Benchmark Almanac

MMMU

Qwen 3.6 Plus 86% leads since April 2026
GPT-5.1 85.4% leads since November 2025
Qwen 3.6 Plus 86% leads since April 2026
In use

The official leaderboard hasn’t scored a model released after Reka Edge (March 2026). Labs report their own numbers for 10 newer models, such as Qwen 3.6 Plus at 86%.

11.5K college-level multimodal questions across 30 subjects. Multiple-choice and open accuracy.

Near-saturated. The test set answers became public on February 12th, 2026, so test scores can now be computed locally.

Released
November 2023
Kind
General visual questions
Level
University
Scored
Checked automatically
Answers
Multiple choice
Tasks
All public
Measures
Capability
Language
English
In and out
Text, Images → Text
Interaction
Single turn
Run by
Anyone
Strongest model tested
Claude Opus 4.5 #62 on the capability index
Last in a launch post
October 2026
Last model added
October 2026
Scores refreshed
November 18th, 2026

In the authors’ words

We introduce MMMU: a new benchmark designed to evaluate multimodal models on massive multi-discipline tasks demanding college-level subject knowledge and deliberate reasoning. MMMU includes 11.5K meticulously collected multimodal questions from college exams, quizzes, and textbooks, covering six core disciplines: Art & Design, Business, Science, Health & Medicine, Humanities & Social Science, and Tech & Engineering. These questions span 30 subjects and 183 subfields, comprising 30 highly heterogeneous image types, such as charts, diagrams, maps, tables, music sheets, and chemical structures. Unlike existing benchmarks, MMMU focuses on advanced perception and reasoning with domain-specific knowledge, challenging models to perform tasks akin to those faced by experts. The evaluation of 14 open-source LMMs as well as the proprietary GPT-4V(ision) and Gemini highlights the substantial challenges posed by MMMU. Even the advanced GPT-4V and Gemini Ultra only achieve accuracies of 56% and 59% respectively, indicating significant room for improvement. We believe MMMU will stimulate the community to build next-generation multimodal foundation models towards expert artificial general intelligence.

Abstract of MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI (arXiv:2311.16502, CC0)
104
Models scored in lab cards
96
Launch posts list it, from 23 labs
51
System cards report it, from 18 labs

Qwen 3.6 Plus leads with 86%

Best score per model as labs report them in their own cards, drawn striped. Labs pick their own settings, so these compare less cleanly than independent runs.

GPT-5.1 leads with 85.4% across all independent runs

Best score per model across the official leaderboard, Epoch AI’s own runs and any board Epoch AI copied. Dotted bars are reruns by Epoch AI or another board, and each row names its source.

Qwen 3.6 Plus leads with 86%, claims included

Best score per model from every source, including labs’ own numbers and claims Epoch AI collected from reports and papers. Labs pick their own settings, so a claim can beat an independent run of the same model. Striped bars are claims, and dotted bars are reruns by Epoch AI or another board.

104 models. Scroll sideways for the rest.

  1. 86.0 Qwen 3.6 Plus
  2. 85.4 GPT-5.1
  3. 85.4 Seed2.0 Pro
  4. 85.0 Qwen3.5 397B-A17B
  5. 84.3 Kimi K2.5
  6. 84.2 GPT-5
  7. 83.9 Qwen3.5-122B-A10B
  8. 83.4 Seed1.8
  9. 82.9 o3
  10. 82.9 Qwen3.6 27B
  11. 82.3 Qwen3.5-27B
  12. 82.0 Gemini 2.5 Pro
  13. 81.7 Gemini 2.5 Pro
  14. 81.7 Qwen 3.6 35B-A3B
  15. 81.6 o4-mini
  16. 81.6 GPT-5 mini
  17. 81.4 Qwen3.5-35B-A3B
  18. 80.7 gemini-robotics-er-1.5-preview
  19. 80.7 Claude Opus 4.5
  20. 80.6 Qwen3-VL-235B-A22B
  21. 80.3 Gemini 2.5 Flash
  22. 80.2 MiniCPM-V-4.7-35B-A3B
  23. 80.1 Qwen3.5-Omni-Plus
  24. 79.7 Gemini 2.5 Flash
  25. 78.7 EXAONE 4.5 33B
  26. 78.4 Qwen3.5-9B
  27. 78.1 STEP3-VL-10B
  28. 78.0 Grok 3
  29. 77.9 Seed1.5-VL
  30. 77.8 Claude Sonnet 4.5
  31. 77.7 Intern-S1
  32. 77.7 InternVL3.5-241B-A28B
  33. 77.6 Qwen3.5-4B
  34. 77.3 o1
  35. 77.1 Claude Opus 4.1
  36. 76.7 Gemini 2.5 Flash
  37. 76.5 Claude Opus 4
  38. 76.1 Llama 4 Behemoth
  39. 76.0 GLM-4.6V
  40. 75.6 GPT-5 nano
  41. 75.4 Gemini 2.0 Flash Thinking
  42. 75.4 GLM-4.5V
  43. 75.3 Keye-VL-2.0-30B-A3B
  44. 75.1 Command A+
  45. 75.0 Claude 3.7 Sonnet
  46. 74.8 GPT-4.1
  47. 74.8 Seed1.6-Thinking
  48. 74.4 GPT-4.5
  49. 74.4 Claude Sonnet 4
  50. 74.2 Step 3
  51. 73.4 Llama 4 Maverick
  52. 73.2 Claude Haiku 4.5
  53. 72.9 Gemini 2.5 Flash-Lite
  54. 72.7 Gemini 2.0 Pro
  55. 72.7 GPT-4.1 mini
  56. 72.2 ERNIE-4.5-VL-28B-A3B-Thinking
  57. 72.0 Gemini 2.5 Flash-Lite
  58. 71.7 Gemini 2.0 Flash
  59. 70.8 Nemotron 3 Nano Omni 30B-A3B
  60. 70.7 Gemini 2.0 Flash
  61. 70.7 LongCat-Flash-Omni
  62. 70.4 Claude 3.5 Sonnet (October 2024)
  63. 70.2 Qwen2.5-VL-72B
  64. 70.0 Kimi k1.5
  65. 70.0 Magistral Medium 1.0
  66. 69.4 Grok-3 mini
  67. 69.4 Llama 4 Scout
  68. 69.1 GPT-4o
  69. 69.1 Qwen3-Omni-30B-A3B
  70. 68.3 Claude 3.5 Sonnet
  71. 68.0 Gemini 2.0 Flash-Lite
  72. 68.0 Amazon Nova Premier
  73. 68.0 GLM-4.1V-9B-Thinking
  74. 68.0 Nemotron Nano 12B v2 VL
  75. 66.1 Grok-2
  76. 66.1 Mistral Medium 3
  77. 66.0 Magistral Small 1.0
  78. 64.9 Gemma 3 27B
  79. 64.2 Qwen3.5-2B
  80. 64.0 Mistral Small 3.1
  81. 64.0 Kimi-VL-A3B-Thinking-2506
  82. 62.5 Mistral Small 3.2
  83. 62.4 Gemini 1.0 Ultra
  84. 62.2 Gemini 1.5 Pro
  85. 61.7 Kimi-VL-A3B-Thinking
  86. 59.6 Gemma 3 12B
  87. 59.4 Claude 3 Opus
  88. 59.4 GPT-4o mini
  89. 59.2 Qwen2.5-Omni-7B
  90. 58.5 Gemini 1.5 Pro
  91. 55.4 GPT-4.1 nano
  92. 55.3 BAGEL-7B-MoT
  93. 55.1 Phi-4-multimodal
  94. 54.3 Phi-4-Reasoning-Vision-15B
  95. 53.1 Claude 3 Sonnet
  96. 50.2 Claude 3 Haiku
  97. 49.0 Qwen3.5-0.8B
  98. 48.8 Gemma 3 4B
  99. 48.4 LFM2.5-VL-3B
  100. 48.2 Llama-3.1-Nemotron-Nano-VL-8B-V1
  101. 43.0 Phi-3.5-vision-instruct
  102. 41.0 Janus-Pro-7B
  103. 39.7 LFM2-VL-1.6B
  104. 32.9 North Micro Vision Instruct
  1. 1 Qwen 3.6 Plus 86%
  2. 2 GPT-5.1 85.4%
  3. 3 Seed2.0 Pro 85.4%
  4. 4 Qwen3.5 397B-A17B 85%
  5. 5 Kimi K2.5 84.3%
  6. 6 GPT-5 84.2%
  7. 7 Qwen3.5-122B-A10B 83.9%
  8. 8 Seed1.8 83.4%
  9. 9 o3 82.9%
  10. 10 Qwen3.6 27B 82.9%
  11. 11 Qwen3.5-27B 82.3%
  12. 12 Gemini 2.5 Pro Jun 2025 82%
  13. 13 Gemini 2.5 Pro Mar 2025 81.7%
  14. 14 Qwen 3.6 35B-A3B 81.7%
  15. 15 o4-mini 81.6%
  16. 16 GPT-5 mini 81.6%
  17. 17 Qwen3.5-35B-A3B 81.4%
  18. 18 gemini-robotics-er-1.5-preview 80.7%
  19. 19 Claude Opus 4.5 80.7%
  20. 20 Qwen3-VL-235B-A22B 80.6%
  21. 21 Gemini 2.5 Flash Sep 2025 80.3%
  22. 22 MiniCPM-V-4.7-35B-A3B 80.2%
  23. 23 Qwen3.5-Omni-Plus 80.1%
  24. 24 Gemini 2.5 Flash Jun 2025 79.7%
  25. 25 EXAONE 4.5 33B 78.7%
  26. 26 Qwen3.5-9B 78.4%
  27. 27 STEP3-VL-10B 78.1%
  28. 28 Grok 3 78%
  29. 29 Seed1.5-VL 77.9%
  30. 30 Claude Sonnet 4.5 77.8%
  31. 31 Intern-S1 77.7%
  32. 32 InternVL3.5-241B-A28B 77.7%
  33. 33 Qwen3.5-4B 77.6%
  34. 34 o1 77.3%
  35. 35 Claude Opus 4.1 77.1%
  36. 36 Gemini 2.5 Flash Apr 2025 76.7%
  37. 37 Claude Opus 4 76.5%
  38. 38 Llama 4 Behemoth 76.1%
  39. 39 GLM-4.6V 76%
  40. 40 GPT-5 nano 75.6%
  41. 41 Gemini 2.0 Flash Thinking Jan 2025 75.4%
  42. 42 GLM-4.5V 75.4%
  43. 43 Keye-VL-2.0-30B-A3B 75.3%
  44. 44 Command A+ 75.1%
  45. 45 Claude 3.7 Sonnet 75%
  46. 46 GPT-4.1 74.8%
  47. 47 Seed1.6-Thinking 74.8%
  48. 48 GPT-4.5 74.4%
  49. 49 Claude Sonnet 4 74.4%
  50. 50 Step 3 74.2%
  51. 51 Llama 4 Maverick 73.4%
  52. 52 Claude Haiku 4.5 73.2%
  53. 53 Gemini 2.5 Flash-Lite Jun 2025 72.9%
  54. 54 Gemini 2.0 Pro 72.7%
  55. 55 GPT-4.1 mini 72.7%
  56. 56 ERNIE-4.5-VL-28B-A3B-Thinking 72.2%
  57. 57 Gemini 2.5 Flash-Lite Sep 2025 72%
  58. 58 Gemini 2.0 Flash Feb 2025 71.7%
  59. 59 Nemotron 3 Nano Omni 30B-A3B 70.8%
  60. 60 Gemini 2.0 Flash Dec 2024 70.7%
  61. 61 LongCat-Flash-Omni 70.7%
  62. 62 Claude 3.5 Sonnet (October 2024) 70.4%
  63. 63 Qwen2.5-VL-72B 70.2%
  64. 64 Kimi k1.5 70%
  65. 65 Magistral Medium 1.0 70%
  66. 66 Grok-3 mini 69.4%
  67. 67 Llama 4 Scout 69.4%
  68. 68 GPT-4o May 2024 69.1%
  69. 69 Qwen3-Omni-30B-A3B 69.1%
  70. 70 Claude 3.5 Sonnet 68.3%
  71. 71 Gemini 2.0 Flash-Lite 68%
  72. 72 Amazon Nova Premier 68%
  73. 73 GLM-4.1V-9B-Thinking 68%
  74. 74 Nemotron Nano 12B v2 VL 68%
  75. 75 Grok-2 Aug 2024 66.1%
  76. 76 Mistral Medium 3 66.1%
  77. 77 Magistral Small 1.0 66%
  78. 78 Gemma 3 27B 64.9%
  79. 79 Qwen3.5-2B 64.2%
  80. 80 Mistral Small 3.1 64%
  81. 81 Kimi-VL-A3B-Thinking-2506 64%
  82. 82 Mistral Small 3.2 62.5%
  83. 83 Gemini 1.0 Ultra 62.4%
  84. 84 Gemini 1.5 Pro May 2024 62.2%
  85. 85 Kimi-VL-A3B-Thinking 61.7%
  86. 86 Gemma 3 12B 59.6%
  87. 87 Claude 3 Opus 59.4%
  88. 88 GPT-4o mini 59.4%
  89. 89 Qwen2.5-Omni-7B 59.2%
  90. 90 Gemini 1.5 Pro Feb 2024 58.5%
  91. 91 GPT-4.1 nano 55.4%
  92. 92 BAGEL-7B-MoT 55.3%
  93. 93 Phi-4-multimodal 55.1%
  94. 94 Phi-4-Reasoning-Vision-15B 54.3%
  95. 95 Claude 3 Sonnet 53.1%
  96. 96 Claude 3 Haiku 50.2%
  97. 97 Qwen3.5-0.8B 49%
  98. 98 Gemma 3 4B 48.8%
  99. 99 LFM2.5-VL-3B 48.4%
  100. 100 Llama-3.1-Nemotron-Nano-VL-8B-V1 48.2%
  101. 101 Phi-3.5-vision-instruct 43%
  102. 102 Janus-Pro-7B 41%
  103. 103 LFM2-VL-1.6B 39.7%
  104. 104 North Micro Vision Instruct 32.9%

Source: Labs’ model cards

137 models. Scroll sideways for the rest.

  1. 85.4 GPT-5.1
  2. 84.2 GPT-5
  3. 84.0 Gemini 2.5 Deep Think
  4. 82.9 o3
  5. 81.6 o4-mini
  6. 80.7 Claude Opus 4.5
  7. 80.1 dots.vlm1
  8. 79.7 Gemini 2.5 Flash
  9. 79.6 Gemini 2.5 Pro
  10. 78.7 Qwen3-VL-235B-A22B
  11. 78.2 o1
  12. 78.0 Grok 3
  13. 77.9 Seed1.5-VL
  14. 77.8 Claude Sonnet 4.5
  15. 77.7 Intern-S1
  16. 77.1 Claude Opus 4.1
  17. 76.5 Claude Opus 4
  18. 76.1 Llama 4 Behemoth
  19. 76.0 Skywork-R1V3-38B
  20. 75.4 GLM-4.5V
  21. 75.0 Claude 3.7 Sonnet
  22. 74.8 Seed1.6-Thinking
  23. 74.4 GPT-4.5
  24. 74.4 Claude Sonnet 4
  25. 73.6 Skywork-R1V2-38B
  26. 73.4 Llama 4 Maverick
  27. 72.7 Gemini 2.0 Pro
  28. 72.2 InternVL3-78B
  29. 71.7 Gemini 2.0 Flash
  30. 70.7 GPT-4o
  31. 70.6 MiMo-VL-7B-RL-2508
  32. 70.3 QVQ-72B-Preview
  33. 70.1 InternVL2_5-78B
  34. 70.1 InternVL3-38B
  35. 69.4 Llama 4 Scout
  36. 69.1 GPT-4o
  37. 69.0 Skywork-R1V-38B
  38. 68.3 Claude 3.5 Sonnet
  39. 68.0 Gemini 2.0 Flash-Lite
  40. 68.0 Amazon Nova Premier
  41. 68.0 GLM-4.1V-9B-Thinking
  42. 67.1 InternVL3-14B
  43. 66.7 MiMo-VL-7B-RL
  44. 65.6 Ovis2-34B
  45. 64.9 Gemma 3 27B
  46. 64.6 MiMo-VL-7B-SFT
  47. 64.5 Qwen2-VL-72B-Instruct
  48. 64.5 Qwen2.5-VL-72B
  49. 63.9 InternVL2.5-38B
  50. 62.7 InternVL3-8B
  51. 62.2 Gemini 1.5 Pro
  52. 62.0 InternVL2-Pro
  53. 62.0 Amazon Nova Pro
  54. 60.3 Llama 3.2 90B
  55. 60.0 InternVL2.5-26B
  56. 59.7 NVLM-D-72B
  57. 59.6 Ovis2-16B
  58. 59.6 Gemma 3 12B
  59. 59.4 Gemini 1.0 Ultra
  60. 59.4 Claude 3 Opus
  61. 59.4 GPT-4o mini
  62. 59.0 Ovis2-8B
  63. 58.6 Qwen2.5-VL-7B
  64. 58.3 InternVL2-Llama3-76B
  65. 58.3 Qianfan-VL-70B
  66. 57.7 InternVL3-9B
  67. 57.0 Kimi-VL-A3B-Instruct
  68. 56.8 GPT-4V
  69. 56.8 LLaVA-OneVision 72B
  70. 56.3 Reka Core
  71. 56.1 Gemini 1.5 Flash
  72. 56.0 InternVL2.5-8B
  73. 55.8 Eagle2.5-8B
  74. 55.2 InternVL2-40B
  75. 54.9 Aria
  76. 53.3 Reka Flash
  77. 53.1 Claude 3 Sonnet
  78. 53.1 Qwen2.5-VL-3B
  79. 51.6 InternVL-Chat-V1-2
  80. 51.4 Qwen-VL-Max
  81. 51.2 InternVL2-8B
  82. 51.1 DeepSeek-VL2
  83. 50.8 MAmmoTH-VL-8B
  84. 50.7 Llama 3.2 11B
  85. 50.2 Claude 3 Haiku
  86. 49.9 LLaVA-NeXT-72B
  87. 49.8 Ovis1.5-Gemma2-9B
  88. 49.8 MiniCPM-V-2_6
  89. 49.7 Cambrian-1-34B
  90. 48.8 LLaVA-OneVision 7B
  91. 48.8 Gemma 3 4B
  92. 48.6 InternVL3-2B
  93. 48.1 LLaVA-v1.6-34B
  94. 48.0 DeepSeek-VL2-Small
  95. 48.0 Ovis2-4B
  96. 47.9 Gemini 1.0 Pro
  97. 47.4 Aquila-VL-2B
  98. 47.1 Qianfan-VL-8B
  99. 46.6 Idefics3-8B-Llama3
  100. 46.4 Qianfan-VL-3B
  101. 45.9 Yi-VL-34B
  102. 45.8 MiniCPM-Llama3-V 2.5
  103. 45.3 Ovis2-2B
  104. 45.2 Qwen-VL-Plus
  105. 45.1 Aya Vision 32B
  106. 43.6 InternVL2.5-2B
  107. 43.4 InternVL3-1B
  108. 43.0 InternLM-XComposer2-VL-7B
  109. 43.0 Phi-3.5-vision-instruct
  110. 42.8 Reka Edge
  111. 42.7 Cambrian-1-8B
  112. 41.4 Bunny-v1.0-4B
  113. 41.1 OmniLMM-12B
  114. 40.9 InternVL2.5-1B
  115. 40.7 DeepSeek-VL2-Tiny
  116. 40.0 Cambrian-1-13B
  117. 39.9 Aya Vision 8B
  118. 39.1 Yi-VL-6B
  119. 39.1 InternVL-Chat-V1-1
  120. 38.2 Bunny-v1.0-3B
  121. 37.2 MiniCPM-V
  122. 37.1 MiniCPM-V 2.0
  123. 36.4 LLaVA-v1.5-13B
  124. 36.3 Emu2-Chat
  125. 36.2 llava-v1.6-vicuna-13b
  126. 36.0 Ovis2-1B
  127. 35.9 Qwen-VL-Chat
  128. 35.8 llava-v1.6-vicuna-7b
  129. 35.7 InstructBLIP FLAN-T5-XXL
  130. 35.4 BLIP-2 FLAN-T5-XXL
  131. 35.3 llava-v1.6-mistral-7b
  132. 34.4 BLIP-2 FLAN-T5-XL
  133. 32.9 InstructBLIP FLAN-T5-XL
  134. 32.7 mPLUG-Owl2
  135. 32.1 CogVLM-17B-Chat
  136. 27.9 Fuyu-8B
  137. 24.4 Kosmos-2
  1. 1 GPT-5.1 85.4%
  2. 2 GPT-5 thinking 84.2%
  3. 3 Gemini 2.5 Deep Think 84%
  4. 4 o3 82.9%
  5. 5 o4-mini 81.6%
  6. 6 Claude Opus 4.5 80.7%
  7. 7 dots.vlm1 80.1%
  8. 8 Gemini 2.5 Flash May 2025 79.7%
  9. 9 Gemini 2.5 Pro May 2025 79.6%
  10. 10 Qwen3-VL-235B-A22B 78.7%
  11. 11 o1 78.2%
  12. 12 Grok 3 78%
  13. 13 Seed1.5-VL thinking 77.9%
  14. 14 Claude Sonnet 4.5 77.8%
  15. 15 Intern-S1 77.7%
  16. 16 Claude Opus 4.1 77.1%
  17. 17 Claude Opus 4 76.5%
  18. 18 Llama 4 Behemoth 76.1%
  19. 19 Skywork-R1V3-38B 76%
  20. 20 GLM-4.5V thinking 75.4%
  21. 21 Claude 3.7 Sonnet 75%
  22. 22 Seed1.6-Thinking 74.8%
  23. 23 GPT-4.5 74.4%
  24. 24 Claude Sonnet 4 74.4%
  25. 25 Skywork-R1V2-38B 73.6%
  26. 26 Llama 4 Maverick 73.4%
  27. 27 Gemini 2.0 Pro 72.7%
  28. 28 InternVL3-78B 72.2%
  29. 29 Gemini 2.0 Flash Feb 2025 71.7%
  30. 30 GPT-4o Nov 2024 70.7%
  31. 31 MiMo-VL-7B-RL-2508 thinking 70.6%
  32. 32 QVQ-72B-Preview 70.3%
  33. 33 InternVL2_5-78B 70.1%
  34. 34 InternVL3-38B 70.1%
  35. 35 Llama 4 Scout 69.4%
  36. 36 GPT-4o May 2024 69.1%
  37. 37 Skywork-R1V-38B 69%
  38. 38 Claude 3.5 Sonnet 68.3%
  39. 39 Gemini 2.0 Flash-Lite 68%
  40. 40 Amazon Nova Premier 68%
  41. 41 GLM-4.1V-9B-Thinking thinking 68%
  42. 42 InternVL3-14B 67.1%
  43. 43 MiMo-VL-7B-RL 66.7%
  44. 44 Ovis2-34B 65.6%
  45. 45 Gemma 3 27B 64.9%
  46. 46 MiMo-VL-7B-SFT 64.6%
  47. 47 Qwen2-VL-72B-Instruct 64.5%
  48. 48 Qwen2.5-VL-72B 64.5%
  49. 49 InternVL2.5-38B 63.9%
  50. 50 InternVL3-8B 62.7%
  51. 51 Gemini 1.5 Pro May 2024 62.2%
  52. 52 InternVL2-Pro 62%
  53. 53 Amazon Nova Pro 62%
  54. 54 Llama 3.2 90B 60.3%
  55. 55 InternVL2.5-26B 60%
  56. 56 NVLM-D-72B 59.7%
  57. 57 Ovis2-16B 59.6%
  58. 58 Gemma 3 12B 59.6%
  59. 59 Gemini 1.0 Ultra 59.4%
  60. 60 Claude 3 Opus 59.4%
  61. 61 GPT-4o mini 59.4%
  62. 62 Ovis2-8B 59%
  63. 63 Qwen2.5-VL-7B 58.6%
  64. 64 InternVL2-Llama3-76B 58.3%
  65. 65 Qianfan-VL-70B 58.3%
  66. 66 InternVL3-9B 57.7%
  67. 67 Kimi-VL-A3B-Instruct 57%
  68. 68 GPT-4V 56.8%
  69. 69 LLaVA-OneVision 72B 56.8%
  70. 70 Reka Core 56.3%
  71. 71 Gemini 1.5 Flash May 2024 56.1%
  72. 72 InternVL2.5-8B 56%
  73. 73 Eagle2.5-8B 55.8%
  74. 74 InternVL2-40B 55.2%
  75. 75 Aria 54.9%
  76. 76 Reka Flash 53.3%
  77. 77 Claude 3 Sonnet 53.1%
  78. 78 Qwen2.5-VL-3B 53.1%
  79. 79 InternVL-Chat-V1-2 51.6%
  80. 80 Qwen-VL-Max 51.4%
  81. 81 InternVL2-8B 51.2%
  82. 82 DeepSeek-VL2 51.1%
  83. 83 MAmmoTH-VL-8B 50.8%
  84. 84 Llama 3.2 11B 50.7%
  85. 85 Claude 3 Haiku 50.2%
  86. 86 LLaVA-NeXT-72B 49.9%
  87. 87 Ovis1.5-Gemma2-9B 49.8%
  88. 88 MiniCPM-V-2_6 49.8%
  89. 89 Cambrian-1-34B 49.7%
  90. 90 LLaVA-OneVision 7B 48.8%
  91. 91 Gemma 3 4B 48.8%
  92. 92 InternVL3-2B 48.6%
  93. 93 LLaVA-v1.6-34B 48.1%
  94. 94 DeepSeek-VL2-Small 48%
  95. 95 Ovis2-4B 48%
  96. 96 Gemini 1.0 Pro 47.9%
  97. 97 Aquila-VL-2B 47.4%
  98. 98 Qianfan-VL-8B 47.1%
  99. 99 Idefics3-8B-Llama3 46.6%
  100. 100 Qianfan-VL-3B 46.4%
  101. 101 Yi-VL-34B 45.9%
  102. 102 MiniCPM-Llama3-V 2.5 45.8%
  103. 103 Ovis2-2B 45.3%
  104. 104 Qwen-VL-Plus 45.2%
  105. 105 Aya Vision 32B 45.1%
  106. 106 InternVL2.5-2B 43.6%
  107. 107 InternVL3-1B 43.4%
  108. 108 InternLM-XComposer2-VL-7B 43%
  109. 109 Phi-3.5-vision-instruct 43%
  110. 110 Reka Edge 42.8%
  111. 111 Cambrian-1-8B 42.7%
  112. 112 Bunny-v1.0-4B 41.4%
  113. 113 OmniLMM-12B 41.1%
  114. 114 InternVL2.5-1B 40.9%
  115. 115 DeepSeek-VL2-Tiny 40.7%
  116. 116 Cambrian-1-13B 40%
  117. 117 Aya Vision 8B 39.9%
  118. 118 Yi-VL-6B 39.1%
  119. 119 InternVL-Chat-V1-1 39.1%
  120. 120 Bunny-v1.0-3B 38.2%
  121. 121 MiniCPM-V 37.2%
  122. 122 MiniCPM-V 2.0 37.1%
  123. 123 LLaVA-v1.5-13B 36.4%
  124. 124 Emu2-Chat 36.3%
  125. 125 llava-v1.6-vicuna-13b 36.2%
  126. 126 Ovis2-1B 36%
  127. 127 Qwen-VL-Chat 35.9%
  128. 128 llava-v1.6-vicuna-7b 35.8%
  129. 129 InstructBLIP FLAN-T5-XXL 35.7%
  130. 130 BLIP-2 FLAN-T5-XXL 35.4%
  131. 131 llava-v1.6-mistral-7b 35.3%
  132. 132 BLIP-2 FLAN-T5-XL 34.4%
  133. 133 InstructBLIP FLAN-T5-XL 32.9%
  134. 134 mPLUG-Owl2 32.7%
  135. 135 CogVLM-17B-Chat 32.1%
  136. 136 Fuyu-8B 27.9%
  137. 137 Kosmos-2 24.4%

Source: Official MMMU leaderboard

202 models. Scroll sideways for the rest.

  1. 86.0 Qwen 3.6 Plus
  2. 85.4 GPT-5.1
  3. 85.4 Seed2.0 Pro
  4. 85.0 Qwen3.5 397B-A17B
  5. 84.3 Kimi K2.5
  6. 84.2 GPT-5
  7. 84.0 Gemini 2.5 Deep Think
  8. 83.9 Qwen3.5-122B-A10B
  9. 83.4 Seed1.8
  10. 82.9 o3
  11. 82.9 Qwen3.6 27B
  12. 82.3 Qwen3.5-27B
  13. 82.0 Gemini 2.5 Pro
  14. 81.7 Gemini 2.5 Pro
  15. 81.7 Qwen 3.6 35B-A3B
  16. 81.6 o4-mini
  17. 81.6 GPT-5 mini
  18. 81.4 Qwen3.5-35B-A3B
  19. 80.7 gemini-robotics-er-1.5-preview
  20. 80.7 Claude Opus 4.5
  21. 80.6 Qwen3-VL-235B-A22B
  22. 80.3 Gemini 2.5 Flash
  23. 80.2 MiniCPM-V-4.7-35B-A3B
  24. 80.1 dots.vlm1
  25. 80.1 Qwen3.5-Omni-Plus
  26. 79.7 Gemini 2.5 Flash
  27. 79.7 Gemini 2.5 Flash
  28. 79.6 Gemini 2.5 Pro
  29. 78.7 EXAONE 4.5 33B
  30. 78.4 Qwen3.5-9B
  31. 78.2 o1
  32. 78.1 STEP3-VL-10B
  33. 78.0 Grok 3
  34. 77.9 Seed1.5-VL
  35. 77.8 Claude Sonnet 4.5
  36. 77.7 Intern-S1
  37. 77.7 InternVL3.5-241B-A28B
  38. 77.6 Qwen3.5-4B
  39. 77.1 Claude Opus 4.1
  40. 76.7 Gemini 2.5 Flash
  41. 76.5 Claude Opus 4
  42. 76.1 Llama 4 Behemoth
  43. 76.0 Skywork-R1V3-38B
  44. 76.0 GLM-4.6V
  45. 75.6 GPT-5 nano
  46. 75.4 Gemini 2.0 Flash Thinking
  47. 75.4 GLM-4.5V
  48. 75.3 Keye-VL-2.0-30B-A3B
  49. 75.1 Command A+
  50. 75.0 Claude 3.7 Sonnet
  51. 74.8 GPT-4.1
  52. 74.8 Seed1.6-Thinking
  53. 74.4 GPT-4.5
  54. 74.4 Claude Sonnet 4
  55. 74.2 Step 3
  56. 73.6 Skywork-R1V2-38B
  57. 73.4 Llama 4 Maverick
  58. 73.2 Claude Haiku 4.5
  59. 72.9 Gemini 2.5 Flash-Lite
  60. 72.7 Gemini 2.0 Pro
  61. 72.7 GPT-4.1 mini
  62. 72.2 InternVL3-78B
  63. 72.2 ERNIE-4.5-VL-28B-A3B-Thinking
  64. 72.0 Gemini 2.5 Flash-Lite
  65. 71.7 Gemini 2.0 Flash
  66. 70.8 Nemotron 3 Nano Omni 30B-A3B
  67. 70.7 GPT-4o
  68. 70.7 Gemini 2.0 Flash
  69. 70.7 LongCat-Flash-Omni
  70. 70.6 MiMo-VL-7B-RL-2508
  71. 70.4 Claude 3.5 Sonnet (October 2024)
  72. 70.3 QVQ-72B-Preview
  73. 70.2 Qwen2.5-VL-72B
  74. 70.1 InternVL2_5-78B
  75. 70.1 InternVL3-38B
  76. 70.0 Kimi k1.5
  77. 70.0 Magistral Medium 1.0
  78. 69.4 Grok-3 mini
  79. 69.4 Llama 4 Scout
  80. 69.1 GPT-4o
  81. 69.1 Qwen3-Omni-30B-A3B
  82. 69.0 Skywork-R1V-38B
  83. 68.3 Claude 3.5 Sonnet
  84. 68.0 Gemini 2.0 Flash-Lite
  85. 68.0 Amazon Nova Premier
  86. 68.0 GLM-4.1V-9B-Thinking
  87. 68.0 Nemotron Nano 12B v2 VL
  88. 67.1 InternVL3-14B
  89. 66.7 MiMo-VL-7B-RL
  90. 66.1 Grok-2
  91. 66.1 Mistral Medium 3
  92. 66.0 Magistral Small 1.0
  93. 65.6 Ovis2-34B
  94. 64.9 Gemma 3 27B
  95. 64.6 MiMo-VL-7B-SFT
  96. 64.5 Qwen2-VL-72B-Instruct
  97. 64.2 Qwen3.5-2B
  98. 64.0 Mistral Small 3.1
  99. 64.0 Kimi-VL-A3B-Thinking-2506
  100. 63.9 InternVL2.5-38B
  101. 62.7 InternVL3-8B
  102. 62.5 Mistral Small 3.2
  103. 62.4 Gemini 1.0 Ultra
  104. 62.2 Gemini 1.5 Pro
  105. 62.0 InternVL2-Pro
  106. 62.0 Amazon Nova Pro
  107. 61.7 Kimi-VL-A3B-Thinking
  108. 60.3 Llama 3.2 90B
  109. 60.0 InternVL2.5-26B
  110. 59.7 NVLM-D-72B
  111. 59.6 Ovis2-16B
  112. 59.6 Gemma 3 12B
  113. 59.4 Claude 3 Opus
  114. 59.4 GPT-4o mini
  115. 59.2 Qwen2.5-Omni-7B
  116. 59.0 Ovis2-8B
  117. 58.6 Qwen2.5-VL-7B
  118. 58.5 Gemini 1.5 Pro
  119. 58.3 InternVL2-Llama3-76B
  120. 58.3 Qianfan-VL-70B
  121. 57.7 InternVL3-9B
  122. 57.0 Kimi-VL-A3B-Instruct
  123. 56.8 GPT-4V
  124. 56.8 LLaVA-OneVision 72B
  125. 56.3 Reka Core
  126. 56.1 Gemini 1.5 Flash
  127. 56.0 InternVL2.5-8B
  128. 55.8 Eagle2.5-8B
  129. 55.4 GPT-4.1 nano
  130. 55.3 BAGEL-7B-MoT
  131. 55.2 InternVL2-40B
  132. 55.1 Phi-4-multimodal
  133. 54.9 Aria
  134. 54.3 Phi-4-Reasoning-Vision-15B
  135. 53.3 Reka Flash
  136. 53.1 Claude 3 Sonnet
  137. 53.1 Qwen2.5-VL-3B
  138. 51.6 InternVL-Chat-V1-2
  139. 51.4 Qwen-VL-Max
  140. 51.2 InternVL2-8B
  141. 51.1 DeepSeek-VL2
  142. 50.8 MAmmoTH-VL-8B
  143. 50.7 Llama 3.2 11B
  144. 50.2 Claude 3 Haiku
  145. 49.9 LLaVA-NeXT-72B
  146. 49.8 Ovis1.5-Gemma2-9B
  147. 49.8 MiniCPM-V-2_6
  148. 49.7 Cambrian-1-34B
  149. 49.0 Qwen3.5-0.8B
  150. 48.8 LLaVA-OneVision 7B
  151. 48.8 Gemma 3 4B
  152. 48.6 InternVL3-2B
  153. 48.4 LFM2.5-VL-3B
  154. 48.2 Llama-3.1-Nemotron-Nano-VL-8B-V1
  155. 48.1 LLaVA-v1.6-34B
  156. 48.0 DeepSeek-VL2-Small
  157. 48.0 Ovis2-4B
  158. 47.9 Gemini 1.0 Pro
  159. 47.4 Aquila-VL-2B
  160. 47.1 Qianfan-VL-8B
  161. 46.6 Idefics3-8B-Llama3
  162. 46.4 Qianfan-VL-3B
  163. 45.9 Yi-VL-34B
  164. 45.8 MiniCPM-Llama3-V 2.5
  165. 45.3 Ovis2-2B
  166. 45.2 Qwen-VL-Plus
  167. 45.1 Aya Vision 32B
  168. 43.6 InternVL2.5-2B
  169. 43.4 InternVL3-1B
  170. 43.0 InternLM-XComposer2-VL-7B
  171. 43.0 Phi-3.5-vision-instruct
  172. 42.8 Reka Edge
  173. 42.7 Cambrian-1-8B
  174. 41.4 Bunny-v1.0-4B
  175. 41.1 OmniLMM-12B
  176. 41.0 Janus-Pro-7B
  177. 40.9 InternVL2.5-1B
  178. 40.7 DeepSeek-VL2-Tiny
  179. 40.0 Cambrian-1-13B
  180. 39.9 Aya Vision 8B
  181. 39.7 LFM2-VL-1.6B
  182. 39.1 Yi-VL-6B
  183. 39.1 InternVL-Chat-V1-1
  184. 38.2 Bunny-v1.0-3B
  185. 37.2 MiniCPM-V
  186. 37.1 MiniCPM-V 2.0
  187. 36.4 LLaVA-v1.5-13B
  188. 36.3 Emu2-Chat
  189. 36.2 llava-v1.6-vicuna-13b
  190. 36.0 Ovis2-1B
  191. 35.9 Qwen-VL-Chat
  192. 35.8 llava-v1.6-vicuna-7b
  193. 35.7 InstructBLIP FLAN-T5-XXL
  194. 35.4 BLIP-2 FLAN-T5-XXL
  195. 35.3 llava-v1.6-mistral-7b
  196. 34.4 BLIP-2 FLAN-T5-XL
  197. 32.9 InstructBLIP FLAN-T5-XL
  198. 32.9 North Micro Vision Instruct
  199. 32.7 mPLUG-Owl2
  200. 32.1 CogVLM-17B-Chat
  201. 27.9 Fuyu-8B
  202. 24.4 Kosmos-2
  1. 1 Qwen 3.6 Plus 86%
  2. 2 GPT-5.1 85.4%
  3. 3 Seed2.0 Pro 85.4%
  4. 4 Qwen3.5 397B-A17B 85%
  5. 5 Kimi K2.5 84.3%
  6. 6 GPT-5 thinking 84.2%
  7. 7 Gemini 2.5 Deep Think 84%
  8. 8 Qwen3.5-122B-A10B 83.9%
  9. 9 Seed1.8 83.4%
  10. 10 o3 82.9%
  11. 11 Qwen3.6 27B 82.9%
  12. 12 Qwen3.5-27B 82.3%
  13. 13 Gemini 2.5 Pro Jun 2025 82%
  14. 14 Gemini 2.5 Pro Mar 2025 81.7%
  15. 15 Qwen 3.6 35B-A3B 81.7%
  16. 16 o4-mini 81.6%
  17. 17 GPT-5 mini 81.6%
  18. 18 Qwen3.5-35B-A3B 81.4%
  19. 19 gemini-robotics-er-1.5-preview 80.7%
  20. 20 Claude Opus 4.5 80.7%
  21. 21 Qwen3-VL-235B-A22B 80.6%
  22. 22 Gemini 2.5 Flash Sep 2025 80.3%
  23. 23 MiniCPM-V-4.7-35B-A3B 80.2%
  24. 24 dots.vlm1 80.1%
  25. 25 Qwen3.5-Omni-Plus 80.1%
  26. 26 Gemini 2.5 Flash May 2025 79.7%
  27. 27 Gemini 2.5 Flash Jun 2025 79.7%
  28. 28 Gemini 2.5 Pro May 2025 79.6%
  29. 29 EXAONE 4.5 33B 78.7%
  30. 30 Qwen3.5-9B 78.4%
  31. 31 o1 78.2%
  32. 32 STEP3-VL-10B 78.1%
  33. 33 Grok 3 78%
  34. 34 Seed1.5-VL thinking 77.9%
  35. 35 Claude Sonnet 4.5 77.8%
  36. 36 Intern-S1 77.7%
  37. 37 InternVL3.5-241B-A28B 77.7%
  38. 38 Qwen3.5-4B 77.6%
  39. 39 Claude Opus 4.1 77.1%
  40. 40 Gemini 2.5 Flash Apr 2025 76.7%
  41. 41 Claude Opus 4 76.5%
  42. 42 Llama 4 Behemoth 76.1%
  43. 43 Skywork-R1V3-38B 76%
  44. 44 GLM-4.6V 76%
  45. 45 GPT-5 nano 75.6%
  46. 46 Gemini 2.0 Flash Thinking Jan 2025 75.4%
  47. 47 GLM-4.5V thinking 75.4%
  48. 48 Keye-VL-2.0-30B-A3B 75.3%
  49. 49 Command A+ 75.1%
  50. 50 Claude 3.7 Sonnet 75%
  51. 51 GPT-4.1 74.8%
  52. 52 Seed1.6-Thinking 74.8%
  53. 53 GPT-4.5 74.4%
  54. 54 Claude Sonnet 4 74.4%
  55. 55 Step 3 74.2%
  56. 56 Skywork-R1V2-38B 73.6%
  57. 57 Llama 4 Maverick 73.4%
  58. 58 Claude Haiku 4.5 73.2%
  59. 59 Gemini 2.5 Flash-Lite Jun 2025 72.9%
  60. 60 Gemini 2.0 Pro 72.7%
  61. 61 GPT-4.1 mini 72.7%
  62. 62 InternVL3-78B 72.2%
  63. 63 ERNIE-4.5-VL-28B-A3B-Thinking 72.2%
  64. 64 Gemini 2.5 Flash-Lite Sep 2025 72%
  65. 65 Gemini 2.0 Flash Feb 2025 71.7%
  66. 66 Nemotron 3 Nano Omni 30B-A3B 70.8%
  67. 67 GPT-4o Nov 2024 70.7%
  68. 68 Gemini 2.0 Flash Dec 2024 70.7%
  69. 69 LongCat-Flash-Omni 70.7%
  70. 70 MiMo-VL-7B-RL-2508 thinking 70.6%
  71. 71 Claude 3.5 Sonnet (October 2024) 70.4%
  72. 72 QVQ-72B-Preview 70.3%
  73. 73 Qwen2.5-VL-72B 70.2%
  74. 74 InternVL2_5-78B 70.1%
  75. 75 InternVL3-38B 70.1%
  76. 76 Kimi k1.5 70%
  77. 77 Magistral Medium 1.0 70%
  78. 78 Grok-3 mini 69.4%
  79. 79 Llama 4 Scout 69.4%
  80. 80 GPT-4o May 2024 69.1%
  81. 81 Qwen3-Omni-30B-A3B 69.1%
  82. 82 Skywork-R1V-38B 69%
  83. 83 Claude 3.5 Sonnet 68.3%
  84. 84 Gemini 2.0 Flash-Lite 68%
  85. 85 Amazon Nova Premier 68%
  86. 86 GLM-4.1V-9B-Thinking thinking 68%
  87. 87 Nemotron Nano 12B v2 VL 68%
  88. 88 InternVL3-14B 67.1%
  89. 89 MiMo-VL-7B-RL 66.7%
  90. 90 Grok-2 Aug 2024 66.1%
  91. 91 Mistral Medium 3 66.1%
  92. 92 Magistral Small 1.0 66%
  93. 93 Ovis2-34B 65.6%
  94. 94 Gemma 3 27B 64.9%
  95. 95 MiMo-VL-7B-SFT 64.6%
  96. 96 Qwen2-VL-72B-Instruct 64.5%
  97. 97 Qwen3.5-2B 64.2%
  98. 98 Mistral Small 3.1 64%
  99. 99 Kimi-VL-A3B-Thinking-2506 64%
  100. 100 InternVL2.5-38B 63.9%
  101. 101 InternVL3-8B 62.7%
  102. 102 Mistral Small 3.2 62.5%
  103. 103 Gemini 1.0 Ultra 62.4%
  104. 104 Gemini 1.5 Pro May 2024 62.2%
  105. 105 InternVL2-Pro 62%
  106. 106 Amazon Nova Pro 62%
  107. 107 Kimi-VL-A3B-Thinking 61.7%
  108. 108 Llama 3.2 90B 60.3%
  109. 109 InternVL2.5-26B 60%
  110. 110 NVLM-D-72B 59.7%
  111. 111 Ovis2-16B 59.6%
  112. 112 Gemma 3 12B 59.6%
  113. 113 Claude 3 Opus 59.4%
  114. 114 GPT-4o mini 59.4%
  115. 115 Qwen2.5-Omni-7B 59.2%
  116. 116 Ovis2-8B 59%
  117. 117 Qwen2.5-VL-7B 58.6%
  118. 118 Gemini 1.5 Pro Feb 2024 58.5%
  119. 119 InternVL2-Llama3-76B 58.3%
  120. 120 Qianfan-VL-70B 58.3%
  121. 121 InternVL3-9B 57.7%
  122. 122 Kimi-VL-A3B-Instruct 57%
  123. 123 GPT-4V 56.8%
  124. 124 LLaVA-OneVision 72B 56.8%
  125. 125 Reka Core 56.3%
  126. 126 Gemini 1.5 Flash May 2024 56.1%
  127. 127 InternVL2.5-8B 56%
  128. 128 Eagle2.5-8B 55.8%
  129. 129 GPT-4.1 nano 55.4%
  130. 130 BAGEL-7B-MoT 55.3%
  131. 131 InternVL2-40B 55.2%
  132. 132 Phi-4-multimodal 55.1%
  133. 133 Aria 54.9%
  134. 134 Phi-4-Reasoning-Vision-15B 54.3%
  135. 135 Reka Flash 53.3%
  136. 136 Claude 3 Sonnet 53.1%
  137. 137 Qwen2.5-VL-3B 53.1%
  138. 138 InternVL-Chat-V1-2 51.6%
  139. 139 Qwen-VL-Max 51.4%
  140. 140 InternVL2-8B 51.2%
  141. 141 DeepSeek-VL2 51.1%
  142. 142 MAmmoTH-VL-8B 50.8%
  143. 143 Llama 3.2 11B 50.7%
  144. 144 Claude 3 Haiku 50.2%
  145. 145 LLaVA-NeXT-72B 49.9%
  146. 146 Ovis1.5-Gemma2-9B 49.8%
  147. 147 MiniCPM-V-2_6 49.8%
  148. 148 Cambrian-1-34B 49.7%
  149. 149 Qwen3.5-0.8B 49%
  150. 150 LLaVA-OneVision 7B 48.8%
  151. 151 Gemma 3 4B 48.8%
  152. 152 InternVL3-2B 48.6%
  153. 153 LFM2.5-VL-3B 48.4%
  154. 154 Llama-3.1-Nemotron-Nano-VL-8B-V1 48.2%
  155. 155 LLaVA-v1.6-34B 48.1%
  156. 156 DeepSeek-VL2-Small 48%
  157. 157 Ovis2-4B 48%
  158. 158 Gemini 1.0 Pro 47.9%
  159. 159 Aquila-VL-2B 47.4%
  160. 160 Qianfan-VL-8B 47.1%
  161. 161 Idefics3-8B-Llama3 46.6%
  162. 162 Qianfan-VL-3B 46.4%
  163. 163 Yi-VL-34B 45.9%
  164. 164 MiniCPM-Llama3-V 2.5 45.8%
  165. 165 Ovis2-2B 45.3%
  166. 166 Qwen-VL-Plus 45.2%
  167. 167 Aya Vision 32B 45.1%
  168. 168 InternVL2.5-2B 43.6%
  169. 169 InternVL3-1B 43.4%
  170. 170 InternLM-XComposer2-VL-7B 43%
  171. 171 Phi-3.5-vision-instruct 43%
  172. 172 Reka Edge 42.8%
  173. 173 Cambrian-1-8B 42.7%
  174. 174 Bunny-v1.0-4B 41.4%
  175. 175 OmniLMM-12B 41.1%
  176. 176 Janus-Pro-7B 41%
  177. 177 InternVL2.5-1B 40.9%
  178. 178 DeepSeek-VL2-Tiny 40.7%
  179. 179 Cambrian-1-13B 40%
  180. 180 Aya Vision 8B 39.9%
  181. 181 LFM2-VL-1.6B 39.7%
  182. 182 Yi-VL-6B 39.1%
  183. 183 InternVL-Chat-V1-1 39.1%
  184. 184 Bunny-v1.0-3B 38.2%
  185. 185 MiniCPM-V 37.2%
  186. 186 MiniCPM-V 2.0 37.1%
  187. 187 LLaVA-v1.5-13B 36.4%
  188. 188 Emu2-Chat 36.3%
  189. 189 llava-v1.6-vicuna-13b 36.2%
  190. 190 Ovis2-1B 36%
  191. 191 Qwen-VL-Chat 35.9%
  192. 192 llava-v1.6-vicuna-7b 35.8%
  193. 193 InstructBLIP FLAN-T5-XXL 35.7%
  194. 194 BLIP-2 FLAN-T5-XXL 35.4%
  195. 195 llava-v1.6-mistral-7b 35.3%
  196. 196 BLIP-2 FLAN-T5-XL 34.4%
  197. 197 InstructBLIP FLAN-T5-XL 32.9%
  198. 198 North Micro Vision Instruct 32.9%
  199. 199 mPLUG-Owl2 32.7%
  200. 200 CogVLM-17B-Chat 32.1%
  201. 201 Fuyu-8B 27.9%
  202. 202 Kosmos-2 24.4%

Sources: Labs’ model cards and official MMMU leaderboard

#ModelScoreSettingDateSource
1 Qwen 3.6 Plus 86% Apr 2026 Lab model card
2 GPT-5.1 85.4% Nov 2025 Lab model card
3 Seed2.0 Pro 85.4% Feb 2026 Lab model card
4 Qwen3.5 397B-A17B 85% Feb 2026 Lab model card
5 Kimi K2.5 84.3% Jan 2026 Lab model card
6 GPT-5 84.2% Aug 2025 Lab model card
7 Qwen3.5-122B-A10B 83.9% Feb 2026 Lab model card
8 Seed1.8 83.4% Dec 2025 Lab model card
9 o3 82.9% Apr 2025 Lab model card
10 Qwen3.6 27B 82.9% Apr 2026 Lab model card
11 Qwen3.5-27B 82.3% Feb 2026 Lab model card
12 Gemini 2.5 Pro Jun 2025 82% Jun 2025 Lab model card
13 Gemini 2.5 Pro Mar 2025 81.7% Mar 2025 Lab model card
14 Qwen 3.6 35B-A3B 81.7% Apr 2026 Lab model card
15 o4-mini 81.6% Apr 2025 Lab model card
16 GPT-5 mini 81.6% Aug 2025 Lab model card
17 Qwen3.5-35B-A3B 81.4% Feb 2026 Lab model card
18 gemini-robotics-er-1.5-preview 80.7% Sep 2025 Lab model card
19 Claude Opus 4.5 80.7% Nov 2025 Lab model card
20 Qwen3-VL-235B-A22B 80.6% Sep 2025 Lab model card
21 Gemini 2.5 Flash Sep 2025 80.3% Sep 2025 Lab model card
22 MiniCPM-V-4.7-35B-A3B 80.2% Oct 2026 Lab model card
23 Qwen3.5-Omni-Plus 80.1% Mar 2026 Lab model card
24 Gemini 2.5 Flash Jun 2025 79.7% Jun 2025 Lab model card
25 EXAONE 4.5 33B 78.7% Apr 2026 Lab model card
26 Qwen3.5-9B 78.4% Mar 2026 Lab model card
27 STEP3-VL-10B 78.1% Jan 2026 Lab model card
28 Grok 3 78% Feb 2025 Lab model card
29 Seed1.5-VL 77.9% May 2025 Lab model card
30 Claude Sonnet 4.5 77.8% Sep 2025 Lab model card
31 Intern-S1 77.7% Jul 2025 Lab model card
32 InternVL3.5-241B-A28B 77.7% Aug 2025 Lab model card
33 Qwen3.5-4B 77.6% Mar 2026 Lab model card
34 o1 77.3% Dec 2024 Lab model card
35 Claude Opus 4.1 77.1% Aug 2025 Lab model card
36 Gemini 2.5 Flash Apr 2025 76.7% Apr 2025 Lab model card
37 Claude Opus 4 76.5% May 2025 Lab model card
38 Llama 4 Behemoth 76.1% Apr 2025 Lab model card
39 GLM-4.6V 76% Dec 2025 Lab model card
40 GPT-5 nano 75.6% Aug 2025 Lab model card
41 Gemini 2.0 Flash Thinking Jan 2025 75.4% Jan 2025 Lab model card
42 GLM-4.5V 75.4% Aug 2025 Lab model card
43 Keye-VL-2.0-30B-A3B 75.3% May 2026 Lab model card
44 Command A+ 75.1% May 2026 Lab model card
45 Claude 3.7 Sonnet 75% Feb 2025 Lab model card
46 GPT-4.1 74.8% Apr 2025 Lab model card
47 Seed1.6-Thinking 74.8% Jun 2025 Lab model card
48 GPT-4.5 74.4% Feb 2025 Lab model card
49 Claude Sonnet 4 74.4% May 2025 Lab model card
50 Step 3 74.2% Jul 2025 Lab model card
51 Llama 4 Maverick 73.4% Apr 2025 Lab model card
52 Claude Haiku 4.5 73.2% Oct 2025 Lab model card
53 Gemini 2.5 Flash-Lite Jun 2025 72.9% Jun 2025 Lab model card
54 Gemini 2.0 Pro 72.7% Feb 2025 Lab model card
55 GPT-4.1 mini 72.7% Apr 2025 Lab model card
56 ERNIE-4.5-VL-28B-A3B-Thinking 72.2% Nov 2025 Lab model card
57 Gemini 2.5 Flash-Lite Sep 2025 72% Sep 2025 Lab model card
58 Gemini 2.0 Flash Feb 2025 71.7% Feb 2025 Lab model card
59 Nemotron 3 Nano Omni 30B-A3B 70.8% Apr 2026 Lab model card
60 Gemini 2.0 Flash Dec 2024 70.7% Dec 2024 Lab model card
61 LongCat-Flash-Omni 70.7% Oct 2025 Lab model card
62 Claude 3.5 Sonnet (October 2024) 70.4% Oct 2024 Lab model card
63 Qwen2.5-VL-72B 70.2% Jan 2025 Lab model card
64 Kimi k1.5 70% Jan 2025 Lab model card
65 Magistral Medium 1.0 70% Jun 2025 Lab model card
66 Grok-3 mini 69.4% Feb 2025 Lab model card
67 Llama 4 Scout 69.4% Apr 2025 Lab model card
68 GPT-4o May 2024 69.1% May 2024 Lab model card
69 Qwen3-Omni-30B-A3B 69.1% Sep 2025 Lab model card
70 Claude 3.5 Sonnet 68.3% Jun 2024 Lab model card
71 Gemini 2.0 Flash-Lite 68% Feb 2025 Lab model card
72 Amazon Nova Premier 68% Apr 2025 Lab model card
73 GLM-4.1V-9B-Thinking 68% Jul 2025 Lab model card
74 Nemotron Nano 12B v2 VL 68% Oct 2025 Lab model card
75 Grok-2 Aug 2024 66.1% Aug 2024 Lab model card
76 Mistral Medium 3 66.1% May 2025 Lab model card
77 Magistral Small 1.0 66% Jun 2025 Lab model card
78 Gemma 3 27B 64.9% Mar 2025 Lab model card
79 Qwen3.5-2B 64.2% Mar 2026 Lab model card
80 Mistral Small 3.1 64% Mar 2025 Lab model card
81 Kimi-VL-A3B-Thinking-2506 64% Jun 2025 Lab model card
82 Mistral Small 3.2 62.5% Jun 2025 Lab model card
83 Gemini 1.0 Ultra 62.4% Dec 2023 Lab model card
84 Gemini 1.5 Pro May 2024 62.2% May 2024 Lab model card
85 Kimi-VL-A3B-Thinking 61.7% Apr 2025 Lab model card
86 Gemma 3 12B 59.6% Mar 2025 Lab model card
87 Claude 3 Opus 59.4% Mar 2024 Lab model card
88 GPT-4o mini 59.4% Jul 2024 Lab model card
89 Qwen2.5-Omni-7B 59.2% Mar 2025 Lab model card
90 Gemini 1.5 Pro Feb 2024 58.5% Feb 2024 Lab model card
91 GPT-4.1 nano 55.4% Apr 2025 Lab model card
92 BAGEL-7B-MoT 55.3% May 2025 Lab model card
93 Phi-4-multimodal 55.1% Feb 2025 Lab model card
94 Phi-4-Reasoning-Vision-15B 54.3% Mar 2026 Lab model card
95 Claude 3 Sonnet 53.1% Mar 2024 Lab model card
96 Claude 3 Haiku 50.2% Mar 2024 Lab model card
97 Qwen3.5-0.8B 49% Mar 2026 Lab model card
98 Gemma 3 4B 48.8% Mar 2025 Lab model card
99 LFM2.5-VL-3B 48.4% Aug 2026 Lab model card
100 Llama-3.1-Nemotron-Nano-VL-8B-V1 48.2% Jun 2025 Lab model card
101 Phi-3.5-vision-instruct 43% Aug 2024 Lab model card
102 Janus-Pro-7B 41% Jan 2025 Lab model card
103 LFM2-VL-1.6B 39.7% Nov 2025 Lab model card
104 North Micro Vision Instruct 32.9% Aug 2026 Lab model card
#ModelScoreSettingDateSource
1 GPT-5.1 85.4% Nov 2025 Official leaderboard
2 GPT-5 84.2% thinking Aug 2025 Official leaderboard
3 Gemini 2.5 Deep Think 84% Aug 2025 Official leaderboard
4 o3 82.9% Apr 2025 Official leaderboard
5 o4-mini 81.6% Apr 2025 Official leaderboard
6 Claude Opus 4.5 80.7% Nov 2025 Official leaderboard
7 dots.vlm1 80.1% Aug 2025 Official leaderboard
8 Gemini 2.5 Flash May 2025 79.7% May 2025 Official leaderboard
9 Gemini 2.5 Pro May 2025 79.6% May 2025 Official leaderboard
10 Qwen3-VL-235B-A22B 78.7% Sep 2025 Official leaderboard
11 o1 78.2% Dec 2024 Official leaderboard
12 Grok 3 78% Apr 2025 Official leaderboard
13 Seed1.5-VL 77.9% thinking May 2025 Official leaderboard
14 Claude Sonnet 4.5 77.8% Sep 2025 Official leaderboard
15 Intern-S1 77.7% Jul 2025 Official leaderboard
16 Claude Opus 4.1 77.1% Aug 2025 Official leaderboard
17 Claude Opus 4 76.5% May 2025 Official leaderboard
18 Llama 4 Behemoth 76.1% Apr 2025 Official leaderboard
19 Skywork-R1V3-38B 76% Jul 2025 Official leaderboard
20 GLM-4.5V 75.4% thinking Aug 2025 Official leaderboard
21 Claude 3.7 Sonnet 75% Feb 2025 Official leaderboard
22 Seed1.6-Thinking 74.8% Jun 2025 Official leaderboard
23 GPT-4.5 74.4% Feb 2025 Official leaderboard
24 Claude Sonnet 4 74.4% May 2025 Official leaderboard
25 Skywork-R1V2-38B 73.6% Apr 2025 Official leaderboard
26 Llama 4 Maverick 73.4% Apr 2025 Official leaderboard
27 Gemini 2.0 Pro 72.7% Feb 2025 Official leaderboard
28 InternVL3-78B 72.2% Apr 2025 Official leaderboard
29 Gemini 2.0 Flash Feb 2025 71.7% Feb 2025 Official leaderboard
30 GPT-4o Nov 2024 70.7% Nov 2024 Official leaderboard
31 MiMo-VL-7B-RL-2508 70.6% thinking Aug 2025 Official leaderboard
32 QVQ-72B-Preview 70.3% Dec 2024 Official leaderboard
33 InternVL2_5-78B 70.1% Dec 2024 Official leaderboard
34 InternVL3-38B 70.1% Apr 2025 Official leaderboard
35 Llama 4 Scout 69.4% Apr 2025 Official leaderboard
36 GPT-4o May 2024 69.1% May 2024 Official leaderboard
37 Skywork-R1V-38B 69% Mar 2025 Official leaderboard
38 Claude 3.5 Sonnet 68.3% Jun 2024 Official leaderboard
39 Gemini 2.0 Flash-Lite 68% Feb 2025 Official leaderboard
40 Amazon Nova Premier 68% Apr 2025 Official leaderboard
41 GLM-4.1V-9B-Thinking 68% thinking Jul 2025 Official leaderboard
42 InternVL3-14B 67.1% Apr 2025 Official leaderboard
43 MiMo-VL-7B-RL 66.7% May 2025 Official leaderboard
44 Ovis2-34B 65.6% Feb 2025 Official leaderboard
45 Gemma 3 27B 64.9% Mar 2025 Official leaderboard
46 MiMo-VL-7B-SFT 64.6% May 2025 Official leaderboard
47 Qwen2-VL-72B-Instruct 64.5% Aug 2024 Official leaderboard
48 Qwen2.5-VL-72B 64.5% Jan 2025 Official leaderboard
49 InternVL2.5-38B 63.9% Dec 2024 Official leaderboard
50 InternVL3-8B 62.7% Apr 2025 Official leaderboard
51 Gemini 1.5 Pro May 2024 62.2% May 2024 Official leaderboard
52 InternVL2-Pro 62% Jul 2024 Official leaderboard
53 Amazon Nova Pro 62% Dec 2024 Official leaderboard
54 Llama 3.2 90B 60.3% Sep 2024 Official leaderboard
55 InternVL2.5-26B 60% Dec 2024 Official leaderboard
56 NVLM-D-72B 59.7% Sep 2024 Official leaderboard
57 Ovis2-16B 59.6% Feb 2025 Official leaderboard
58 Gemma 3 12B 59.6% Mar 2025 Official leaderboard
59 Gemini 1.0 Ultra 59.4% Dec 2023 Official leaderboard
60 Claude 3 Opus 59.4% Feb 2024 Official leaderboard
61 GPT-4o mini 59.4% Jul 2024 Official leaderboard
62 Ovis2-8B 59% Feb 2025 Official leaderboard
63 Qwen2.5-VL-7B 58.6% Jan 2025 Official leaderboard
64 InternVL2-Llama3-76B 58.3% Jul 2024 Official leaderboard
65 Qianfan-VL-70B 58.3% Sep 2025 Official leaderboard
66 InternVL3-9B 57.7% Apr 2025 Official leaderboard
67 Kimi-VL-A3B-Instruct 57% Apr 2025 Official leaderboard
68 GPT-4V 56.8% Nov 2023 Official leaderboard
69 LLaVA-OneVision 72B 56.8% Aug 2024 Official leaderboard
70 Reka Core 56.3% Apr 2024 Official leaderboard
71 Gemini 1.5 Flash May 2024 56.1% May 2024 Official leaderboard
72 InternVL2.5-8B 56% Dec 2024 Official leaderboard
73 Eagle2.5-8B 55.8% Apr 2025 Official leaderboard
74 InternVL2-40B 55.2% Jul 2024 Official leaderboard
75 Aria 54.9% Sep 2024 Official leaderboard
76 Reka Flash 53.3% Feb 2024 Official leaderboard
77 Claude 3 Sonnet 53.1% Feb 2024 Official leaderboard
78 Qwen2.5-VL-3B 53.1% Jan 2025 Official leaderboard
79 InternVL-Chat-V1-2 51.6% Feb 2024 Official leaderboard
80 Qwen-VL-Max 51.4% Jan 2024 Official leaderboard
81 InternVL2-8B 51.2% Jul 2024 Official leaderboard
82 DeepSeek-VL2 51.1% Dec 2024 Official leaderboard
83 MAmmoTH-VL-8B 50.8% Nov 2024 Official leaderboard
84 Llama 3.2 11B 50.7% Sep 2024 Official leaderboard
85 Claude 3 Haiku 50.2% Mar 2024 Official leaderboard
86 LLaVA-NeXT-72B 49.9% May 2024 Official leaderboard
87 Ovis1.5-Gemma2-9B 49.8% Jul 2024 Official leaderboard
88 MiniCPM-V-2_6 49.8% Aug 2024 Official leaderboard
89 Cambrian-1-34B 49.7% Jun 2024 Official leaderboard
90 LLaVA-OneVision 7B 48.8% Aug 2024 Official leaderboard
91 Gemma 3 4B 48.8% Mar 2025 Official leaderboard
92 InternVL3-2B 48.6% Apr 2025 Official leaderboard
93 LLaVA-v1.6-34B 48.1% Jan 2024 Official leaderboard
94 DeepSeek-VL2-Small 48% Dec 2024 Official leaderboard
95 Ovis2-4B 48% Feb 2025 Official leaderboard
96 Gemini 1.0 Pro 47.9% Dec 2023 Official leaderboard
97 Aquila-VL-2B 47.4% Oct 2024 Official leaderboard
98 Qianfan-VL-8B 47.1% Sep 2025 Official leaderboard
99 Idefics3-8B-Llama3 46.6% Aug 2024 Official leaderboard
100 Qianfan-VL-3B 46.4% Sep 2025 Official leaderboard
101 Yi-VL-34B 45.9% Dec 2023 Official leaderboard
102 MiniCPM-Llama3-V 2.5 45.8% May 2024 Official leaderboard
103 Ovis2-2B 45.3% Feb 2025 Official leaderboard
104 Qwen-VL-Plus 45.2% Jan 2024 Official leaderboard
105 Aya Vision 32B 45.1% Mar 2025 Official leaderboard
106 InternVL2.5-2B 43.6% Dec 2024 Official leaderboard
107 InternVL3-1B 43.4% Apr 2025 Official leaderboard
108 InternLM-XComposer2-VL-7B 43% Jan 2024 Official leaderboard
109 Phi-3.5-vision-instruct 43% Aug 2024 Official leaderboard
110 Reka Edge 42.8% Mar 2026 Official leaderboard
111 Cambrian-1-8B 42.7% Jun 2024 Official leaderboard
112 Bunny-v1.0-4B 41.4% Apr 2024 Official leaderboard
113 OmniLMM-12B 41.1% Jan 2024 Official leaderboard
114 InternVL2.5-1B 40.9% Dec 2024 Official leaderboard
115 DeepSeek-VL2-Tiny 40.7% Dec 2024 Official leaderboard
116 Cambrian-1-13B 40% Jun 2024 Official leaderboard
117 Aya Vision 8B 39.9% Mar 2025 Official leaderboard
118 Yi-VL-6B 39.1% Dec 2023 Official leaderboard
119 InternVL-Chat-V1-1 39.1% Jan 2024 Official leaderboard
120 Bunny-v1.0-3B 38.2% Feb 2024 Official leaderboard
121 MiniCPM-V 37.2% Jan 2024 Official leaderboard
122 MiniCPM-V 2.0 37.1% Apr 2024 Official leaderboard
123 LLaVA-v1.5-13B 36.4% Oct 2023 Official leaderboard
124 Emu2-Chat 36.3% Dec 2023 Official leaderboard
125 llava-v1.6-vicuna-13b 36.2% Jan 2024 Official leaderboard
126 Ovis2-1B 36% Feb 2025 Official leaderboard
127 Qwen-VL-Chat 35.9% Aug 2023 Official leaderboard
128 llava-v1.6-vicuna-7b 35.8% Jan 2024 Official leaderboard
129 InstructBLIP FLAN-T5-XXL 35.7% Jun 2023 Official leaderboard
130 BLIP-2 FLAN-T5-XXL 35.4% Feb 2023 Official leaderboard
131 llava-v1.6-mistral-7b 35.3% Jan 2024 Official leaderboard
132 BLIP-2 FLAN-T5-XL 34.4% Feb 2023 Official leaderboard
133 InstructBLIP FLAN-T5-XL 32.9% May 2023 Official leaderboard
134 mPLUG-Owl2 32.7% Nov 2023 Official leaderboard
135 CogVLM-17B-Chat 32.1% Nov 2023 Official leaderboard
136 Fuyu-8B 27.9% Oct 2023 Official leaderboard
137 Kosmos-2 24.4% Jun 2023 Official leaderboard
#ModelScoreSettingDateSource
1 Qwen 3.6 Plus 86% Apr 2026 Lab model card
2 GPT-5.1 85.4% Nov 2025 Official leaderboard
3 Seed2.0 Pro 85.4% Feb 2026 Lab model card
4 Qwen3.5 397B-A17B 85% Feb 2026 Lab model card
5 Kimi K2.5 84.3% Jan 2026 Lab model card
6 GPT-5 84.2% thinking Aug 2025 Official leaderboard
7 Gemini 2.5 Deep Think 84% Aug 2025 Official leaderboard
8 Qwen3.5-122B-A10B 83.9% Feb 2026 Lab model card
9 Seed1.8 83.4% Dec 2025 Lab model card
10 o3 82.9% Apr 2025 Official leaderboard
11 Qwen3.6 27B 82.9% Apr 2026 Lab model card
12 Qwen3.5-27B 82.3% Feb 2026 Lab model card
13 Gemini 2.5 Pro Jun 2025 82% Jun 2025 Lab model card
14 Gemini 2.5 Pro Mar 2025 81.7% Mar 2025 Lab model card
15 Qwen 3.6 35B-A3B 81.7% Apr 2026 Lab model card
16 o4-mini 81.6% Apr 2025 Official leaderboard
17 GPT-5 mini 81.6% Aug 2025 Lab model card
18 Qwen3.5-35B-A3B 81.4% Feb 2026 Lab model card
19 gemini-robotics-er-1.5-preview 80.7% Sep 2025 Lab model card
20 Claude Opus 4.5 80.7% Nov 2025 Official leaderboard
21 Qwen3-VL-235B-A22B 80.6% Sep 2025 Lab model card
22 Gemini 2.5 Flash Sep 2025 80.3% Sep 2025 Lab model card
23 MiniCPM-V-4.7-35B-A3B 80.2% Oct 2026 Lab model card
24 dots.vlm1 80.1% Aug 2025 Official leaderboard
25 Qwen3.5-Omni-Plus 80.1% Mar 2026 Lab model card
26 Gemini 2.5 Flash May 2025 79.7% May 2025 Official leaderboard
27 Gemini 2.5 Flash Jun 2025 79.7% Jun 2025 Lab model card
28 Gemini 2.5 Pro May 2025 79.6% May 2025 Official leaderboard
29 EXAONE 4.5 33B 78.7% Apr 2026 Lab model card
30 Qwen3.5-9B 78.4% Mar 2026 Lab model card
31 o1 78.2% Dec 2024 Official leaderboard
32 STEP3-VL-10B 78.1% Jan 2026 Lab model card
33 Grok 3 78% Apr 2025 Official leaderboard
34 Seed1.5-VL 77.9% thinking May 2025 Official leaderboard
35 Claude Sonnet 4.5 77.8% Sep 2025 Official leaderboard
36 Intern-S1 77.7% Jul 2025 Official leaderboard
37 InternVL3.5-241B-A28B 77.7% Aug 2025 Lab model card
38 Qwen3.5-4B 77.6% Mar 2026 Lab model card
39 Claude Opus 4.1 77.1% Aug 2025 Official leaderboard
40 Gemini 2.5 Flash Apr 2025 76.7% Apr 2025 Lab model card
41 Claude Opus 4 76.5% May 2025 Official leaderboard
42 Llama 4 Behemoth 76.1% Apr 2025 Official leaderboard
43 Skywork-R1V3-38B 76% Jul 2025 Official leaderboard
44 GLM-4.6V 76% Dec 2025 Lab model card
45 GPT-5 nano 75.6% Aug 2025 Lab model card
46 Gemini 2.0 Flash Thinking Jan 2025 75.4% Jan 2025 Lab model card
47 GLM-4.5V 75.4% thinking Aug 2025 Official leaderboard
48 Keye-VL-2.0-30B-A3B 75.3% May 2026 Lab model card
49 Command A+ 75.1% May 2026 Lab model card
50 Claude 3.7 Sonnet 75% Feb 2025 Official leaderboard
51 GPT-4.1 74.8% Apr 2025 Lab model card
52 Seed1.6-Thinking 74.8% Jun 2025 Official leaderboard
53 GPT-4.5 74.4% Feb 2025 Official leaderboard
54 Claude Sonnet 4 74.4% May 2025 Official leaderboard
55 Step 3 74.2% Jul 2025 Lab model card
56 Skywork-R1V2-38B 73.6% Apr 2025 Official leaderboard
57 Llama 4 Maverick 73.4% Apr 2025 Official leaderboard
58 Claude Haiku 4.5 73.2% Oct 2025 Lab model card
59 Gemini 2.5 Flash-Lite Jun 2025 72.9% Jun 2025 Lab model card
60 Gemini 2.0 Pro 72.7% Feb 2025 Official leaderboard
61 GPT-4.1 mini 72.7% Apr 2025 Lab model card
62 InternVL3-78B 72.2% Apr 2025 Official leaderboard
63 ERNIE-4.5-VL-28B-A3B-Thinking 72.2% Nov 2025 Lab model card
64 Gemini 2.5 Flash-Lite Sep 2025 72% Sep 2025 Lab model card
65 Gemini 2.0 Flash Feb 2025 71.7% Feb 2025 Official leaderboard
66 Nemotron 3 Nano Omni 30B-A3B 70.8% Apr 2026 Lab model card
67 GPT-4o Nov 2024 70.7% Nov 2024 Official leaderboard
68 Gemini 2.0 Flash Dec 2024 70.7% Dec 2024 Lab model card
69 LongCat-Flash-Omni 70.7% Oct 2025 Lab model card
70 MiMo-VL-7B-RL-2508 70.6% thinking Aug 2025 Official leaderboard
71 Claude 3.5 Sonnet (October 2024) 70.4% Oct 2024 Lab model card
72 QVQ-72B-Preview 70.3% Dec 2024 Official leaderboard
73 Qwen2.5-VL-72B 70.2% Jan 2025 Lab model card
74 InternVL2_5-78B 70.1% Dec 2024 Official leaderboard
75 InternVL3-38B 70.1% Apr 2025 Official leaderboard
76 Kimi k1.5 70% Jan 2025 Lab model card
77 Magistral Medium 1.0 70% Jun 2025 Lab model card
78 Grok-3 mini 69.4% Feb 2025 Lab model card
79 Llama 4 Scout 69.4% Apr 2025 Official leaderboard
80 GPT-4o May 2024 69.1% May 2024 Official leaderboard
81 Qwen3-Omni-30B-A3B 69.1% Sep 2025 Lab model card
82 Skywork-R1V-38B 69% Mar 2025 Official leaderboard
83 Claude 3.5 Sonnet 68.3% Jun 2024 Official leaderboard
84 Gemini 2.0 Flash-Lite 68% Feb 2025 Official leaderboard
85 Amazon Nova Premier 68% Apr 2025 Official leaderboard
86 GLM-4.1V-9B-Thinking 68% thinking Jul 2025 Official leaderboard
87 Nemotron Nano 12B v2 VL 68% Oct 2025 Lab model card
88 InternVL3-14B 67.1% Apr 2025 Official leaderboard
89 MiMo-VL-7B-RL 66.7% May 2025 Official leaderboard
90 Grok-2 Aug 2024 66.1% Aug 2024 Lab model card
91 Mistral Medium 3 66.1% May 2025 Lab model card
92 Magistral Small 1.0 66% Jun 2025 Lab model card
93 Ovis2-34B 65.6% Feb 2025 Official leaderboard
94 Gemma 3 27B 64.9% Mar 2025 Official leaderboard
95 MiMo-VL-7B-SFT 64.6% May 2025 Official leaderboard
96 Qwen2-VL-72B-Instruct 64.5% Aug 2024 Official leaderboard
97 Qwen3.5-2B 64.2% Mar 2026 Lab model card
98 Mistral Small 3.1 64% Mar 2025 Lab model card
99 Kimi-VL-A3B-Thinking-2506 64% Jun 2025 Lab model card
100 InternVL2.5-38B 63.9% Dec 2024 Official leaderboard
101 InternVL3-8B 62.7% Apr 2025 Official leaderboard
102 Mistral Small 3.2 62.5% Jun 2025 Lab model card
103 Gemini 1.0 Ultra 62.4% Dec 2023 Lab model card
104 Gemini 1.5 Pro May 2024 62.2% May 2024 Official leaderboard
105 InternVL2-Pro 62% Jul 2024 Official leaderboard
106 Amazon Nova Pro 62% Dec 2024 Official leaderboard
107 Kimi-VL-A3B-Thinking 61.7% Apr 2025 Lab model card
108 Llama 3.2 90B 60.3% Sep 2024 Official leaderboard
109 InternVL2.5-26B 60% Dec 2024 Official leaderboard
110 NVLM-D-72B 59.7% Sep 2024 Official leaderboard
111 Ovis2-16B 59.6% Feb 2025 Official leaderboard
112 Gemma 3 12B 59.6% Mar 2025 Official leaderboard
113 Claude 3 Opus 59.4% Feb 2024 Official leaderboard
114 GPT-4o mini 59.4% Jul 2024 Official leaderboard
115 Qwen2.5-Omni-7B 59.2% Mar 2025 Lab model card
116 Ovis2-8B 59% Feb 2025 Official leaderboard
117 Qwen2.5-VL-7B 58.6% Jan 2025 Official leaderboard
118 Gemini 1.5 Pro Feb 2024 58.5% Feb 2024 Lab model card
119 InternVL2-Llama3-76B 58.3% Jul 2024 Official leaderboard
120 Qianfan-VL-70B 58.3% Sep 2025 Official leaderboard
121 InternVL3-9B 57.7% Apr 2025 Official leaderboard
122 Kimi-VL-A3B-Instruct 57% Apr 2025 Official leaderboard
123 GPT-4V 56.8% Nov 2023 Official leaderboard
124 LLaVA-OneVision 72B 56.8% Aug 2024 Official leaderboard
125 Reka Core 56.3% Apr 2024 Official leaderboard
126 Gemini 1.5 Flash May 2024 56.1% May 2024 Official leaderboard
127 InternVL2.5-8B 56% Dec 2024 Official leaderboard
128 Eagle2.5-8B 55.8% Apr 2025 Official leaderboard
129 GPT-4.1 nano 55.4% Apr 2025 Lab model card
130 BAGEL-7B-MoT 55.3% May 2025 Lab model card
131 InternVL2-40B 55.2% Jul 2024 Official leaderboard
132 Phi-4-multimodal 55.1% Feb 2025 Lab model card
133 Aria 54.9% Sep 2024 Official leaderboard
134 Phi-4-Reasoning-Vision-15B 54.3% Mar 2026 Lab model card
135 Reka Flash 53.3% Feb 2024 Official leaderboard
136 Claude 3 Sonnet 53.1% Feb 2024 Official leaderboard
137 Qwen2.5-VL-3B 53.1% Jan 2025 Official leaderboard
138 InternVL-Chat-V1-2 51.6% Feb 2024 Official leaderboard
139 Qwen-VL-Max 51.4% Jan 2024 Official leaderboard
140 InternVL2-8B 51.2% Jul 2024 Official leaderboard
141 DeepSeek-VL2 51.1% Dec 2024 Official leaderboard
142 MAmmoTH-VL-8B 50.8% Nov 2024 Official leaderboard
143 Llama 3.2 11B 50.7% Sep 2024 Official leaderboard
144 Claude 3 Haiku 50.2% Mar 2024 Official leaderboard
145 LLaVA-NeXT-72B 49.9% May 2024 Official leaderboard
146 Ovis1.5-Gemma2-9B 49.8% Jul 2024 Official leaderboard
147 MiniCPM-V-2_6 49.8% Aug 2024 Official leaderboard
148 Cambrian-1-34B 49.7% Jun 2024 Official leaderboard
149 Qwen3.5-0.8B 49% Mar 2026 Lab model card
150 LLaVA-OneVision 7B 48.8% Aug 2024 Official leaderboard
151 Gemma 3 4B 48.8% Mar 2025 Official leaderboard
152 InternVL3-2B 48.6% Apr 2025 Official leaderboard
153 LFM2.5-VL-3B 48.4% Aug 2026 Lab model card
154 Llama-3.1-Nemotron-Nano-VL-8B-V1 48.2% Jun 2025 Lab model card
155 LLaVA-v1.6-34B 48.1% Jan 2024 Official leaderboard
156 DeepSeek-VL2-Small 48% Dec 2024 Official leaderboard
157 Ovis2-4B 48% Feb 2025 Official leaderboard
158 Gemini 1.0 Pro 47.9% Dec 2023 Official leaderboard
159 Aquila-VL-2B 47.4% Oct 2024 Official leaderboard
160 Qianfan-VL-8B 47.1% Sep 2025 Official leaderboard
161 Idefics3-8B-Llama3 46.6% Aug 2024 Official leaderboard
162 Qianfan-VL-3B 46.4% Sep 2025 Official leaderboard
163 Yi-VL-34B 45.9% Dec 2023 Official leaderboard
164 MiniCPM-Llama3-V 2.5 45.8% May 2024 Official leaderboard
165 Ovis2-2B 45.3% Feb 2025 Official leaderboard
166 Qwen-VL-Plus 45.2% Jan 2024 Official leaderboard
167 Aya Vision 32B 45.1% Mar 2025 Official leaderboard
168 InternVL2.5-2B 43.6% Dec 2024 Official leaderboard
169 InternVL3-1B 43.4% Apr 2025 Official leaderboard
170 InternLM-XComposer2-VL-7B 43% Jan 2024 Official leaderboard
171 Phi-3.5-vision-instruct 43% Aug 2024 Official leaderboard
172 Reka Edge 42.8% Mar 2026 Official leaderboard
173 Cambrian-1-8B 42.7% Jun 2024 Official leaderboard
174 Bunny-v1.0-4B 41.4% Apr 2024 Official leaderboard
175 OmniLMM-12B 41.1% Jan 2024 Official leaderboard
176 Janus-Pro-7B 41% Jan 2025 Lab model card
177 InternVL2.5-1B 40.9% Dec 2024 Official leaderboard
178 DeepSeek-VL2-Tiny 40.7% Dec 2024 Official leaderboard
179 Cambrian-1-13B 40% Jun 2024 Official leaderboard
180 Aya Vision 8B 39.9% Mar 2025 Official leaderboard
181 LFM2-VL-1.6B 39.7% Nov 2025 Lab model card
182 Yi-VL-6B 39.1% Dec 2023 Official leaderboard
183 InternVL-Chat-V1-1 39.1% Jan 2024 Official leaderboard
184 Bunny-v1.0-3B 38.2% Feb 2024 Official leaderboard
185 MiniCPM-V 37.2% Jan 2024 Official leaderboard
186 MiniCPM-V 2.0 37.1% Apr 2024 Official leaderboard
187 LLaVA-v1.5-13B 36.4% Oct 2023 Official leaderboard
188 Emu2-Chat 36.3% Dec 2023 Official leaderboard
189 llava-v1.6-vicuna-13b 36.2% Jan 2024 Official leaderboard
190 Ovis2-1B 36% Feb 2025 Official leaderboard
191 Qwen-VL-Chat 35.9% Aug 2023 Official leaderboard
192 llava-v1.6-vicuna-7b 35.8% Jan 2024 Official leaderboard
193 InstructBLIP FLAN-T5-XXL 35.7% Jun 2023 Official leaderboard
194 BLIP-2 FLAN-T5-XXL 35.4% Feb 2023 Official leaderboard
195 llava-v1.6-mistral-7b 35.3% Jan 2024 Official leaderboard
196 BLIP-2 FLAN-T5-XL 34.4% Feb 2023 Official leaderboard
197 InstructBLIP FLAN-T5-XL 32.9% May 2023 Official leaderboard
198 North Micro Vision Instruct 32.9% Aug 2026 Lab model card
199 mPLUG-Owl2 32.7% Nov 2023 Official leaderboard
200 CogVLM-17B-Chat 32.1% Nov 2023 Official leaderboard
201 Fuyu-8B 27.9% Oct 2023 Official leaderboard
202 Kosmos-2 24.4% Jun 2023 Official leaderboard

The benchmark's own leaderboard has 186 entries, 137 of them models we track. Switch the scores above to rank them together.

Scores at each effort level

Models the leaderboard ran at two or more effort levels. We don’t have enough cost data here to say what the extra effort costs.

Lowest effort to highest, light to dark
GPT-5
non-thinking thinking
84.2%
Seed1.5-VL
thinking
77.9%
MiMo-VL-7B-RL-2508
non-thinking thinking
70.6%

Source: Official MMMU leaderboard

ModelEffortHarnessScoreCost per taskOutput tokens
GPT-5.1 85.4%
GPT-5 thinking 84.2%
Gemini 2.5 Deep Think 84%
o3 82.9%
o4-mini 81.6%
Claude Opus 4.5 80.7%
dots.vlm1 80.1%
Gemini 2.5 Flash May 2025 79.7%
Gemini 2.5 Pro May 2025 79.6%
Qwen3-VL-235B-A22B 78.7%
o1 78.2%
Grok 3 78%
Seed1.5-VL thinking 77.9%
Claude Sonnet 4.5 77.8%
Intern-S1 77.7%
Claude Opus 4.1 77.1%
Claude Opus 4 76.5%
Llama 4 Behemoth 76.1%
Skywork-R1V3-38B 76%
GLM-4.5V thinking 75.4%
Claude 3.7 Sonnet 75%
Seed1.6-Thinking 74.8%
GPT-4.5 74.4%
Claude Sonnet 4 74.4%
GPT-5 non-thinking 74.4%
Skywork-R1V2-38B 73.6%
Seed1.5-VL 73.6%
Llama 4 Maverick 73.4%
Gemini 2.0 Pro 72.7%
InternVL3-78B 72.2%
Gemini 2.0 Flash Feb 2025 71.7%
GPT-4o Nov 2024 70.7%
MiMo-VL-7B-RL-2508 thinking 70.6%
QVQ-72B-Preview 70.3%
InternVL2_5-78B 70.1%
InternVL3-38B 70.1%
Llama 4 Scout 69.4%
GPT-4o May 2024 69.1%
Skywork-R1V-38B 69%
Claude 3.5 Sonnet 68.3%
Gemini 2.0 Flash-Lite 68%
Amazon Nova Premier 68%
GLM-4.1V-9B-Thinking thinking 68%
InternVL3-14B 67.1%
MiMo-VL-7B-RL 66.7%
Ovis2-34B 65.6%
Gemma 3 27B 64.9%
MiMo-VL-7B-SFT 64.6%
Qwen2-VL-72B-Instruct 64.5%
Qwen2.5-VL-72B 64.5%
InternVL2.5-38B 63.9%
MiMo-VL-7B-RL-2508 non-thinking 63.1%
InternVL3-8B 62.7%
Gemini 1.5 Pro May 2024 62.2%
InternVL2-Pro 62%
Amazon Nova Pro 62%
Llama 3.2 90B 60.3%
InternVL2.5-26B 60%
NVLM-D-72B 59.7%
Ovis2-16B 59.6%
Gemma 3 12B 59.6%
Gemini 1.0 Ultra 59.4%
Claude 3 Opus 59.4%
GPT-4o mini 59.4%
Ovis2-8B 59%
Qwen2.5-VL-7B 58.6%
InternVL2-Llama3-76B 58.3%
Qianfan-VL-70B 58.3%
InternVL3-9B 57.7%
Kimi-VL-A3B-Instruct 57%
GPT-4V 56.8%
LLaVA-OneVision 72B 56.8%
Reka Core 56.3%
Gemini 1.5 Flash May 2024 56.1%
InternVL2.5-8B 56%
Eagle2.5-8B 55.8%
InternVL2-40B 55.2%
Aria 54.9%
Reka Flash 53.3%
Claude 3 Sonnet 53.1%
Qwen2.5-VL-3B 53.1%
InternVL-Chat-V1-2 51.6%
Qwen-VL-Max 51.4%
InternVL2-8B 51.2%
DeepSeek-VL2 51.1%
MAmmoTH-VL-8B 50.8%
Llama 3.2 11B 50.7%
Claude 3 Haiku 50.2%
LLaVA-NeXT-72B 49.9%
Ovis1.5-Gemma2-9B 49.8%
MiniCPM-V-2_6 49.8%
Cambrian-1-34B 49.7%
LLaVA-OneVision 7B 48.8%
Gemma 3 4B 48.8%
InternVL3-2B 48.6%
LLaVA-v1.6-34B 48.1%
DeepSeek-VL2-Small 48%
Ovis2-4B 48%
Gemini 1.0 Pro 47.9%
Aquila-VL-2B 47.4%
Qianfan-VL-8B 47.1%
Idefics3-8B-Llama3 46.6%
Qianfan-VL-3B 46.4%
Yi-VL-34B 45.9%
MiniCPM-Llama3-V 2.5 45.8%
Ovis2-2B 45.3%
Qwen-VL-Plus 45.2%
Aya Vision 32B 45.1%
InternVL2.5-2B 43.6%
InternVL3-1B 43.4%
InternLM-XComposer2-VL-7B 43%
Phi-3.5-vision-instruct 43%
Reka Edge 42.8%
Cambrian-1-8B 42.7%
Bunny-v1.0-4B 41.4%
OmniLMM-12B 41.1%
InternVL2.5-1B 40.9%
DeepSeek-VL2-Tiny 40.7%
Cambrian-1-13B 40%
Aya Vision 8B 39.9%
Yi-VL-6B 39.1%
InternVL-Chat-V1-1 39.1%
Bunny-v1.0-3B 38.2%
MiniCPM-V 37.2%
MiniCPM-V 2.0 37.1%
LLaVA-v1.5-13B 36.4%
Emu2-Chat 36.3%
llava-v1.6-vicuna-13b 36.2%
Ovis2-1B 36%
Qwen-VL-Chat 35.9%
llava-v1.6-vicuna-7b 35.8%
InstructBLIP FLAN-T5-XXL 35.7%
BLIP-2 FLAN-T5-XXL 35.4%
llava-v1.6-mistral-7b 35.3%
BLIP-2 FLAN-T5-XL 34.4%
InstructBLIP FLAN-T5-XL 32.9%
mPLUG-Owl2 32.7%
CogVLM-17B-Chat 32.1%
Fuyu-8B 27.9%
Kosmos-2 24.4%

11 models have held number one in labs’ own numbers since its release in November 2023 10 models have held number one across all independent runs since its release in November 2023 13 models have held number one with claims included since its release in November 2023

Lab claims count from the day the card came out, independent runs from the model’s release. We draw one row each for the benchmark’s own leaderboard and what labs claim in their cards.

University of Wisconsin-Madison OpenAI Google DeepMind Anthropic xAI Qwen
Own leaderboard Passed 85% in Nov 2025, by GPT-5.1
GPT-5.1 85.4%
Lab claims Passed 85% in Nov 2025, by GPT-5.1

Sources: Official MMMU leaderboard and labs’ model cards

GPT-5.1 on the official leaderboard passed 85% in November 2025

That was 24 months after its release. By the same age, 43% of the benchmarks from 2023 had passed 85%. All the scores we have, one dot each, so a model tested at several settings appears more than once.

Plot with other benchmarks
On the benchmark’s own leaderboard Reported by the lab in its model card Best so far
0% 20% 40% 60% 80% 100% 2023 2024 2025 2026 Near the ceiling (85%) Qwen 3.6 Plus GPT-5 o1 GPT-4o Gemini 1.0 Ultra GPT-4V LLaVA-v1.5-13B 0% 20% 40% 60% 80% 100% 2023 2024 2025 2026 Near the ceiling (85%) Qwen 3.6 Plus o1

Sources: Official MMMU leaderboard and labs’ model cards

3 labs put it in a launch post in the last six months

Launch posts from every lab that has listed it, one tick per post. Tall colored ticks include it, and short gray ones leave it out.

Google DeepMind
Anthropic
OpenAI
xAI
Moonshot AI
DeepSeek
Qwen
Microsoft
Baidu
Mistral AI
Meta
Amazon
ByteDance Seed
NVIDIA
Z.ai
Shanghai AI Lab
StepFun
Cohere
Liquid AI
Meituan
LG AI Research
Kuaishou
OpenBMB (ModelBest)
DateLaunch postScoreAs the post writes it
Oct 7, 2026 MiniCPM-V-4.7-35B-A3B 80.2 MMMU
Aug 12, 2026 LFM2.5-VL-3B 48.4 MMMU (val)
Aug 12, 2026 North Micro Vision Instruct 32.9 MMMU DEV_VAL
May 25, 2026 Keye-VL-2.0-30B-A3B 75.3 MMMU
May 20, 2026 Command A+ 75.1 MMMU (75.1% in text, 75% in chart)
Apr 22, 2026 Qwen3.6 27B 82.9 MMMU
Apr 15, 2026 Qwen 3.6 35B-A3B 81.7 MMMU
Apr 9, 2026 EXAONE 4.5 33B 78.7 MMMU
Apr 2, 2026 Qwen 3.6 Plus 86 MMMU
Mar 30, 2026 Qwen3.5-Omni-Plus 80.1 MMMU
Mar 4, 2026 Phi-4-Reasoning-Vision-15B 54.3 MMMU_VAL (default mode)
Mar 2, 2026 Qwen3.5-0.8B 49 MMMU 49/47.4 (with CI / without CI)
Mar 2, 2026 Qwen3.5-2B 64.2 MMMU 64.2/64.2 (with CI / without CI)
Mar 2, 2026 Qwen3.5-4B 77.6 MMMU
Mar 2, 2026 Qwen3.5-9B 78.4 MMMU
Feb 24, 2026 Qwen3.5-35B-A3B 81.4 MMMU
Feb 24, 2026 Qwen3.5-27B 82.3 MMMU
Feb 24, 2026 Qwen3.5-122B-A10B 83.9 MMMU
Feb 16, 2026 Qwen3.5 397B-A17B 85 MMMU
Jan 13, 2026 STEP3-VL-10B 78.1 MMMU (SeRe)
Dec 18, 2025 Seed1.8 83.4 MMMU
Dec 8, 2025 GLM-4.6V 76 MMMU (Val)
Nov 24, 2025 Claude Opus 4.5 80.7 Visual reasoning MMMU (validation)
Nov 13, 2025 GPT-5.1 85.4 MMMU
Nov 11, 2025 ERNIE-4.5-VL-28B-A3B-Thinking 72.2 MMMU
Oct 31, 2025 LongCat-Flash-Omni 70.7 MMMU val
Oct 28, 2025 Nemotron Nano 12B v2 VL 68 MMMU* (val, ChatGPT judge)
Oct 15, 2025 Claude Haiku 4.5 73.2 Visual reasoning MMMU (validation)
Sep 29, 2025 Claude Sonnet 4.5 77.8 Visual reasoning MMMU (validation)
Sep 25, 2025 Gemini 2.5 Flash-Lite 72 MMMU single attempt, Thinking
Sep 25, 2025 Gemini 2.5 Flash 80.3 MMMU single attempt, model card
Sep 23, 2025 Qwen3-VL-235B-A22B 80.6 MMMU_VAL
Sep 22, 2025 Qwen3-Omni-30B-A3B 69.1 MMMU_val
Aug 25, 2025 InternVL3.5-241B-A28B 77.7 MMMU (val)
Aug 12, 2025 LFM2-VL-1.6B 38.4 MMMU (Val)
Aug 11, 2025 GLM-4.5V 75.4 MMMU (val)
Aug 7, 2025 GPT-5 nano 75.6 MMMU
Aug 7, 2025 GPT-5 mini 81.6 MMMU
Aug 7, 2025 GPT-5 84.2 MMMU College-level visual problem-solving
Aug 5, 2025 Claude Opus 4.1 77.1 Visual reasoning MMMU (validation)
Jul 31, 2025 Command A Vision MMMU (chart only)
Jul 31, 2025 Step 3 74.2 MMMU
Jul 24, 2025 Intern-S1 77.7 MMMU
Jul 1, 2025 GLM-4.1V-9B-Thinking 68 MMMU
Jun 25, 2025 Seed1.6-Thinking 74.8 MMMU
Jun 21, 2025 Kimi-VL-A3B-Thinking-2506 64 MMMU (val, Pass@1)
Jun 20, 2025 Mistral Small 3.2 62.5 MMMU
Jun 17, 2025 Gemini 2.5 Flash 79.7 MMMU single attempt
Jun 17, 2025 Gemini 2.5 Flash-Lite 72.9 MMMU single attempt, Thinking
Jun 17, 2025 Gemini 2.5 Pro 82 MMMU, single attempt (pass@1)
Jun 3, 2025 Llama-3.1-Nemotron-Nano-VL-8B-V1 48.2 MMMU Val with chatGPT as a judge
May 22, 2025 Claude Sonnet 4 74.4 Visual reasoning MMMU (validation)
May 22, 2025 Claude Opus 4 76.5 Visual reasoning MMMU (validation)
May 20, 2025 BAGEL-7B-MoT 55.3 MMMU
May 12, 2025 Seed1.5-VL 77.9 MMMU
May 7, 2025 Mistral Medium 3 66.1 MMMU 0-shot
Apr 30, 2025 Amazon Nova Premier 68 MMMU
Apr 17, 2025 Gemini 2.5 Flash 76.7 MMMU single attempt
Apr 16, 2025 o4-mini 81.6 MMMU
Apr 16, 2025 o3 82.9 MMMU College-level visual problem-solving
Apr 14, 2025 GPT-4.1 nano 55.4 MMMU
Apr 14, 2025 GPT-4.1 mini 72.7 MMMU
Apr 14, 2025 GPT-4.1 74.8 MMMU
Apr 10, 2025 Kimi-VL-A3B-Thinking 61.7 MMMU (val) (Pass@1)
Apr 5, 2025 Llama 4 Scout 69.4 MMMU, 0-shot, accuracy
Apr 5, 2025 Llama 4 Maverick 73.4 MMMU, 0-shot, accuracy
Apr 5, 2025 Llama 4 Behemoth 76.1 MMMU
Mar 27, 2025 Qwen2.5-Omni-7B 59.2 MMMUval
Mar 25, 2025 Gemini 2.5 Pro 81.7 MMMU, single attempt (pass@1)
Mar 17, 2025 Mistral Small 3.1 64 MMMU
Mar 16, 2025 ERNIE 4.5 MMMU
Mar 12, 2025 Gemma 3 27B 64.9 MMMU (val) (IT); PT MMMU = 56.1
Feb 27, 2025 GPT-4.5 74.4 MMMU (multimodal)
Feb 26, 2025 Phi-4-multimodal 55.1 MMMU
Feb 24, 2025 Claude 3.7 Sonnet 75 Visual reasoning MMMU (validation) (64K extended thinking)
Feb 19, 2025 Grok-3 mini 69.4 MMMU [Grok 3 mini, non-reasoning table]
Feb 19, 2025 Grok 3 78 MMMU (Grok 3 Think; pass@1 = 76)
Feb 5, 2025 Gemini 2.0 Flash-Lite 68 MMMU
Feb 5, 2025 Gemini 2.0 Flash 71.7 MMMU
Feb 5, 2025 Gemini 2.0 Pro 72.7 MMMU
Jan 28, 2025 Qwen2.5-VL-72B 70.2 MMMUval
Jan 27, 2025 Janus-Pro-7B 41 MMMU
Jan 21, 2025 Gemini 2.0 Flash Thinking 75.4 MMMU (Multimodal reasoning)
Jan 20, 2025 Kimi k1.5 70 MMMU-Val (Pass@1), long-CoT
Dec 17, 2024 o1 77.3 MMMU (pass @1)
Dec 11, 2024 Gemini 2.0 Flash 70.7 MMMU
Oct 22, 2024 Claude 3.5 Sonnet (October 2024) 70.4 MMMU (validation)
Sep 12, 2024 o1-preview MMMU (val) pass@1
Aug 13, 2024 Grok-2 66.1 MMMU (0-shot CoT)
Jul 18, 2024 GPT-4o mini 59.4 MMMU
Jun 20, 2024 Claude 3.5 Sonnet 68.3 MMMU (validation)
May 14, 2024 Gemini 1.5 Pro 62.2 MMMU (val), 0-shot
May 13, 2024 GPT-4o 69.1 MMMU (%) (val)
Mar 4, 2024 Claude 3 Opus 59.4 MMMU (val) Overall
Feb 15, 2024 Gemini 1.5 Pro 58.5 MMMU (val), 0-shot
Dec 6, 2023 Gemini 1.0 Ultra 62.4 MMMU (val), Maj1@32 (pass@1 = 59.4%)

51 system cards report it, from 18 labs

Besides launch posts, we read the system cards, model cards and technical reports labs publish with a release. They report far more, including safety and frontier-risk tests.

DateDocumentScoreAs the document writes itSection
Jun 9, 2026 Keye-VL-2.0-30B-A3B technical report 75.3 MMMU (Figure 5, printed value) Capabilities
Apr 27, 2026 Nemotron 3 Nano Omni 30B-A3B technical report 70.8 MMMU (val), reasoning on, 55.2 reasoning off (Table 7) Capabilities
Apr 17, 2026 Qwen3.5-Omni-Plus technical report 80.1 MMMU (Table 6) Capabilities
Apr 9, 2026 EXAONE 4.5 33B technical report 78.7 MMMU (Table 2, Reasoning mode) Capabilities
Mar 21, 2026 Seed1.8 model card 83.4 MMMU (Table 2) Capabilities
Mar 4, 2026 Phi-4-Reasoning-Vision-15B technical report 54.3 MMMU VAL, default mode, 52 force nothink, 55 force thinking (Tables 5 and 6) Capabilities
Feb 14, 2026 Seed2.0 Pro model card 85.4 MMMU (Table 8) Capabilities
Jan 30, 2026 Kimi K2.5 technical report 84.3 MMMU (val) (Table 4) Capabilities
Jan 14, 2026 STEP3-VL-10B technical report 78.1 MMMU, SeRe (Tables 1 and 3). PaCoRe 80.11 Capabilities
Jan 1, 2026 GLM-4.6V technical report 76 MMMU (Val), GLM-4.6V thinking (Table 2) Capabilities
Nov 28, 2025 LFM2-VL-1.6B technical report 39.7 MMMU, LFM2-VL-1.6B (Table 8) Capabilities
Nov 26, 2025 Qwen3-VL-235B-A22B technical report 80.6 MMMU (Table 2) Capabilities
Nov 24, 2025 Claude Opus 4.5 system card 80.7 MMMU (validation), 64k thinking, avg of 5 trials (Table 2.3.A; 80.72% in 2.20) Capabilities
Nov 6, 2025 Nemotron Nano 12B v2 VL technical report 67.8 MMMU (val), reasoning on (Table 3). Reasoning off 55.3 Capabilities
Oct 31, 2025 LongCat-Flash-Omni technical report 70.7 MMMU val (Table 5) Capabilities
Sep 26, 2025 Gemini 2.5 Flash model card 80.3 Visual reasoning MMMU, single attempt (pass@1) (Table, p.5) Capabilities
Sep 25, 2025 gemini-robotics-er-1.5-preview technical report 80.7 MMMU (Table 20, thinking on). Thinking off 79.3 Capabilities
Sep 22, 2025 Qwen3-Omni-30B-A3B technical report 69.1 MMMU val, Instruct (Table 9). Thinking 75.6 (Table 10) Capabilities
Aug 25, 2025 InternVL3.5-241B-A28B technical report 77.7 MMMU (val) (Table 2, Table 3). With parallel thinking 78.7 Capabilities
Aug 21, 2025 Intern-S1 technical report 77.7 MMMU (Table 2) Capabilities
Aug 13, 2025 GLM-4.5V technical report 75.4 MMMU (Val), GLM-4.5V thinking (Table 2) Capabilities
Jul 7, 2025 Gemini 2.5 Pro technical report 82 MMMU, single attempt (Table 3) Capabilities
Jul 7, 2025 Gemini 2.5 Flash technical report 79.7 MMMU, single attempt (Table 3) Capabilities
Jul 1, 2025 GLM-4.1V-9B-Thinking technical report 68 MMMU (Val), GLM-4.1V-9B-Thinking thinking (Table 2) Capabilities
Jun 23, 2025 Kimi-VL-A3B-Thinking-2506 technical report 64 MMMU (val) (Pass@1) (Table 4) Capabilities
Jun 12, 2025 Magistral Small 1.0 technical report 66 MMMU, Magistral Small bar, printed label (Figure 10) Capabilities
Jun 12, 2025 Magistral Medium 1.0 technical report 70 MMMU, printed bar label (Figure 10) Capabilities
May 20, 2025 BAGEL-7B-MoT technical report 55.3 MMMU (Table 4) Capabilities
May 11, 2025 Seed1.5-VL technical report 77.9 MMMU, thinking (Table 6). Non-thinking 73.6 Capabilities
Apr 30, 2025 Amazon Nova Premier technical report 68 MMMU, CoT (Table 1) Capabilities
Apr 29, 2025 Gemini 2.5 Flash model card 76.7 MMMU, single attempt (pass@1) (Table, p.4) Capabilities
Apr 28, 2025 Gemini 2.5 Pro model card 81.7 MMMU, single attempt pass@1 (Table, p.4, column Gemini 2.5 Pro Experimental 03-25) Capabilities
Apr 15, 2025 Gemini 2.0 Flash model card 71.7 MMMU (Table, p.3, column Gemini 2.0 Flash (GA)) Capabilities
Apr 10, 2025 Kimi-VL-A3B-Thinking technical report 61.7 MMMU (val) (Pass@1) (Table 4). Figure 13 shows 49.2 at 1k rising to 61.7 at 16k max thinking tokens Capabilities
Apr 10, 2025 Gemini 2.0 Flash-Lite model card 68 MMMU (Table, p.3) Capabilities
Apr 5, 2025 Llama 4 Scout model card 69.4 MMMU, 0-shot, accuracy, instruction tuned (Instruction tuned models table) Capabilities
Apr 5, 2025 Llama 4 Maverick model card 73.4 MMMU, 0-shot, accuracy, instruction tuned (Instruction tuned models table) Capabilities
Mar 26, 2025 Qwen2.5-Omni-7B technical report 59.2 MMMU val (Table 5) Capabilities
Mar 25, 2025 Gemma 3 4B technical report 48.8 MMMU (val), IT (Table 6 and Table 16) Capabilities
Mar 25, 2025 Gemma 3 27B technical report 64.9 MMMU (val), IT (Table 6 and Table 16) Capabilities
Mar 25, 2025 Gemma 3 12B technical report 59.6 MMMU (val), IT (Table 6 and Table 16) Capabilities
Mar 3, 2025 Phi-4-multimodal technical report 55.1 MMMU (val) (Table 1) Capabilities
Feb 19, 2025 Qwen2.5-VL-72B technical report 70.2 MMMU val (Table 3) Capabilities
Jan 27, 2025 Janus-Pro-7B technical report 41 MMMU (Table 3) Capabilities
Jan 20, 2025 Kimi k1.5 technical report 70 MMMU-Val (Pass@1), long-CoT (Table 2). Short-CoT 68.0 (Table 3) Capabilities
Oct 22, 2024 Claude 3.5 Sonnet (October 2024) model card 70.4 MMMU (validation), 0-shot CoT (Table 5) Capabilities
Aug 30, 2024 Phi-3.5-vision-instruct technical report 43 MMMU (val), 0-shot (Table 5) Capabilities
Jun 20, 2024 Claude 3.5 Sonnet model card 68.3 MMMU (validation), 0-shot CoT (Table 2) Capabilities
Mar 4, 2024 Claude 3 Sonnet model card 53.1 MMMU (val), Overall, 0-shot. Per-discipline values also given (Table 3) Capabilities
Mar 4, 2024 Claude 3 Opus model card 59.4 MMMU (val), Overall, 0-shot. Per-discipline values also given (Table 3) Capabilities
Mar 4, 2024 Claude 3 Haiku model card 50.2 MMMU (val), Overall, 0-shot. Per-discipline values also given (Table 3) Capabilities

The lab's number comes out ahead in 3 of 4 pairs that differ

Each score a lab reported for its own model, beside the same model's best score on the leaderboard. Gaps mostly come from different harnesses, effort levels and task subsets. 35 of them match, which usually means one side copied the other. Every benchmark.

Model Lab says Board says Gap
Qwen2.5-VL-72B 70.2% MMMUval 64.5% Leaderboard +5.7 pts
Gemini 1.0 Ultra 62.4% MMMU (val), Maj1@32 (pass@1 = 59.4%) 59.4% Leaderboard +3.0 pts
Qwen3-VL-235B-A22B 80.6% MMMU_VAL 78.7% Leaderboard +1.9 pts
o1 77.3% MMMU (pass @1) 78.2% Leaderboard −0.9 pts
Claude 3 Opus 59.4% MMMU (val) Overall 59.4% Leaderboard Same
GPT-4o May 2024 69.1% MMMU (%) (val) 69.1% Leaderboard Same
Gemini 1.5 Pro May 2024 62.2% MMMU (val), 0-shot 62.2% Leaderboard Same
Claude 3.5 Sonnet 68.3% MMMU (validation) 68.3% Leaderboard Same
GPT-4o mini 59.4% MMMU 59.4% Leaderboard Same
Gemini 2.0 Pro 72.7% MMMU 72.7% Leaderboard Same
Gemini 2.0 Flash Feb 2025 71.7% MMMU 71.7% Leaderboard Same
Gemini 2.0 Flash-Lite 68% MMMU 68% Leaderboard Same
Grok 3 78% MMMU (Grok 3 Think; pass@1 = 76) 78% Leaderboard Same
Claude 3.7 Sonnet 75% Visual reasoning MMMU (validation) (64K extended thinking) 75% Leaderboard Same
GPT-4.5 74.4% MMMU (multimodal) 74.4% Leaderboard Same
Gemma 3 27B 64.9% MMMU (val) (IT); PT MMMU = 56.1 64.9% Leaderboard Same
Llama 4 Behemoth 76.1% MMMU 76.1% Leaderboard Same
Llama 4 Maverick 73.4% MMMU, 0-shot, accuracy 73.4% Leaderboard Same
Llama 4 Scout 69.4% MMMU, 0-shot, accuracy 69.4% Leaderboard Same
o3 82.9% MMMU College-level visual problem-solving 82.9% Leaderboard Same
o4-mini 81.6% MMMU 81.6% Leaderboard Same
Amazon Nova Premier 68% MMMU 68% Leaderboard Same
Seed1.5-VL 77.9% MMMU 77.9% Leaderboard, thinking Same
Claude Opus 4 76.5% Visual reasoning MMMU (validation) 76.5% Leaderboard Same
Claude Sonnet 4 74.4% Visual reasoning MMMU (validation) 74.4% Leaderboard Same
Seed1.6-Thinking 74.8% MMMU 74.8% Leaderboard Same
GLM-4.1V-9B-Thinking 68% MMMU 68% Leaderboard, thinking Same
Intern-S1 77.7% MMMU 77.7% Leaderboard Same
Claude Opus 4.1 77.1% Visual reasoning MMMU (validation) 77.1% Leaderboard Same
GPT-5 84.2% MMMU College-level visual problem-solving 84.2% Leaderboard, thinking Same
GLM-4.5V 75.4% MMMU (val) 75.4% Leaderboard, thinking Same
Claude Sonnet 4.5 77.8% Visual reasoning MMMU (validation) 77.8% Leaderboard Same
GPT-5.1 85.4% MMMU 85.4% Leaderboard Same
Claude Opus 4.5 80.7% Visual reasoning MMMU (validation) 80.7% Leaderboard Same
Claude 3 Haiku 50.2% MMMU (val), Overall, 0-shot. Per-discipline values also given (Table 3) 50.2% Leaderboard Same
Claude 3 Sonnet 53.1% MMMU (val), Overall, 0-shot. Per-discipline values also given (Table 3) 53.1% Leaderboard Same
Phi-3.5-vision-instruct 43% MMMU (val), 0-shot (Table 5) 43% Leaderboard Same
Gemma 3 12B 59.6% MMMU (val), IT (Table 6 and Table 16) 59.6% Leaderboard Same
Gemma 3 4B 48.8% MMMU (val), IT (Table 6 and Table 16) 48.8% Leaderboard Same

One logged change that moves scores

Changes by the maintainers, so a score from before a change may not compare with one from after it. Newest first, each with the maintainers' own source. The list may be incomplete. What we log.

  1. Leaderboard rules changed February 12th, 2026

    The MMMU team released the test answers, allowing local test scoring. Later test results no longer come exclusively from evaluation against hidden answers. Source

Versions

More in Vision

All 636 in Vision
  • MMMU-Pro In use Harder MMMU: college-level multimodal questions with more options and vision-only inputs to remove text shortcuts. GPT-5.6 Sol 84.6%
  • CharXiv In use Chart understanding on real arXiv figures. Reasoning questions require synthesizing information from complex charts. Claude Fable 5 93.5%
  • MathVista In use Math reasoning in visual contexts (charts, geometry, puzzles) from 31 datasets. Answer accuracy. Seed2.1 Pro 90.7%
  • MATH-Vision (MathVision) In use 3,040 competition math problems with visual context. Answer accuracy. Qwen 3.8 Max 97.7%
  • MMStar In use Models answer 1,500 human-curated image questions that cannot be solved without the image, across 6 core capabilities. Scored by accuracy. Qwen 3.8 Max 85.9%
  • ChartQA In use Models answer human-written and generated questions about chart images that need visual and arithmetic reasoning. Scored by relaxed accuracy with a 5 percent numeric tolerance. Command A Vision 90.9%

Data audit

All 10 checks pass. Every benchmark

Catalog record 2 pass
  • Pass Task access All tasks are public.
  • Pass Confidence Checked against a primary source.
Scores 3 pass 2 notes
  • Pass Independent runs Scores from the official leaderboard (186 entries), launch posts (93 scores) and system cards (51 scores).
  • Pass Models scored 202 models we track, plus 49 other entries on its leaderboard.
  • Pass Newest score The newest is from October 2026, for MiniCPM-V-4.7-35B-A3B.
  • Note Frontier models None of the top 10 has a score, which is fine for a retired test. The strongest tested is Claude Opus 4.5 (#62).
  • Note Headroom Saturated. The best is 86%, past 85% since November 2025.
Leaderboard import 3 pass
  • Pass Importer We read the board on mmmu-benchmark.github.io: 140 rows for models we track and 49 other entries at the last read.
  • Pass Last read November 18th, 2026.
  • Pass Read worked The last read worked.
Consistency 2 pass
  • Pass Lab claims All 39 pairs agree within 10 points.
  • Pass Known issues No published audit found problems.

How we check