":383,"children":[{"id":382}]}]}]}]},"dependencies":[{"id":0,"targets":[[5,"change"]],"inputs":[5,7,8,9],"outputs":[11],"backend_fn":true,"js":null,"queue":true,"api_name":"filter_df","scroll_to_output":false,"show_progress":"full","batch":false,"max_batch_size":4,"cancels":[],"types":{"generator":false,"cancel":false},"collects_event_data":false,"trigger_after":null,"trigger_only_on_success":false,"trigger_mode":"always_last","show_api":true,"zerogpu":false,"rendered_in":null},{"id":1,"targets":[[8,"change"]],"inputs":[5,7,8,9],"outputs":[11],"backend_fn":true,"js":null,"queue":true,"api_name":"filter_df_1","scroll_to_output":false,"show_progress":"full","batch":false,"max_batch_size":4,"cancels":[],"types":{"generator":false,"cancel":false},"collects_event_data":false,"trigger_after":null,"trigger_only_on_success":false,"trigger_mode":"always_last","show_api":true,"zerogpu":false,"rendered_in":null},{"id":2,"targets":[[9,"change"]],"inputs":[5,7,8,9],"outputs":[11],"backend_fn":true,"js":null,"queue":true,"api_name":"filter_df_2","scroll_to_output":false,"show_progress":"full","batch":false,"max_batch_size":4,"cancels":[],"types":{"generator":false,"cancel":false},"collects_event_data":false,"trigger_after":null,"trigger_only_on_success":false,"trigger_mode":"always_last","show_api":true,"zerogpu":false,"rendered_in":null},{"id":3,"targets":[[7,"submit"]],"inputs":[5,7,8,9],"outputs":[11],"backend_fn":true,"js":null,"queue":true,"api_name":"filter_df_3","scroll_to_output":false,"show_progress":"full","batch":false,"max_batch_size":4,"cancels":[],"types":{"generator":false,"cancel":false},"collects_event_data":false,"trigger_after":null,"trigger_only_on_success":false,"trigger_mode":"once","show_api":true,"zerogpu":false,"rendered_in":null},{"id":4,"targets":[[17,"change"]],"inputs":[24,17,19,20,21],"outputs":[23],"backend_fn":true,"js":null,"queue":true,"api_name":"filter_df_l2","scroll_to_output":false,"show_progress":"full","batch":false,"max_batch_size":4,"cancels":[],"types":{"generator":false,"cancel":false},"collects_event_data":false,"trigger_after":null,"trigger_only_on_success":false,"trigger_mode":"always_last","show_api":true,"zerogpu":false,"rendered_in":null},{"id":5,"targets":[[20,"change"]],"inputs":[24,17,19,20,21],"outputs":[23],"backend_fn":true,"js":null,"queue":true,"api_name":"filter_df_l2_1","scroll_to_output":false,"show_progress":"full","batch":false,"max_batch_size":4,"cancels":[],"types":{"generator":false,"cancel":false},"collects_event_data":false,"trigger_after":null,"trigger_only_on_success":false,"trigger_mode":"always_last","show_api":true,"zerogpu":false,"rendered_in":null},{"id":6,"targets":[[21,"change"]],"inputs":[24,17,19,20,21],"outputs":[23],"backend_fn":true,"js":null,"queue":true,"api_name":"filter_df_l2_2","scroll_to_output":false,"show_progress":"full","batch":false,"max_batch_size":4,"cancels":[],"types":{"generator":false,"cancel":false},"collects_event_data":false,"trigger_after":null,"trigger_only_on_success":false,"trigger_mode":"always_last","show_api":true,"zerogpu":false,"rendered_in":null},{"id":7,"targets":[[19,"submit"]],"inputs":[24,17,19,20,21],"outputs":[23],"backend_fn":true,"js":null,"queue":true,"api_name":"filter_df_l2_3","scroll_to_output":false,"show_progress":"full","batch":false,"max_batch_size":4,"cancels":[],"types":{"generator":false,"cancel":false},"collects_event_data":false,"trigger_after":null,"trigger_only_on_success":false,"trigger_mode":"once","show_api":true,"zerogpu":false,"rendered_in":null},{"id":8,"targets":[[29,"change"]],"inputs":[36,29,31,32,33],"outputs":[35],"backend_fn":true,"js":null,"queue":true,"api_name":"filter_df_l2_4","scroll_to_output":false,"show_progress":"full","batch":false,"max_batch_size":4,"cancels":[],"types":{"generator":false,"cancel":false},"collects_event_data":false,"trigger_after":null,"trigger_only_on_success":false,"trigger_mode":"always_last","show_api":true,"zerogpu":false,"rendered_in":null},{"id":9,"targets":[[32,"change"]],"inputs":[36,29,31,32,33],"outputs":[35],"backend_fn":true,"js":null,"queue":true,"api_name":"filter_df_l2_5","scroll_to_output":false,"show_progress":"full","batch":false,"max_batch_size":4,"cancels":[],"types":{"generator":false,"cancel":false},"collects_event_data":false,"trigger_after":null,"trigger_only_on_success":false,"trigger_mode":"always_last","show_api":true,"zerogpu":false,"rendered_in":null},{"id":10,"targets":[[33,"change"]],"inputs":[36,29,31,32,33],"outputs":[35],"backend_fn":true,"js":null,"queue":true,"api_name":"filter_df_l2_6","scroll_to_output":false,"show_progress":"full","batch":false,"max_batch_size":4,"cancels":[],"types":{"generator":false,"cancel":false},"collects_event_data":false,"trigger_after":null,"trigger_only_on_success":false,"trigger_mode":"always_last","show_api":true,"zerogpu":false,"rendered_in":null},{"id":11,"targets":[[31,"submit"]],"inputs":[36,29,31,32,33],"outputs":[35],"backend_fn":true,"js":null,"queue":true,"api_name":"filter_df_l2_7","scroll_to_output":false,"show_progress":"full","batch":false,"max_batch_size":4,"cancels":[],"types":{"generator":false,"cancel":false},"collects_event_data":false,"trigger_after":null,"trigger_only_on_success":false,"trigger_mode":"once","show_api":true,"zerogpu":false,"rendered_in":null},{"id":12,"targets":[[41,"change"]],"inputs":[48,41,43,44,45],"outputs":[47],"backend_fn":true,"js":null,"queue":true,"api_name":"filter_df_l2_8","scroll_to_output":false,"show_progress":"full","batch":false,"max_batch_size":4,"cancels":[],"types":{"generator":false,"cancel":false},"collects_event_data":false,"trigger_after":null,"trigger_only_on_success":false,"trigger_mode":"always_last","show_api":true,"zerogpu":false,"rendered_in":null},{"id":13,"targets":[[44,"change"]],"inputs":[48,41,43,44,45],"outputs":[47],"backend_fn":true,"js":null,"queue":true,"api_name":"filter_df_l2_9","scroll_to_output":false,"show_progress":"full","batch":false,"max_batch_size":4,"cancels":[],"types":{"generator":false,"cancel":false},"collects_event_data":false,"trigger_after":null,"trigger_only_on_success":false,"trigger_mode":"always_last","show_api":true,"zerogpu":false,"rendered_in":null},{"id":14,"targets":[[45,"change"]],"inputs":[48,41,43,44,45],"outputs":[47],"backend_fn":true,"js":null,"queue":true,"api_name":"filter_df_l2_10","scroll_to_output":false,"show_progress":"full","batch":false,"max_batch_size":4,"cancels":[],"types":{"generator":false,"cancel":false},"collects_event_data":false,"trigger_after":null,"trigger_only_on_success":false,"trigger_mode":"always_last","show_api":true,"zerogpu":false,"rendered_in":null},{"id":15,"targets":[[43,"submit"]],"inputs":[48,41,43,44,45],"outputs":[47],"backend_fn":true,"js":null,"queue":true,"api_name":"filter_df_l2_11","scroll_to_output":false,"show_progress":"full","batch":false,"max_batch_size":4,"cancels":[],"types":{"generator":false,"cancel":false},"collects_event_data":false,"trigger_after":null,"trigger_only_on_success":false,"trigger_mode":"once","show_api":true,"zerogpu":false,"rendered_in":null},{"id":16,"targets":[[53,"change"]],"inputs":[60,53,55,56,57],"outputs":[59],"backend_fn":true,"js":null,"queue":true,"api_name":"filter_df_l2_12","scroll_to_output":false,"show_progress":"full","batch":false,"max_batch_size":4,"cancels":[],"types":{"generator":false,"cancel":false},"collects_event_data":false,"trigger_after":null,"trigger_only_on_success":false,"trigger_mode":"always_last","show_api":true,"zerogpu":false,"rendered_in":null},{"id":17,"targets":[[56,"change"]],"inputs":[60,53,55,56,57],"outputs":[59],"backend_fn":true,"js":null,"queue":true,"api_name":"filter_df_l2_13","scroll_to_output":false,"show_progress":"full","batch":false,"max_batch_size":4,"cancels":[],"types":{"generator":false,"cancel":false},"collects_event_data":false,"trigger_after":null,"trigger_only_on_success":false,"trigger_mode":"always_last","show_api":true,"zerogpu":false,"rendered_in":null},{"id":18,"targets":[[57,"change"]],"inputs":[60,53,55,56,57],"outputs":[59],"backend_fn":true,"js":null,"queue":true,"api_name":"filter_df_l2_14","scroll_to_output":false,"show_progress":"full","batch":false,"max_batch_size":4,"cancels":[],"types":{"generator":false,"cancel":false},"collects_event_data":false,"trigger_after":null,"trigger_only_on_success":false,"trigger_mode":"always_last","show_api":true,"zerogpu":false,"rendered_in":null},{"id":19,"targets":[[55,"submit"]],"inputs":[60,53,55,56,57],"outputs":[59],"backend_fn":true,"js":null,"queue":true,"api_name":"filter_df_l2_15","scroll_to_output":false,"show_progress":"full","batch":false,"max_batch_size":4,"cancels":[],"types":{"generator":false,"cancel":false},"collects_event_data":false,"trigger_after":null,"trigger_only_on_success":false,"trigger_mode":"once","show_api":true,"zerogpu":false,"rendered_in":null},{"id":20,"targets":[[64,"change"]],"inputs":[71,64,66,67,68],"outputs":[70],"backend_fn":true,"js":null,"queue":true,"api_name":"filter_df_l2_16","scroll_to_output":false,"show_progress":"full","batch":false,"max_batch_size":4,"cancels":[],"types":{"generator":false,"cancel":false},"collects_event_data":false,"trigger_after":null,"trigger_only_on_success":false,"trigger_mode":"always_last","show_api":true,"zerogpu":false,"rendered_in":null},{"id":21,"targets":[[67,"change"]],"inputs":[71,64,66,67,68],"outputs":[70],"backend_fn":true,"js":null,"queue":true,"api_name":"filter_df_l2_17","scroll_to_output":false,"show_progress":"full","batch":false,"max_batch_size":4,"cancels":[],"types":{"generator":false,"cancel":false},"collects_event_data":false,"trigger_after":null,"trigger_only_on_success":false,"trigger_mode":"always_last","show_api":true,"zerogpu":false,"rendered_in":null},{"id":22,"targets":[[68,"change"]],"inputs":[71,64,66,67,68],"outputs":[70],"backend_fn":true,"js":null,"queue":true,"api_name":"filter_df_l2_18","scroll_to_output":false,"show_progress":"full","batch":false,"max_batch_size":4,"cancels":[],"types":{"generator":false,"cancel":false},"collects_event_data":false,"trigger_after":null,"trigger_only_on_success":false,"trigger_mode":"always_last","show_api":true,"zerogpu":false,"rendered_in":null},{"id":23,"targets":[[66,"submit"]],"inputs":[71,64,66,67,68],"outputs":[70],"backend_fn":true,"js":null,"queue":true,"api_name":"filter_df_l2_19","scroll_to_output":false,"show_progress":"full","batch":false,"max_batch_size":4,"cancels":[],"types":{"generator":false,"cancel":false},"collects_event_data":false,"trigger_after":null,"trigger_only_on_success":false,"trigger_mode":"once","show_api":true,"zerogpu":false,"rendered_in":null},{"id":24,"targets":[[75,"change"]],"inputs":[82,75,77,78,79],"outputs":[81],"backend_fn":true,"js":null,"queue":true,"api_name":"filter_df_l2_20","scroll_to_output":false,"show_progress":"full","batch":false,"max_batch_size":4,"cancels":[],"types":{"generator":false,"cancel":false},"collects_event_data":false,"trigger_after":null,"trigger_only_on_success":false,"trigger_mode":"always_last","show_api":true,"zerogpu":false,"rendered_in":null},{"id":25,"targets":[[78,"change"]],"inputs":[82,75,77,78,79],"outputs":[81],"backend_fn":true,"js":null,"queue":true,"api_name":"filter_df_l2_21","scroll_to_output":false,"show_progress":"full","batch":false,"max_batch_size":4,"cancels":[],"types":{"generator":false,"cancel":false},"collects_event_data":false,"trigger_after":null,"trigger_only_on_success":false,"trigger_mode":"always_last","show_api":true,"zerogpu":false,"rendered_in":null},{"id":26,"targets":[[79,"change"]],"inputs":[82,75,77,78,79],"outputs":[81],"backend_fn":true,"js":null,"queue":true,"api_name":"filter_df_l2_22","scroll_to_output":false,"show_progress":"full","batch":false,"max_batch_size":4,"cancels":[],"types":{"generator":false,"cancel":false},"collects_event_data":false,"trigger_after":null,"trigger_only_on_success":false,"trigger_mode":"always_last","show_api":true,"zerogpu":false,"rendered_in":null},{"id":27,"targets":[[77,"submit"]],"inputs":[82,75,77,78,79],"outputs":[81],"backend_fn":true,"js":null,"queue":true,"api_name":"filter_df_l2_23","scroll_to_output":false,"show_progress":"full","batch":false,"max_batch_size":4,"cancels":[],"types":{"generator":false,"cancel":false},"collects_event_data":false,"trigger_after":null,"trigger_only_on_success":false,"trigger_mode":"once","show_api":true,"zerogpu":false,"rendered_in":null},{"id":28,"targets":[[86,"change"]],"inputs":[93,86,88,89,90],"outputs":[92],"backend_fn":true,"js":null,"queue":true,"api_name":"filter_df_l2_24","scroll_to_output":false,"show_progress":"full","batch":false,"max_batch_size":4,"cancels":[],"types":{"generator":false,"cancel":false},"collects_event_data":false,"trigger_after":null,"trigger_only_on_success":false,"trigger_mode":"always_last","show_api":true,"zerogpu":false,"rendered_in":null},{"id":29,"targets":[[89,"change"]],"inputs":[93,86,88,89,90],"outputs":[92],"backend_fn":true,"js":null,"queue":true,"api_name":"filter_df_l2_25","scroll_to_output":false,"show_progress":"full","batch":false,"max_batch_size":4,"cancels":[],"types":{"generator":false,"cancel":false},"collects_event_data":false,"trigger_after":null,"trigger_only_on_success":false,"trigger_mode":"always_last","show_api":true,"zerogpu":false,"rendered_in":null},{"id":30,"targets":[[90,"change"]],"inputs":[93,86,88,89,90],"outputs":[92],"backend_fn":true,"js":null,"queue":true,"api_name":"filter_df_l2_26","scroll_to_output":false,"show_progress":"full","batch":false,"max_batch_size":4,"cancels":[],"types":{"generator":false,"cancel":false},"collects_event_data":false,"trigger_after":null,"trigger_only_on_success":false,"trigger_mode":"always_last","show_api":true,"zerogpu":false,"rendered_in":null},{"id":31,"targets":[[88,"submit"]],"inputs":[93,86,88,89,90],"outputs":[92],"backend_fn":true,"js":null,"queue":true,"api_name":"filter_df_l2_27","scroll_to_output":false,"show_progress":"full","batch":false,"max_batch_size":4,"cancels":[],"types":{"generator":false,"cancel":false},"collects_event_data":false,"trigger_after":null,"trigger_only_on_success":false,"trigger_mode":"once","show_api":true,"zerogpu":false,"rendered_in":null},{"id":32,"targets":[[98,"change"]],"inputs":[105,98,100,101,102],"outputs":[104],"backend_fn":true,"js":null,"queue":true,"api_name":"filter_df_l2_28","scroll_to_output":false,"show_progress":"full","batch":false,"max_batch_size":4,"cancels":[],"types":{"generator":false,"cancel":false},"collects_event_data":false,"trigger_after":null,"trigger_only_on_success":false,"trigger_mode":"always_last","show_api":true,"zerogpu":false,"rendered_in":null},{"id":33,"targets":[[101,"change"]],"inputs":[105,98,100,101,102],"outputs":[104],"backend_fn":true,"js":null,"queue":true,"api_name":"filter_df_l2_29","scroll_to_output":false,"show_progress":"full","batch":false,"max_batch_size":4,"cancels":[],"types":{"generator":false,"cancel":false},"collects_event_data":false,"trigger_after":null,"trigger_only_on_success":false,"trigger_mode":"always_last","show_api":true,"zerogpu":false,"rendered_in":null},{"id":34,"targets":[[102,"change"]],"inputs":[105,98,100,101,102],"outputs":[104],"backend_fn":true,"js":null,"queue":true,"api_name":"filter_df_l2_30","scroll_to_output":false,"show_progress":"full","batch":false,"max_batch_size":4,"cancels":[],"types":{"generator":false,"cancel":false},"collects_event_data":false,"trigger_after":null,"trigger_only_on_success":false,"trigger_mode":"always_last","show_api":true,"zerogpu":false,"rendered_in":null},{"id":35,"targets":[[100,"submit"]],"inputs":[105,98,100,101,102],"outputs":[104],"backend_fn":true,"js":null,"queue":true,"api_name":"filter_df_l2_31","scroll_to_output":false,"show_progress":"full","batch":false,"max_batch_size":4,"cancels":[],"types":{"generator":false,"cancel":false},"collects_event_data":false,"trigger_after":null,"trigger_only_on_success":false,"trigger_mode":"once","show_api":true,"zerogpu":false,"rendered_in":null},{"id":36,"targets":[[110,"change"]],"inputs":[117,110,112,113,114],"outputs":[116],"backend_fn":true,"js":null,"queue":true,"api_name":"filter_df_l2_32","scroll_to_output":false,"show_progress":"full","batch":false,"max_batch_size":4,"cancels":[],"types":{"generator":false,"cancel":false},"collects_event_data":false,"trigger_after":null,"trigger_only_on_success":false,"trigger_mode":"always_last","show_api":true,"zerogpu":false,"rendered_in":null},{"id":37,"targets":[[113,"change"]],"inputs":[117,110,112,113,114],"outputs":[116],"backend_fn":true,"js":null,"queue":true,"api_name":"filter_df_l2_33","scroll_to_output":false,"show_progress":"full","batch":false,"max_batch_size":4,"cancels":[],"types":{"generator":false,"cancel":false},"collects_event_data":false,"trigger_after":null,"trigger_only_on_success":false,"trigger_mode":"always_last","show_api":true,"zerogpu":false,"rendered_in":null},{"id":38,"targets":[[114,"change"]],"inputs":[117,110,112,113,114],"outputs":[116],"backend_fn":true,"js":null,"queue":true,"api_name":"filter_df_l2_34","scroll_to_output":false,"show_progress":"full","batch":false,"max_batch_size":4,"cancels":[],"types":{"generator":false,"cancel":false},"collects_event_data":false,"trigger_after":null,"trigger_only_on_success":false,"trigger_mode":"always_last","show_api":true,"zerogpu":false,"rendered_in":null},{"id":39,"targets":[[112,"submit"]],"inputs":[117,110,112,113,114],"outputs":[116],"backend_fn":true,"js":null,"queue":true,"api_name":"filter_df_l2_35","scroll_to_output":false,"show_progress":"full","batch":false,"max_batch_size":4,"cancels":[],"types":{"generator":false,"cancel":false},"collects_event_data":false,"trigger_after":null,"trigger_only_on_success":false,"trigger_mode":"once","show_api":true,"zerogpu":false,"rendered_in":null},{"id":40,"targets":[[122,"change"]],"inputs":[129,122,124,125,126],"outputs":[128],"backend_fn":true,"js":null,"queue":true,"api_name":"filter_df_l2_36","scroll_to_output":false,"show_progress":"full","batch":false,"max_batch_size":4,"cancels":[],"types":{"generator":false,"cancel":false},"collects_event_data":false,"trigger_after":null,"trigger_only_on_success":false,"trigger_mode":"always_last","show_api":true,"zerogpu":false,"rendered_in":null},{"id":41,"targets":[[125,"change"]],"inputs":[129,122,124,125,126],"outputs":[128],"backend_fn":true,"js":null,"queue":true,"api_name":"filter_df_l2_37","scroll_to_output":false,"show_progress":"full","batch":false,"max_batch_size":4,"cancels":[],"types":{"generator":false,"cancel":false},"collects_event_data":false,"trigger_after":null,"trigger_only_on_success":false,"trigger_mode":"always_last","show_api":true,"zerogpu":false,"rendered_in":null},{"id":42,"targets":[[126,"change"]],"inputs":[129,122,124,125,126],"outputs":[128],"backend_fn":true,"js":null,"queue":true,"api_name":"filter_df_l2_38","scroll_to_output":false,"show_progress":"full","batch":false,"max_batch_size":4,"cancels":[],"types":{"generator":false,"cancel":false},"collects_event_data":false,"trigger_after":null,"trigger_only_on_success":false,"trigger_mode":"always_last","show_api":true,"zerogpu":false,"rendered_in":null},{"id":43,"targets":[[124,"submit"]],"inputs":[129,122,124,125,126],"outputs":[128],"backend_fn":true,"js":null,"queue":true,"api_name":"filter_df_l2_39","scroll_to_output":false,"show_progress":"full","batch":false,"max_batch_size":4,"cancels":[],"types":{"generator":false,"cancel":false},"collects_event_data":false,"trigger_after":null,"trigger_only_on_success":false,"trigger_mode":"once","show_api":true,"zerogpu":false,"rendered_in":null},{"id":44,"targets":[[134,"change"]],"inputs":[141,134,136,137,138],"outputs":[140],"backend_fn":true,"js":null,"queue":true,"api_name":"filter_df_l2_40","scroll_to_output":false,"show_progress":"full","batch":false,"max_batch_size":4,"cancels":[],"types":{"generator":false,"cancel":false},"collects_event_data":false,"trigger_after":null,"trigger_only_on_success":false,"trigger_mode":"always_last","show_api":true,"zerogpu":false,"rendered_in":null},{"id":45,"targets":[[137,"change"]],"inputs":[141,134,136,137,138],"outputs":[140],"backend_fn":true,"js":null,"queue":true,"api_name":"filter_df_l2_41","scroll_to_output":false,"show_progress":"full","batch":false,"max_batch_size":4,"cancels":[],"types":{"generator":false,"cancel":false},"collects_event_data":false,"trigger_after":null,"trigger_only_on_success":false,"trigger_mode":"always_last","show_api":true,"zerogpu":false,"rendered_in":null},{"id":46,"targets":[[138,"change"]],"inputs":[141,134,136,137,138],"outputs":[140],"backend_fn":true,"js":null,"queue":true,"api_name":"filter_df_l2_42","scroll_to_output":false,"show_progress":"full","batch":false,"max_batch_size":4,"cancels":[],"types":{"generator":false,"cancel":false},"collects_event_data":false,"trigger_after":null,"trigger_only_on_success":false,"trigger_mode":"always_last","show_api":true,"zerogpu":false,"rendered_in":null},{"id":47,"targets":[[136,"submit"]],"inputs":[141,134,136,137,138],"outputs":[140],"backend_fn":true,"js":null,"queue":true,"api_name":"filter_df_l2_43","scroll_to_output":false,"show_progress":"full","batch":false,"max_batch_size":4,"cancels":[],"types":{"generator":false,"cancel":false},"collects_event_data":false,"trigger_after":null,"trigger_only_on_success":false,"trigger_mode":"once","show_api":true,"zerogpu":false,"rendered_in":null},{"id":48,"targets":[[146,"change"]],"inputs":[153,146,148,149,150],"outputs":[152],"backend_fn":true,"js":null,"queue":true,"api_name":"filter_df_l2_44","scroll_to_output":false,"show_progress":"full","batch":false,"max_batch_size":4,"cancels":[],"types":{"generator":false,"cancel":false},"collects_event_data":false,"trigger_after":null,"trigger_only_on_success":false,"trigger_mode":"always_last","show_api":true,"zerogpu":false,"rendered_in":null},{"id":49,"targets":[[149,"change"]],"inputs":[153,146,148,149,150],"outputs":[152],"backend_fn":true,"js":null,"queue":true,"api_name":"filter_df_l2_45","scroll_to_output":false,"show_progress":"full","batch":false,"max_batch_size":4,"cancels":[],"types":{"generator":false,"cancel":false},"collects_event_data":false,"trigger_after":null,"trigger_only_on_success":false,"trigger_mode":"always_last","show_api":true,"zerogpu":false,"rendered_in":null},{"id":50,"targets":[[150,"change"]],"inputs":[153,146,148,149,150],"outputs":[152],"backend_fn":true,"js":null,"queue":true,"api_name":"filter_df_l2_46","scroll_to_output":false,"show_progress":"full","batch":false,"max_batch_size":4,"cancels":[],"types":{"generator":false,"cancel":false},"collects_event_data":false,"trigger_after":null,"trigger_only_on_success":false,"trigger_mode":"always_last","show_api":true,"zerogpu":false,"rendered_in":null},{"id":51,"targets":[[148,"submit"]],"inputs":[153,146,148,149,150],"outputs":[152],"backend_fn":true,"js":null,"queue":true,"api_name":"filter_df_l2_47","scroll_to_output":false,"show_progress":"full","batch":false,"max_batch_size":4,"cancels":[],"types":{"generator":false,"cancel":false},"collects_event_data":false,"trigger_after":null,"trigger_only_on_success":false,"trigger_mode":"once","show_api":true,"zerogpu":false,"rendered_in":null},{"id":52,"targets":[[157,"change"]],"inputs":[164,157,159,160,161],"outputs":[163],"backend_fn":true,"js":null,"queue":true,"api_name":"filter_df_l2_48","scroll_to_output":false,"show_progress":"full","batch":false,"max_batch_size":4,"cancels":[],"types":{"generator":false,"cancel":false},"collects_event_data":false,"trigger_after":null,"trigger_only_on_success":false,"trigger_mode":"always_last","show_api":true,"zerogpu":false,"rendered_in":null},{"id":53,"targets":[[160,"change"]],"inputs":[164,157,159,160,161],"outputs":[163],"backend_fn":true,"js":null,"queue":true,"api_name":"filter_df_l2_49","scroll_to_output":false,"show_progress":"full","batch":false,"max_batch_size":4,"cancels":[],"types":{"generator":false,"cancel":false},"collects_event_data":false,"trigger_after":null,"trigger_only_on_success":false,"trigger_mode":"always_last","show_api":true,"zerogpu":false,"rendered_in":null},{"id":54,"targets":[[161,"change"]],"inputs":[164,157,159,160,161],"outputs":[163],"backend_fn":true,"js":null,"queue":true,"api_name":"filter_df_l2_50","scroll_to_output":false,"show_progress":"full","batch":false,"max_batch_size":4,"cancels":[],"types":{"generator":false,"cancel":false},"collects_event_data":false,"trigger_after":null,"trigger_only_on_success":false,"trigger_mode":"always_last","show_api":true,"zerogpu":false,"rendered_in":null},{"id":55,"targets":[[159,"submit"]],"inputs":[164,157,159,160,161],"outputs":[163],"backend_fn":true,"js":null,"queue":true,"api_name":"filter_df_l2_51","scroll_to_output":false,"show_progress":"full","batch":false,"max_batch_size":4,"cancels":[],"types":{"generator":false,"cancel":false},"collects_event_data":false,"trigger_after":null,"trigger_only_on_success":false,"trigger_mode":"once","show_api":true,"zerogpu":false,"rendered_in":null},{"id":56,"targets":[[169,"change"]],"inputs":[176,169,171,172,173],"outputs":[175],"backend_fn":true,"js":null,"queue":true,"api_name":"filter_df_l2_52","scroll_to_output":false,"show_progress":"full","batch":false,"max_batch_size":4,"cancels":[],"types":{"generator":false,"cancel":false},"collects_event_data":false,"trigger_after":null,"trigger_only_on_success":false,"trigger_mode":"always_last","show_api":true,"zerogpu":false,"rendered_in":null},{"id":57,"targets":[[172,"change"]],"inputs":[176,169,171,172,173],"outputs":[175],"backend_fn":true,"js":null,"queue":true,"api_name":"filter_df_l2_53","scroll_to_output":false,"show_progress":"full","batch":false,"max_batch_size":4,"cancels":[],"types":{"generator":false,"cancel":false},"collects_event_data":false,"trigger_after":null,"trigger_only_on_success":false,"trigger_mode":"always_last","show_api":true,"zerogpu":false,"rendered_in":null},{"id":58,"targets":[[173,"change"]],"inputs":[176,169,171,172,173],"outputs":[175],"backend_fn":true,"js":null,"queue":true,"api_name":"filter_df_l2_54","scroll_to_output":false,"show_progress":"full","batch":false,"max_batch_size":4,"cancels":[],"types":{"generator":false,"cancel":false},"collects_event_data":false,"trigger_after":null,"trigger_only_on_success":false,"trigger_mode":"always_last","show_api":true,"zerogpu":false,"rendered_in":null},{"id":59,"targets":[[171,"submit"]],"inputs":[176,169,171,172,173],"outputs":[175],"backend_fn":true,"js":null,"queue":true,"api_name":"filter_df_l2_55","scroll_to_output":false,"show_progress":"full","batch":false,"max_batch_size":4,"cancels":[],"types":{"generator":false,"cancel":false},"collects_event_data":false,"trigger_after":null,"trigger_only_on_success":false,"trigger_mode":"once","show_api":true,"zerogpu":false,"rendered_in":null},{"id":60,"targets":[[181,"change"]],"inputs":[188,181,183,184,185],"outputs":[187],"backend_fn":true,"js":null,"queue":true,"api_name":"filter_df_l2_56","scroll_to_output":false,"show_progress":"full","batch":false,"max_batch_size":4,"cancels":[],"types":{"generator":false,"cancel":false},"collects_event_data":false,"trigger_after":null,"trigger_only_on_success":false,"trigger_mode":"always_last","show_api":true,"zerogpu":false,"rendered_in":null},{"id":61,"targets":[[184,"change"]],"inputs":[188,181,183,184,185],"outputs":[187],"backend_fn":true,"js":null,"queue":true,"api_name":"filter_df_l2_57","scroll_to_output":false,"show_progress":"full","batch":false,"max_batch_size":4,"cancels":[],"types":{"generator":false,"cancel":false},"collects_event_data":false,"trigger_after":null,"trigger_only_on_success":false,"trigger_mode":"always_last","show_api":true,"zerogpu":false,"rendered_in":null},{"id":62,"targets":[[185,"change"]],"inputs":[188,181,183,184,185],"outputs":[187],"backend_fn":true,"js":null,"queue":true,"api_name":"filter_df_l2_58","scroll_to_output":false,"show_progress":"full","batch":false,"max_batch_size":4,"cancels":[],"types":{"generator":false,"cancel":false},"collects_event_data":false,"trigger_after":null,"trigger_only_on_success":false,"trigger_mode":"always_last","show_api":true,"zerogpu":false,"rendered_in":null},{"id":63,"targets":[[183,"submit"]],"inputs":[188,181,183,184,185],"outputs":[187],"backend_fn":true,"js":null,"queue":true,"api_name":"filter_df_l2_59","scroll_to_output":false,"show_progress":"full","batch":false,"max_batch_size":4,"cancels":[],"types":{"generator":false,"cancel":false},"collects_event_data":false,"trigger_after":null,"trigger_only_on_success":false,"trigger_mode":"once","show_api":true,"zerogpu":false,"rendered_in":null},{"id":64,"targets":[[193,"change"]],"inputs":[200,193,195,196,197],"outputs":[199],"backend_fn":true,"js":null,"queue":true,"api_name":"filter_df_l2_60","scroll_to_output":false,"show_progress":"full","batch":false,"max_batch_size":4,"cancels":[],"types":{"generator":false,"cancel":false},"collects_event_data":false,"trigger_after":null,"trigger_only_on_success":false,"trigger_mode":"always_last","show_api":true,"zerogpu":false,"rendered_in":null},{"id":65,"targets":[[196,"change"]],"inputs":[200,193,195,196,197],"outputs":[199],"backend_fn":true,"js":null,"queue":true,"api_name":"filter_df_l2_61","scroll_to_output":false,"show_progress":"full","batch":false,"max_batch_size":4,"cancels":[],"types":{"generator":false,"cancel":false},"collects_event_data":false,"trigger_after":null,"trigger_only_on_success":false,"trigger_mode":"always_last","show_api":true,"zerogpu":false,"rendered_in":null},{"id":66,"targets":[[197,"change"]],"inputs":[200,193,195,196,197],"outputs":[199],"backend_fn":true,"js":null,"queue":true,"api_name":"filter_df_l2_62","scroll_to_output":false,"show_progress":"full","batch":false,"max_batch_size":4,"cancels":[],"types":{"generator":false,"cancel":false},"collects_event_data":false,"trigger_after":null,"trigger_only_on_success":false,"trigger_mode":"always_last","show_api":true,"zerogpu":false,"rendered_in":null},{"id":67,"targets":[[195,"submit"]],"inputs":[200,193,195,196,197],"outputs":[199],"backend_fn":true,"js":null,"queue":true,"api_name":"filter_df_l2_63","scroll_to_output":false,"show_progress":"full","batch":false,"max_batch_size":4,"cancels":[],"types":{"generator":false,"cancel":false},"collects_event_data":false,"trigger_after":null,"trigger_only_on_success":false,"trigger_mode":"once","show_api":true,"zerogpu":false,"rendered_in":null},{"id":68,"targets":[[205,"change"]],"inputs":[212,205,207,208,209],"outputs":[211],"backend_fn":true,"js":null,"queue":true,"api_name":"filter_df_l2_64","scroll_to_output":false,"show_progress":"full","batch":false,"max_batch_size":4,"cancels":[],"types":{"generator":false,"cancel":false},"collects_event_data":false,"trigger_after":null,"trigger_only_on_success":false,"trigger_mode":"always_last","show_api":true,"zerogpu":false,"rendered_in":null},{"id":69,"targets":[[208,"change"]],"inputs":[212,205,207,208,209],"outputs":[211],"backend_fn":true,"js":null,"queue":true,"api_name":"filter_df_l2_65","scroll_to_output":false,"show_progress":"full","batch":false,"max_batch_size":4,"cancels":[],"types":{"generator":false,"cancel":false},"collects_event_data":false,"trigger_after":null,"trigger_only_on_success":false,"trigger_mode":"always_last","show_api":true,"zerogpu":false,"rendered_in":null},{"id":70,"targets":[[209,"change"]],"inputs":[212,205,207,208,209],"outputs":[211],"backend_fn":true,"js":null,"queue":true,"api_name":"filter_df_l2_66","scroll_to_output":false,"show_progress":"full","batch":false,"max_batch_size":4,"cancels":[],"types":{"generator":false,"cancel":false},"collects_event_data":false,"trigger_after":null,"trigger_only_on_success":false,"trigger_mode":"always_last","show_api":true,"zerogpu":false,"rendered_in":null},{"id":71,"targets":[[207,"submit"]],"inputs":[212,205,207,208,209],"outputs":[211],"backend_fn":true,"js":null,"queue":true,"api_name":"filter_df_l2_67","scroll_to_output":false,"show_progress":"full","batch":false,"max_batch_size":4,"cancels":[],"types":{"generator":false,"cancel":false},"collects_event_data":false,"trigger_after":null,"trigger_only_on_success":false,"trigger_mode":"once","show_api":true,"zerogpu":false,"rendered_in":null},{"id":72,"targets":[[217,"change"]],"inputs":[224,217,219,220,221],"outputs":[223],"backend_fn":true,"js":null,"queue":true,"api_name":"filter_df_l2_68","scroll_to_output":false,"show_progress":"full","batch":false,"max_batch_size":4,"cancels":[],"types":{"generator":false,"cancel":false},"collects_event_data":false,"trigger_after":null,"trigger_only_on_success":false,"trigger_mode":"always_last","show_api":true,"zerogpu":false,"rendered_in":null},{"id":73,"targets":[[220,"change"]],"inputs":[224,217,219,220,221],"outputs":[223],"backend_fn":true,"js":null,"queue":true,"api_name":"filter_df_l2_69","scroll_to_output":false,"show_progress":"full","batch":false,"max_batch_size":4,"cancels":[],"types":{"generator":false,"cancel":false},"collects_event_data":false,"trigger_after":null,"trigger_only_on_success":false,"trigger_mode":"always_last","show_api":true,"zerogpu":false,"rendered_in":null},{"id":74,"targets":[[221,"change"]],"inputs":[224,217,219,220,221],"outputs":[223],"backend_fn":true,"js":null,"queue":true,"api_name":"filter_df_l2_70","scroll_to_output":false,"show_progress":"full","batch":false,"max_batch_size":4,"cancels":[],"types":{"generator":false,"cancel":false},"collects_event_data":false,"trigger_after":null,"trigger_only_on_success":false,"trigger_mode":"always_last","show_api":true,"zerogpu":false,"rendered_in":null},{"id":75,"targets":[[219,"submit"]],"inputs":[224,217,219,220,221],"outputs":[223],"backend_fn":true,"js":null,"queue":true,"api_name":"filter_df_l2_71","scroll_to_output":false,"show_progress":"full","batch":false,"max_batch_size":4,"cancels":[],"types":{"generator":false,"cancel":false},"collects_event_data":false,"trigger_after":null,"trigger_only_on_success":false,"trigger_mode":"once","show_api":true,"zerogpu":false,"rendered_in":null},{"id":76,"targets":[[229,"change"]],"inputs":[236,229,231,232,233],"outputs":[235],"backend_fn":true,"js":null,"queue":true,"api_name":"filter_df_l2_72","scroll_to_output":false,"show_progress":"full","batch":false,"max_batch_size":4,"cancels":[],"types":{"generator":false,"cancel":false},"collects_event_data":false,"trigger_after":null,"trigger_only_on_success":false,"trigger_mode":"always_last","show_api":true,"zerogpu":false,"rendered_in":null},{"id":77,"targets":[[232,"change"]],"inputs":[236,229,231,232,233],"outputs":[235],"backend_fn":true,"js":null,"queue":true,"api_name":"filter_df_l2_73","scroll_to_output":false,"show_progress":"full","batch":false,"max_batch_size":4,"cancels":[],"types":{"generator":false,"cancel":false},"collects_event_data":false,"trigger_after":null,"trigger_only_on_success":false,"trigger_mode":"always_last","show_api":true,"zerogpu":false,"rendered_in":null},{"id":78,"targets":[[233,"change"]],"inputs":[236,229,231,232,233],"outputs":[235],"backend_fn":true,"js":null,"queue":true,"api_name":"filter_df_l2_74","scroll_to_output":false,"show_progress":"full","batch":false,"max_batch_size":4,"cancels":[],"types":{"generator":false,"cancel":false},"collects_event_data":false,"trigger_after":null,"trigger_only_on_success":false,"trigger_mode":"always_last","show_api":true,"zerogpu":false,"rendered_in":null},{"id":79,"targets":[[231,"submit"]],"inputs":[236,229,231,232,233],"outputs":[235],"backend_fn":true,"js":null,"queue":true,"api_name":"filter_df_l2_75","scroll_to_output":false,"show_progress":"full","batch":false,"max_batch_size":4,"cancels":[],"types":{"generator":false,"cancel":false},"collects_event_data":false,"trigger_after":null,"trigger_only_on_success":false,"trigger_mode":"once","show_api":true,"zerogpu":false,"rendered_in":null},{"id":80,"targets":[[241,"change"]],"inputs":[248,241,243,244,245],"outputs":[247],"backend_fn":true,"js":null,"queue":true,"api_name":"filter_df_l2_76","scroll_to_output":false,"show_progress":"full","batch":false,"max_batch_size":4,"cancels":[],"types":{"generator":false,"cancel":false},"collects_event_data":false,"trigger_after":null,"trigger_only_on_success":false,"trigger_mode":"always_last","show_api":true,"zerogpu":false,"rendered_in":null},{"id":81,"targets":[[244,"change"]],"inputs":[248,241,243,244,245],"outputs":[247],"backend_fn":true,"js":null,"queue":true,"api_name":"filter_df_l2_77","scroll_to_output":false,"show_progress":"full","batch":false,"max_batch_size":4,"cancels":[],"types":{"generator":false,"cancel":false},"collects_event_data":false,"trigger_after":null,"trigger_only_on_success":false,"trigger_mode":"always_last","show_api":true,"zerogpu":false,"rendered_in":null},{"id":82,"targets":[[245,"change"]],"inputs":[248,241,243,244,245],"outputs":[247],"backend_fn":true,"js":null,"queue":true,"api_name":"filter_df_l2_78","scroll_to_output":false,"show_progress":"full","batch":false,"max_batch_size":4,"cancels":[],"types":{"generator":false,"cancel":false},"collects_event_data":false,"trigger_after":null,"trigger_only_on_success":false,"trigger_mode":"always_last","show_api":true,"zerogpu":false,"rendered_in":null},{"id":83,"targets":[[243,"submit"]],"inputs":[248,241,243,244,245],"outputs":[247],"backend_fn":true,"js":null,"queue":true,"api_name":"filter_df_l2_79","scroll_to_output":false,"show_progress":"full","batch":false,"max_batch_size":4,"cancels":[],"types":{"generator":false,"cancel":false},"collects_event_data":false,"trigger_after":null,"trigger_only_on_success":false,"trigger_mode":"once","show_api":true,"zerogpu":false,"rendered_in":null},{"id":84,"targets":[[253,"change"]],"inputs":[260,253,255,256,257],"outputs":[259],"backend_fn":true,"js":null,"queue":true,"api_name":"filter_df_l2_80","scroll_to_output":false,"show_progress":"full","batch":false,"max_batch_size":4,"cancels":[],"types":{"generator":false,"cancel":false},"collects_event_data":false,"trigger_after":null,"trigger_only_on_success":false,"trigger_mode":"always_last","show_api":true,"zerogpu":false,"rendered_in":null},{"id":85,"targets":[[256,"change"]],"inputs":[260,253,255,256,257],"outputs":[259],"backend_fn":true,"js":null,"queue":true,"api_name":"filter_df_l2_81","scroll_to_output":false,"show_progress":"full","batch":false,"max_batch_size":4,"cancels":[],"types":{"generator":false,"cancel":false},"collects_event_data":false,"trigger_after":null,"trigger_only_on_success":false,"trigger_mode":"always_last","show_api":true,"zerogpu":false,"rendered_in":null},{"id":86,"targets":[[257,"change"]],"inputs":[260,253,255,256,257],"outputs":[259],"backend_fn":true,"js":null,"queue":true,"api_name":"filter_df_l2_82","scroll_to_output":false,"show_progress":"full","batch":false,"max_batch_size":4,"cancels":[],"types":{"generator":false,"cancel":false},"collects_event_data":false,"trigger_after":null,"trigger_only_on_success":false,"trigger_mode":"always_last","show_api":true,"zerogpu":false,"rendered_in":null},{"id":87,"targets":[[255,"submit"]],"inputs":[260,253,255,256,257],"outputs":[259],"backend_fn":true,"js":null,"queue":true,"api_name":"filter_df_l2_83","scroll_to_output":false,"show_progress":"full","batch":false,"max_batch_size":4,"cancels":[],"types":{"generator":false,"cancel":false},"collects_event_data":false,"trigger_after":null,"trigger_only_on_success":false,"trigger_mode":"once","show_api":true,"zerogpu":false,"rendered_in":null},{"id":88,"targets":[[265,"change"]],"inputs":[272,265,267,268,269],"outputs":[271],"backend_fn":true,"js":null,"queue":true,"api_name":"filter_df_l2_84","scroll_to_output":false,"show_progress":"full","batch":false,"max_batch_size":4,"cancels":[],"types":{"generator":false,"cancel":false},"collects_event_data":false,"trigger_after":null,"trigger_only_on_success":false,"trigger_mode":"always_last","show_api":true,"zerogpu":false,"rendered_in":null},{"id":89,"targets":[[268,"change"]],"inputs":[272,265,267,268,269],"outputs":[271],"backend_fn":true,"js":null,"queue":true,"api_name":"filter_df_l2_85","scroll_to_output":false,"show_progress":"full","batch":false,"max_batch_size":4,"cancels":[],"types":{"generator":false,"cancel":false},"collects_event_data":false,"trigger_after":null,"trigger_only_on_success":false,"trigger_mode":"always_last","show_api":true,"zerogpu":false,"rendered_in":null},{"id":90,"targets":[[269,"change"]],"inputs":[272,265,267,268,269],"outputs":[271],"backend_fn":true,"js":null,"queue":true,"api_name":"filter_df_l2_86","scroll_to_output":false,"show_progress":"full","batch":false,"max_batch_size":4,"cancels":[],"types":{"generator":false,"cancel":false},"collects_event_data":false,"trigger_after":null,"trigger_only_on_success":false,"trigger_mode":"always_last","show_api":true,"zerogpu":false,"rendered_in":null},{"id":91,"targets":[[267,"submit"]],"inputs":[272,265,267,268,269],"outputs":[271],"backend_fn":true,"js":null,"queue":true,"api_name":"filter_df_l2_87","scroll_to_output":false,"show_progress":"full","batch":false,"max_batch_size":4,"cancels":[],"types":{"generator":false,"cancel":false},"collects_event_data":false,"trigger_after":null,"trigger_only_on_success":false,"trigger_mode":"once","show_api":true,"zerogpu":false,"rendered_in":null},{"id":92,"targets":[[277,"change"]],"inputs":[284,277,279,280,281],"outputs":[283],"backend_fn":true,"js":null,"queue":true,"api_name":"filter_df_l2_88","scroll_to_output":false,"show_progress":"full","batch":false,"max_batch_size":4,"cancels":[],"types":{"generator":false,"cancel":false},"collects_event_data":false,"trigger_after":null,"trigger_only_on_success":false,"trigger_mode":"always_last","show_api":true,"zerogpu":false,"rendered_in":null},{"id":93,"targets":[[280,"change"]],"inputs":[284,277,279,280,281],"outputs":[283],"backend_fn":true,"js":null,"queue":true,"api_name":"filter_df_l2_89","scroll_to_output":false,"show_progress":"full","batch":false,"max_batch_size":4,"cancels":[],"types":{"generator":false,"cancel":false},"collects_event_data":false,"trigger_after":null,"trigger_only_on_success":false,"trigger_mode":"always_last","show_api":true,"zerogpu":false,"rendered_in":null},{"id":94,"targets":[[281,"change"]],"inputs":[284,277,279,280,281],"outputs":[283],"backend_fn":true,"js":null,"queue":true,"api_name":"filter_df_l2_90","scroll_to_output":false,"show_progress":"full","batch":false,"max_batch_size":4,"cancels":[],"types":{"generator":false,"cancel":false},"collects_event_data":false,"trigger_after":null,"trigger_only_on_success":false,"trigger_mode":"always_last","show_api":true,"zerogpu":false,"rendered_in":null},{"id":95,"targets":[[279,"submit"]],"inputs":[284,277,279,280,281],"outputs":[283],"backend_fn":true,"js":null,"queue":true,"api_name":"filter_df_l2_91","scroll_to_output":false,"show_progress":"full","batch":false,"max_batch_size":4,"cancels":[],"types":{"generator":false,"cancel":false},"collects_event_data":false,"trigger_after":null,"trigger_only_on_success":false,"trigger_mode":"once","show_api":true,"zerogpu":false,"rendered_in":null},{"id":96,"targets":[[289,"change"]],"inputs":[296,289,291,292,293],"outputs":[295],"backend_fn":true,"js":null,"queue":true,"api_name":"filter_df_l2_92","scroll_to_output":false,"show_progress":"full","batch":false,"max_batch_size":4,"cancels":[],"types":{"generator":false,"cancel":false},"collects_event_data":false,"trigger_after":null,"trigger_only_on_success":false,"trigger_mode":"always_last","show_api":true,"zerogpu":false,"rendered_in":null},{"id":97,"targets":[[292,"change"]],"inputs":[296,289,291,292,293],"outputs":[295],"backend_fn":true,"js":null,"queue":true,"api_name":"filter_df_l2_93","scroll_to_output":false,"show_progress":"full","batch":false,"max_batch_size":4,"cancels":[],"types":{"generator":false,"cancel":false},"collects_event_data":false,"trigger_after":null,"trigger_only_on_success":false,"trigger_mode":"always_last","show_api":true,"zerogpu":false,"rendered_in":null},{"id":98,"targets":[[293,"change"]],"inputs":[296,289,291,292,293],"outputs":[295],"backend_fn":true,"js":null,"queue":true,"api_name":"filter_df_l2_94","scroll_to_output":false,"show_progress":"full","batch":false,"max_batch_size":4,"cancels":[],"types":{"generator":false,"cancel":false},"collects_event_data":false,"trigger_after":null,"trigger_only_on_success":false,"trigger_mode":"always_last","show_api":true,"zerogpu":false,"rendered_in":null},{"id":99,"targets":[[291,"submit"]],"inputs":[296,289,291,292,293],"outputs":[295],"backend_fn":true,"js":null,"queue":true,"api_name":"filter_df_l2_95","scroll_to_output":false,"show_progress":"full","batch":false,"max_batch_size":4,"cancels":[],"types":{"generator":false,"cancel":false},"collects_event_data":false,"trigger_after":null,"trigger_only_on_success":false,"trigger_mode":"once","show_api":true,"zerogpu":false,"rendered_in":null},{"id":100,"targets":[[301,"change"]],"inputs":[308,301,303,304,305],"outputs":[307],"backend_fn":true,"js":null,"queue":true,"api_name":"filter_df_l2_96","scroll_to_output":false,"show_progress":"full","batch":false,"max_batch_size":4,"cancels":[],"types":{"generator":false,"cancel":false},"collects_event_data":false,"trigger_after":null,"trigger_only_on_success":false,"trigger_mode":"always_last","show_api":true,"zerogpu":false,"rendered_in":null},{"id":101,"targets":[[304,"change"]],"inputs":[308,301,303,304,305],"outputs":[307],"backend_fn":true,"js":null,"queue":true,"api_name":"filter_df_l2_97","scroll_to_output":false,"show_progress":"full","batch":false,"max_batch_size":4,"cancels":[],"types":{"generator":false,"cancel":false},"collects_event_data":false,"trigger_after":null,"trigger_only_on_success":false,"trigger_mode":"always_last","show_api":true,"zerogpu":false,"rendered_in":null},{"id":102,"targets":[[305,"change"]],"inputs":[308,301,303,304,305],"outputs":[307],"backend_fn":true,"js":null,"queue":true,"api_name":"filter_df_l2_98","scroll_to_output":false,"show_progress":"full","batch":false,"max_batch_size":4,"cancels":[],"types":{"generator":false,"cancel":false},"collects_event_data":false,"trigger_after":null,"trigger_only_on_success":false,"trigger_mode":"always_last","show_api":true,"zerogpu":false,"rendered_in":null},{"id":103,"targets":[[303,"submit"]],"inputs":[308,301,303,304,305],"outputs":[307],"backend_fn":true,"js":null,"queue":true,"api_name":"filter_df_l2_99","scroll_to_output":false,"show_progress":"full","batch":false,"max_batch_size":4,"cancels":[],"types":{"generator":false,"cancel":false},"collects_event_data":false,"trigger_after":null,"trigger_only_on_success":false,"trigger_mode":"once","show_api":true,"zerogpu":false,"rendered_in":null},{"id":104,"targets":[[313,"change"]],"inputs":[320,313,315,316,317],"outputs":[319],"backend_fn":true,"js":null,"queue":true,"api_name":"filter_df_l2_100","scroll_to_output":false,"show_progress":"full","batch":false,"max_batch_size":4,"cancels":[],"types":{"generator":false,"cancel":false},"collects_event_data":false,"trigger_after":null,"trigger_only_on_success":false,"trigger_mode":"always_last","show_api":true,"zerogpu":false,"rendered_in":null},{"id":105,"targets":[[316,"change"]],"inputs":[320,313,315,316,317],"outputs":[319],"backend_fn":true,"js":null,"queue":true,"api_name":"filter_df_l2_101","scroll_to_output":false,"show_progress":"full","batch":false,"max_batch_size":4,"cancels":[],"types":{"generator":false,"cancel":false},"collects_event_data":false,"trigger_after":null,"trigger_only_on_success":false,"trigger_mode":"always_last","show_api":true,"zerogpu":false,"rendered_in":null},{"id":106,"targets":[[317,"change"]],"inputs":[320,313,315,316,317],"outputs":[319],"backend_fn":true,"js":null,"queue":true,"api_name":"filter_df_l2_102","scroll_to_output":false,"show_progress":"full","batch":false,"max_batch_size":4,"cancels":[],"types":{"generator":false,"cancel":false},"collects_event_data":false,"trigger_after":null,"trigger_only_on_success":false,"trigger_mode":"always_last","show_api":true,"zerogpu":false,"rendered_in":null},{"id":107,"targets":[[315,"submit"]],"inputs":[320,313,315,316,317],"outputs":[319],"backend_fn":true,"js":null,"queue":true,"api_name":"filter_df_l2_103","scroll_to_output":false,"show_progress":"full","batch":false,"max_batch_size":4,"cancels":[],"types":{"generator":false,"cancel":false},"collects_event_data":false,"trigger_after":null,"trigger_only_on_success":false,"trigger_mode":"once","show_api":true,"zerogpu":false,"rendered_in":null},{"id":108,"targets":[[325,"change"]],"inputs":[332,325,327,328,329],"outputs":[331],"backend_fn":true,"js":null,"queue":true,"api_name":"filter_df_l2_104","scroll_to_output":false,"show_progress":"full","batch":false,"max_batch_size":4,"cancels":[],"types":{"generator":false,"cancel":false},"collects_event_data":false,"trigger_after":null,"trigger_only_on_success":false,"trigger_mode":"always_last","show_api":true,"zerogpu":false,"rendered_in":null},{"id":109,"targets":[[328,"change"]],"inputs":[332,325,327,328,329],"outputs":[331],"backend_fn":true,"js":null,"queue":true,"api_name":"filter_df_l2_105","scroll_to_output":false,"show_progress":"full","batch":false,"max_batch_size":4,"cancels":[],"types":{"generator":false,"cancel":false},"collects_event_data":false,"trigger_after":null,"trigger_only_on_success":false,"trigger_mode":"always_last","show_api":true,"zerogpu":false,"rendered_in":null},{"id":110,"targets":[[329,"change"]],"inputs":[332,325,327,328,329],"outputs":[331],"backend_fn":true,"js":null,"queue":true,"api_name":"filter_df_l2_106","scroll_to_output":false,"show_progress":"full","batch":false,"max_batch_size":4,"cancels":[],"types":{"generator":false,"cancel":false},"collects_event_data":false,"trigger_after":null,"trigger_only_on_success":false,"trigger_mode":"always_last","show_api":true,"zerogpu":false,"rendered_in":null},{"id":111,"targets":[[327,"submit"]],"inputs":[332,325,327,328,329],"outputs":[331],"backend_fn":true,"js":null,"queue":true,"api_name":"filter_df_l2_107","scroll_to_output":false,"show_progress":"full","batch":false,"max_batch_size":4,"cancels":[],"types":{"generator":false,"cancel":false},"collects_event_data":false,"trigger_after":null,"trigger_only_on_success":false,"trigger_mode":"once","show_api":true,"zerogpu":false,"rendered_in":null},{"id":112,"targets":[[336,"change"]],"inputs":[343,336,338,339,340],"outputs":[342],"backend_fn":true,"js":null,"queue":true,"api_name":"filter_df_l2_108","scroll_to_output":false,"show_progress":"full","batch":false,"max_batch_size":4,"cancels":[],"types":{"generator":false,"cancel":false},"collects_event_data":false,"trigger_after":null,"trigger_only_on_success":false,"trigger_mode":"always_last","show_api":true,"zerogpu":false,"rendered_in":null},{"id":113,"targets":[[339,"change"]],"inputs":[343,336,338,339,340],"outputs":[342],"backend_fn":true,"js":null,"queue":true,"api_name":"filter_df_l2_109","scroll_to_output":false,"show_progress":"full","batch":false,"max_batch_size":4,"cancels":[],"types":{"generator":false,"cancel":false},"collects_event_data":false,"trigger_after":null,"trigger_only_on_success":false,"trigger_mode":"always_last","show_api":true,"zerogpu":false,"rendered_in":null},{"id":114,"targets":[[340,"change"]],"inputs":[343,336,338,339,340],"outputs":[342],"backend_fn":true,"js":null,"queue":true,"api_name":"filter_df_l2_110","scroll_to_output":false,"show_progress":"full","batch":false,"max_batch_size":4,"cancels":[],"types":{"generator":false,"cancel":false},"collects_event_data":false,"trigger_after":null,"trigger_only_on_success":false,"trigger_mode":"always_last","show_api":true,"zerogpu":false,"rendered_in":null},{"id":115,"targets":[[338,"submit"]],"inputs":[343,336,338,339,340],"outputs":[342],"backend_fn":true,"js":null,"queue":true,"api_name":"filter_df_l2_111","scroll_to_output":false,"show_progress":"full","batch":false,"max_batch_size":4,"cancels":[],"types":{"generator":false,"cancel":false},"collects_event_data":false,"trigger_after":null,"trigger_only_on_success":false,"trigger_mode":"once","show_api":true,"zerogpu":false,"rendered_in":null},{"id":116,"targets":[[347,"change"]],"inputs":[354,347,349,350,351],"outputs":[353],"backend_fn":true,"js":null,"queue":true,"api_name":"filter_df_l2_112","scroll_to_output":false,"show_progress":"full","batch":false,"max_batch_size":4,"cancels":[],"types":{"generator":false,"cancel":false},"collects_event_data":false,"trigger_after":null,"trigger_only_on_success":false,"trigger_mode":"always_last","show_api":true,"zerogpu":false,"rendered_in":null},{"id":117,"targets":[[350,"change"]],"inputs":[354,347,349,350,351],"outputs":[353],"backend_fn":true,"js":null,"queue":true,"api_name":"filter_df_l2_113","scroll_to_output":false,"show_progress":"full","batch":false,"max_batch_size":4,"cancels":[],"types":{"generator":false,"cancel":false},"collects_event_data":false,"trigger_after":null,"trigger_only_on_success":false,"trigger_mode":"always_last","show_api":true,"zerogpu":false,"rendered_in":null},{"id":118,"targets":[[351,"change"]],"inputs":[354,347,349,350,351],"outputs":[353],"backend_fn":true,"js":null,"queue":true,"api_name":"filter_df_l2_114","scroll_to_output":false,"show_progress":"full","batch":false,"max_batch_size":4,"cancels":[],"types":{"generator":false,"cancel":false},"collects_event_data":false,"trigger_after":null,"trigger_only_on_success":false,"trigger_mode":"always_last","show_api":true,"zerogpu":false,"rendered_in":null},{"id":119,"targets":[[349,"submit"]],"inputs":[354,347,349,350,351],"outputs":[353],"backend_fn":true,"js":null,"queue":true,"api_name":"filter_df_l2_115","scroll_to_output":false,"show_progress":"full","batch":false,"max_batch_size":4,"cancels":[],"types":{"generator":false,"cancel":false},"collects_event_data":false,"trigger_after":null,"trigger_only_on_success":false,"trigger_mode":"once","show_api":true,"zerogpu":false,"rendered_in":null},{"id":120,"targets":[[358,"change"]],"inputs":[365,358,360,361,362],"outputs":[364],"backend_fn":true,"js":null,"queue":true,"api_name":"filter_df_l2_116","scroll_to_output":false,"show_progress":"full","batch":false,"max_batch_size":4,"cancels":[],"types":{"generator":false,"cancel":false},"collects_event_data":false,"trigger_after":null,"trigger_only_on_success":false,"trigger_mode":"always_last","show_api":true,"zerogpu":false,"rendered_in":null},{"id":121,"targets":[[361,"change"]],"inputs":[365,358,360,361,362],"outputs":[364],"backend_fn":true,"js":null,"queue":true,"api_name":"filter_df_l2_117","scroll_to_output":false,"show_progress":"full","batch":false,"max_batch_size":4,"cancels":[],"types":{"generator":false,"cancel":false},"collects_event_data":false,"trigger_after":null,"trigger_only_on_success":false,"trigger_mode":"always_last","show_api":true,"zerogpu":false,"rendered_in":null},{"id":122,"targets":[[362,"change"]],"inputs":[365,358,360,361,362],"outputs":[364],"backend_fn":true,"js":null,"queue":true,"api_name":"filter_df_l2_118","scroll_to_output":false,"show_progress":"full","batch":false,"max_batch_size":4,"cancels":[],"types":{"generator":false,"cancel":false},"collects_event_data":false,"trigger_after":null,"trigger_only_on_success":false,"trigger_mode":"always_last","show_api":true,"zerogpu":false,"rendered_in":null},{"id":123,"targets":[[360,"submit"]],"inputs":[365,358,360,361,362],"outputs":[364],"backend_fn":true,"js":null,"queue":true,"api_name":"filter_df_l2_119","scroll_to_output":false,"show_progress":"full","batch":false,"max_batch_size":4,"cancels":[],"types":{"generator":false,"cancel":false},"collects_event_data":false,"trigger_after":null,"trigger_only_on_success":false,"trigger_mode":"once","show_api":true,"zerogpu":false,"rendered_in":null},{"id":124,"targets":[[370,"change"]],"inputs":[377,370,372,373,374],"outputs":[376],"backend_fn":true,"js":null,"queue":true,"api_name":"filter_df_l2_120","scroll_to_output":false,"show_progress":"full","batch":false,"max_batch_size":4,"cancels":[],"types":{"generator":false,"cancel":false},"collects_event_data":false,"trigger_after":null,"trigger_only_on_success":false,"trigger_mode":"always_last","show_api":true,"zerogpu":false,"rendered_in":null},{"id":125,"targets":[[373,"change"]],"inputs":[377,370,372,373,374],"outputs":[376],"backend_fn":true,"js":null,"queue":true,"api_name":"filter_df_l2_121","scroll_to_output":false,"show_progress":"full","batch":false,"max_batch_size":4,"cancels":[],"types":{"generator":false,"cancel":false},"collects_event_data":false,"trigger_after":null,"trigger_only_on_success":false,"trigger_mode":"always_last","show_api":true,"zerogpu":false,"rendered_in":null},{"id":126,"targets":[[374,"change"]],"inputs":[377,370,372,373,374],"outputs":[376],"backend_fn":true,"js":null,"queue":true,"api_name":"filter_df_l2_122","scroll_to_output":false,"show_progress":"full","batch":false,"max_batch_size":4,"cancels":[],"types":{"generator":false,"cancel":false},"collects_event_data":false,"trigger_after":null,"trigger_only_on_success":false,"trigger_mode":"always_last","show_api":true,"zerogpu":false,"rendered_in":null},{"id":127,"targets":[[372,"submit"]],"inputs":[377,370,372,373,374],"outputs":[376],"backend_fn":true,"js":null,"queue":true,"api_name":"filter_df_l2_123","scroll_to_output":false,"show_progress":"full","batch":false,"max_batch_size":4,"cancels":[],"types":{"generator":false,"cancel":false},"collects_event_data":false,"trigger_after":null,"trigger_only_on_success":false,"trigger_mode":"once","show_api":true,"zerogpu":false,"rendered_in":null}],"root":"https://opencompass-open-vlm-leaderboard.hf.space","username":null}