Benchmark Almanac

GPQA Diamond

Gemini 4 Carbon 97% leads since October 2026
Gemini 4 Carbon 97% leads since October 2026
GPT-6.2 Astra 97% leads since November 2026
In use

The official leaderboard hasn’t scored a model released after GPT-6.2 Astra (November 2026). Labs report their own numbers for one newer model: Inkling 2 Mini at 86.6%.

198 graduate-level 'Google-proof' multiple-choice questions in biology, chemistry and physics.

Saturated (about 94-96%). Several 2026 cards use it only as a substrate for CoT-controllability or monitor-evasion tests.

Released
November 2023
Kind
Science questions
Level
Expert
Scored
Checked automatically
Answers
Multiple choice
Tasks
All public
Measures
Capability
Language
English
In and out
Text → Text
Interaction
Single turn
Items from
Another benchmark
Refresh
One fixed set
Run by
Anyone
Based on
GPQA Main
Strongest model tested
GPT-6.2 Astra #1 on the capability index
Last in a launch post
November 2026
Last model added
November 2026
Scores refreshed
November 20th, 2026

In the authors’ words

We present GPQA, a challenging dataset of 448 multiple-choice questions written by domain experts in biology, physics, and chemistry. We ensure that the questions are high-quality and extremely difficult: experts who have or are pursuing PhDs in the corresponding domains reach 65% accuracy (74% when discounting clear mistakes the experts identified in retrospect), while highly skilled non-expert validators only reach 34% accuracy, despite spending on average over 30 minutes with unrestricted access to the web (i.e., the questions are "Google-proof"). The questions are also difficult for state-of-the-art AI systems, with our strongest GPT-4 based baseline achieving 39% accuracy. If we are to use future AI systems to help us answer very hard questions, for example, when developing new scientific knowledge, we need to develop scalable oversight methods that enable humans to supervise their outputs, which may be difficult even if the supervisors are themselves skilled and knowledgeable. The difficulty of GPQA both for skilled non-experts and frontier AI systems should enable realistic scalable oversight experiments, which we hope can help devise ways for human experts to reliably get truthful information from AI systems that surpass human capabilities.

Abstract of GPQA: A Graduate-Level Google-Proof Q&A Benchmark (arXiv:2311.12022, CC0)
20
Models scored on its own leaderboard
258
Launch posts list it, from 38 labs
168
System cards report it, from 32 labs

Gemini 4 Carbon leads with 97%

Best score per model from the benchmark's own leaderboard, read on November 20th, 2026. Where a model ran with several settings or harnesses, we keep its best.

Gemini 4 Carbon leads with 97% 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.

GPT-6.2 Astra leads with 97%, 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.

  1. 1 Gemini 4 Carbon 97%
  2. 2 Grok 4.6 95%
  3. 3 GPT-6 Astra 95%
  4. 4 Gemini 4 Argon 95%
  5. 5 Gemini 3.1 Pro 93.9%
  6. 6 GPT-6.1 Sol 93.9%
  7. 7 Gemini 3.8 Flash 92.9%
  8. 8 Claude Opus 5 92.9%
  9. 9 Grok 4.7 92.6%
  10. 10 GPT-6 Sol 91.9%
  11. 11 Claude Sonnet 5.5 91.9%
  12. 12 Claude Opus 5.5 90.8%
  13. 13 Gemini 3.6 Flash 89.9%
  14. 14 DeepSeek V4.1 Flash 1017 89.4%
  15. 15 Claude Haiku 5.5 84.8%
  16. 16 Gemma 4 26B A4B 83.2%
  17. 17 Gemma 4 31B IT 82.8%
  18. 18 GPT-6 Luna 81.8%
  19. 19 GPT-5.6 Luna 80.8%
  20. 20 GPT-5.6 Terra 79.3%

Source: Official GPQA Diamond leaderboard

231 models. Scroll sideways for the rest.

  1. 97.0 Gemini 4 Carbon
  2. 96.8 GPT-6.2 Astra
  3. 96.8 Gemini 4 Hydrogen
  4. 96.4 Gemini 4 Argon
  5. 96.0 Claude Fable 5.2
  6. 95.8 GPT-6 Astra
  7. 95.6 Claude Sonnet 5.5
  8. 95.4 Gemini 3.8 Flash
  9. 95.4 GPT-6.1 Sol
  10. 95.0 Grok 4.6
  11. 94.8 Gemini 3.7 Flash
  12. 94.6 GPT-5.4 Pro
  13. 94.4 Gemini 3.1 Pro
  14. 94.3 GPT-6 Sol
  15. 94.3 GPT-6.1 Terra
  16. 94.2 Kimi K3.1 Pro
  17. 94.1 Gemini 3.6 Flash
  18. 94.1 Claude Opus 5.5
  19. 94.0 GPT-5.5
  20. 93.9 GPT-5.5 Pro
  21. 93.9 Claude Fable 5
  22. 93.9 Claude Opus 5
  23. 93.5 GPT-5.6 Sol
  24. 93.4 Grok 4.5
  25. 93.3 GPT-5.6 Terra
  26. 93.3 GPT-5.4
  27. 93.2 DeepSeek V4.1 Flash 1017
  28. 93.1 Kimi K3
  29. 93.1 Doubao Seed Evolving
  30. 92.8 Gemini 3.5 Flash
  31. 92.7 Grok 4.7
  32. 92.7 Qwen 3.8 Max
  33. 92.6 Gemini 3 Pro
  34. 92.3 Qwen3.8 Max (0902)
  35. 91.9 GLM-5.2
  36. 91.7 DeepSeek V4 Pro 0813
  37. 91.6 GPT-5.6 Luna
  38. 91.4 GPT-5.2
  39. 91.0 Claude Opus 4.8
  40. 91.0 DeepSeek V4 Flash 0731
  41. 90.9 DeepSeek-V4-Pro
  42. 90.9 Qwen3.7-Max
  43. 90.9 MiniMax-M3
  44. 90.9 GLM-5.3
  45. 90.8 Kimi K2.6
  46. 90.5 Claude Opus 4.6
  47. 90.5 Claude Sonnet 5
  48. 90.5 GPT-6 Luna
  49. 90.2 Claude Opus 4.7
  50. 90.2 GLM-5.3-Flash
  51. 90.2 Mistral Large 4
  52. 89.9 GLM-5.1
  53. 89.8 DeepSeek V4.1 Flash
  54. 89.8 Muse Spark
  55. 89.7 Claude Haiku 5.5
  56. 89.6 Doubao Seed 2.1 Turbo
  57. 89.4 Gemini 3 Flash
  58. 89.3 Grok 4.20
  59. 89.3 Doubao Seed 2.1 Pro
  60. 88.8 Grok 4.3 Beta
  61. 88.6 Muse Spark Open
  62. 88.5 Inkling-Small
  63. 88.4 Qwen 3.6 Plus
  64. 88.3 Inkling
  65. 88.2 Doubao-Seed-2.0 Pro
  66. 88.1 Doubao Seed 2.0 Lite
  67. 88.1 Mistral Large 4 Preview
  68. 87.9 Qwen3.7-Plus
  69. 87.9 Kimi K2.7 Code
  70. 87.8 GLM-5
  71. 87.6 GPT-5.1
  72. 87.6 Kimi K2.5
  73. 87.4 Claude Sonnet 4.6
  74. 87.4 Qwen 3.6 Max (Preview)
  75. 87.0 Grok 4
  76. 86.9 GPT-5.4 Mini
  77. 86.4 Qwen3.5 397B-A17B
  78. 86.2 GPT-5
  79. 86.0 Claude Opus 4.5
  80. 85.9 Qwen3.6 27B
  81. 85.3 Nemotron 3 Ultra
  82. 85.3 Gemini 2.5 Pro
  83. 84.8 Qwen 3.5 Plus (hosted 397B-A17B)
  84. 84.8 Qwen 3.6 35B-A3B
  85. 84.2 Kimi K2 Thinking
  86. 83.8 Gemini 2.5 Pro
  87. 83.5 Qwen3.5-35B-A3B
  88. 83.4 DeepSeek-V3.2
  89. 83.3 GLM-4.7
  90. 83.3 Qwen 3.6 Flash
  91. 83.3 Gemini 3.5 Flash-Lite
  92. 83.2 Gemma 4 26B A4B
  93. 82.8 Gemma 4 31B IT
  94. 82.5 GPT-5.5 Instant
  95. 82.3 Claude Sonnet 4.5
  96. 82.3 Qwen 3.5 Flash (hosted 35B-A3B)
  97. 82.3 Qwen3.7 Flash
  98. 81.8 o3
  99. 81.8 Gemini 3.1 Flash-Lite
  100. 80.0 Qwen3-235B-A22B-Thinking
  101. 79.7 Claude 3.7 Sonnet
  102. 79.6 o4-mini
  103. 79.2 Claude Sonnet 4
  104. 79.0 Qwen3.5-9B
  105. 78.5 GPT-5.4 Nano
  106. 77.6 Doubao-Seed-1.6
  107. 77.3 Claude Opus 4.1
  108. 77.0 o3-mini
  109. 76.8 o1
  110. 76.3 DeepSeek-R1
  111. 76.3 Grok-3 mini
  112. 76.3 Claude Opus 4
  113. 75.8 Grok 3
  114. 75.8 gpt-oss-120b
  115. 75.0 GPT-5 mini
  116. 72.6 Qwen3-Max
  117. 71.7 DeepSeek-R1
  118. 71.5 seed-oss-36b-instruct
  119. 71.2 Claude Haiku 4.5
  120. 70.7 Qwen3-235B-A22B
  121. 70.1 Qwen3-30B-A3B-Thinking
  122. 69.4 GPT-5 nano
  123. 68.7 GPT-4.5
  124. 67.6 DeepSeek-V3
  125. 67.0 Llama 4 Maverick
  126. 66.9 GPT-4.1
  127. 66.7 Gemini 2.5 Pro
  128. 65.8 GPT-4.1 mini
  129. 65.7 Qwen3-32B
  130. 65.7 Gemini 2.0 Pro
  131. 65.4 QWQ-Plus
  132. 65.3 QwQ-32B
  133. 64.1 DeepSeek-R1-Distill-Qwen-32B
  134. 64.1 Gemini 2.0 Flash
  135. 63.8 Qwen3-14B
  136. 62.4 o1-mini
  137. 61.7 Qwen3-30B-A3B
  138. 60.8 gpt-oss-20b
  139. 60.5 glm-4.7-flash
  140. 59.5 Mistral Medium 3
  141. 57.2 Gemini 1.5 Pro
  142. 57.1 Gemini 2.0 Flash Thinking
  143. 56.8 Qwen3-8B
  144. 56.5 DeepSeek-V3
  145. 56.1 Qwen2.5-Max
  146. 56.1 Phi-4
  147. 56.1 Magistral Small 1.0
  148. 55.7 DeepSeek-R1-Distill-Llama-70B
  149. 55.6 Qwen3-30B-A3B-Instruct
  150. 55.3 Claude 3.5 Sonnet (October 2024)
  151. 54.0 Claude 3.5 Sonnet
  152. 53.8 Grok-2
  153. 52.3 Qwen3-4B
  154. 51.8 Llama 4 Scout
  155. 51.3 Mistral Large 2
  156. 50.9 Llama 3.1-405B
  157. 50.3 o1-preview
  158. 49.2 GPT-4o
  159. 49.1 Qwen2.5-72B
  160. 49.0 Mistral Small 3.2
  161. 49.0 Mistral Large 2
  162. 48.9 GPT-4.1 nano
  163. 48.9 GPT-4o
  164. 48.1 Qwen Plus
  165. 47.9 GPT-4o
  166. 47.7 Gemma 3 27B
  167. 47.6 Magistral Small 1.2
  168. 47.5 Mistral Small 3.1
  169. 47.4 Llama 3.3 70B
  170. 47.3 Gemini 1.5 Flash
  171. 47.3 Mistral Small 3
  172. 47.2 Claude 3 Opus
  173. 46.6 GPT-4 Turbo
  174. 46.3 Tulu 3 (Tülu 3) 70B
  175. 46.1 Qwen2.5-32B
  176. 45.9 Gemini 1.5 Pro
  177. 45.8 qwen3-4b-instruct-2507
  178. 45.1 glm-4.7-flash_none
  179. 44.7 DeepSeek-R1-Distill-Qwen-14B
  180. 44.2 Llama 3.1-70B
  181. 43.4 WizardLM-2 8x22B
  182. 42.4 GPT-4 Turbo
  183. 41.8 Qwen-Turbo
  184. 41.0 Llama 3.2 90B
  185. 40.8 Qwen2-72B
  186. 40.6 Claude 3 Sonnet
  187. 40.6 Llama 3-70B
  188. 40.4 Gemini 1.5 Flash
  189. 39.5 Gemma 3 12B
  190. 38.8 Mistral Large
  191. 38.1 Claude 3.5 Haiku
  192. 38.0 Qwen3-1.7B
  193. 37.7 GPT-4o mini
  194. 37.5 Hermes 2 Theta Llama-3 70B
  195. 36.5 Gemma 2 27B
  196. 36.3 Claude 3 Haiku
  197. 35.7 GPT-4
  198. 35.5 Qwen2.5-7B
  199. 34.7 Claude 2
  200. 34.1 Mixtral 8x22B
  201. 34.0 Gemini 1.0 Pro
  202. 33.9 Eurus-2-7B-PRIME
  203. 33.6 DeepSeek-R1-Distill-Qwen-1.5B
  204. 33.0 Claude 2.1
  205. 33.0 Gemini 1.5 Flash 8B
  206. 32.9 DBRX
  207. 32.0 Yi-1.5-34B
  208. 30.7 Qwen1.5-32B
  209. 30.6 GPT-4
  210. 30.6 Mixtral 8x7B
  211. 29.9 Mistral NeMo
  212. 28.8 Qwen1.5-72B
  213. 28.3 granite-4.0-micro
  214. 28.0 GPT-3.5 Turbo
  215. 27.6 phi-3-medium 14B
  216. 27.5 Gemma 2 9B
  217. 27.2 GPT-3.5 Turbo
  218. 27.1 Ministral 8B
  219. 27.0 Llama 3.1-8B
  220. 26.3 Llama 2-70B
  221. 26.1 Llama 3-8B
  222. 25.3 Ministral 3B
  223. 24.6 DeepSeek LLM 67B
  224. 24.0 granite-4.0-1b
  225. 23.9 Llama 3.2 1B
  226. 23.2 Gemma 3 4B
  227. 19.9 Gemma 3 1B
  228. 15.2 Mistral 7B v0.3
  229. 14.7 Yi-34B
  230. 11.2 granite-4.0-350m
  231. 9.28 deepseek-r1-0528-qwen3-8b
  1. 1 Gemini 4 Carbon 97%
  2. 2 GPT-6.2 Astra max 96.8%
  3. 3 Gemini 4 Hydrogen xhigh 96.8%
  4. 4 Gemini 4 Argon high 96.4%
  5. 5 Claude Fable 5.2 with fallback, max 96%
  6. 6 GPT-6 Astra max 95.8%
  7. 7 Claude Sonnet 5.5 max 95.6%
  8. 8 Gemini 3.8 Flash high 95.4%
  9. 9 GPT-6.1 Sol max 95.4%
  10. 10 Grok 4.6 95%
  11. 11 Gemini 3.7 Flash high 94.8%
  12. 12 GPT-5.4 Pro xhigh 94.6%
  13. 13 Gemini 3.1 Pro high 94.4%
  14. 14 GPT-6 Sol max 94.3%
  15. 15 GPT-6.1 Terra max 94.3%
  16. 16 Kimi K3.1 Pro Together, max 94.2%
  17. 17 Gemini 3.6 Flash high 94.1%
  18. 18 Claude Opus 5.5 with fallback, max 94.1%
  19. 19 GPT-5.5 xhigh 94%
  20. 20 GPT-5.5 Pro xhigh 93.9%
  21. 21 Claude Fable 5 with fallback, max 93.9%
  22. 22 Claude Opus 5 max 93.9%
  23. 23 GPT-5.6 Sol max 93.5%
  24. 24 Grok 4.5 high 93.4%
  25. 25 GPT-5.6 Terra max 93.3%
  26. 26 GPT-5.4 xhigh 93.3%
  27. 27 DeepSeek V4.1 Flash 1017 max 93.2%
  28. 28 Kimi K3 max 93.1%
  29. 29 Doubao Seed Evolving Nov 2026, high 93.1%
  30. 30 Gemini 3.5 Flash high 92.8%
  31. 31 Grok 4.7 xhigh 92.7%
  32. 32 Qwen 3.8 Max xhigh 92.7%
  33. 33 Gemini 3 Pro 92.6%
  34. 34 Qwen3.8 Max (0902) xhigh 92.3%
  35. 35 GLM-5.2 max 91.9%
  36. 36 DeepSeek V4 Pro 0813 max 91.7%
  37. 37 GPT-5.6 Luna max 91.6%
  38. 38 GPT-5.2 xhigh 91.4%
  39. 39 Claude Opus 4.8 max 91%
  40. 40 DeepSeek V4 Flash 0731 max 91%
  41. 41 DeepSeek-V4-Pro high 90.9%
  42. 42 Qwen3.7-Max 90.9%
  43. 43 MiniMax-M3 90.9%
  44. 44 GLM-5.3 max 90.9%
  45. 45 Kimi K2.6 90.8%
  46. 46 Claude Opus 4.6 32k thinking 90.5%
  47. 47 Claude Sonnet 5 xhigh 90.5%
  48. 48 GPT-6 Luna max 90.5%
  49. 49 Claude Opus 4.7 xhigh 90.2%
  50. 50 GLM-5.3-Flash max 90.2%
  51. 51 Mistral Large 4 high 90.2%
  52. 52 GLM-5.1 89.9%
  53. 53 DeepSeek V4.1 Flash max 89.8%
  54. 54 Muse Spark 89.8%
  55. 55 Claude Haiku 5.5 max 89.7%
  56. 56 Doubao Seed 2.1 Turbo high 89.6%
  57. 57 Gemini 3 Flash high 89.4%
  58. 58 Grok 4.20 89.3%
  59. 59 Doubao Seed 2.1 Pro high 89.3%
  60. 60 Grok 4.3 Beta high 88.8%
  61. 61 Muse Spark Open xhigh 88.6%
  62. 62 Inkling-Small xhigh 88.5%
  63. 63 Qwen 3.6 Plus 2026-04-02 88.4%
  64. 64 Inkling xhigh 88.3%
  65. 65 Doubao-Seed-2.0 Pro high 88.2%
  66. 66 Doubao Seed 2.0 Lite Apr 2026, high 88.1%
  67. 67 Mistral Large 4 Preview high 88.1%
  68. 68 Qwen3.7-Plus 87.9%
  69. 69 Kimi K2.7 Code 87.9%
  70. 70 GLM-5 87.8%
  71. 71 GPT-5.1 high 87.6%
  72. 72 Kimi K2.5 Fireworks 87.6%
  73. 73 Claude Sonnet 4.6 32k thinking 87.4%
  74. 74 Qwen 3.6 Max (Preview) 87.4%
  75. 75 Grok 4 87%
  76. 76 GPT-5.4 Mini xhigh 86.9%
  77. 77 Qwen3.5 397B-A17B none 86.4%
  78. 78 GPT-5 high 86.2%
  79. 79 Claude Opus 4.5 32k thinking 86%
  80. 80 Qwen3.6 27B 85.9%
  81. 81 Nemotron 3 Ultra 85.3%
  82. 82 Gemini 2.5 Pro Jun 2025 85.3%
  83. 83 Qwen 3.5 Plus (hosted 397B-A17B) 84.8%
  84. 84 Qwen 3.6 35B-A3B none 84.8%
  85. 85 Kimi K2 Thinking 84.2%
  86. 86 Gemini 2.5 Pro Mar 2025 83.8%
  87. 87 Qwen3.5-35B-A3B 83.5%
  88. 88 DeepSeek-V3.2 Thinking 83.4%
  89. 89 GLM-4.7 83.3%
  90. 90 Qwen 3.6 Flash 2026-04-16 83.3%
  91. 91 Gemini 3.5 Flash-Lite high 83.3%
  92. 92 Gemma 4 26B A4B 83.2%
  93. 93 Gemma 4 31B IT 82.8%
  94. 94 GPT-5.5 Instant 82.5%
  95. 95 Claude Sonnet 4.5 59k thinking 82.3%
  96. 96 Qwen 3.5 Flash (hosted 35B-A3B) 82.3%
  97. 97 Qwen3.7 Flash 82.3%
  98. 98 o3 high 81.8%
  99. 99 Gemini 3.1 Flash-Lite high 81.8%
  100. 100 Qwen3-235B-A22B-Thinking Jul 2025 80%
  101. 101 Claude 3.7 Sonnet 64k thinking 79.7%
  102. 102 o4-mini high 79.6%
  103. 103 Claude Sonnet 4 59K 79.2%
  104. 104 Qwen3.5-9B 79%
  105. 105 GPT-5.4 Nano high 78.5%
  106. 106 Doubao-Seed-1.6 thinking 77.6%
  107. 107 Claude Opus 4.1 16K 77.3%
  108. 108 o3-mini high 77%
  109. 109 o1 high 76.8%
  110. 110 DeepSeek-R1 May 2025 76.3%
  111. 111 Grok-3 mini low 76.3%
  112. 112 Claude Opus 4 16K 76.3%
  113. 113 Grok 3 75.8%
  114. 114 gpt-oss-120b high 75.8%
  115. 115 GPT-5 mini high 75%
  116. 116 Qwen3-Max 72.6%
  117. 117 DeepSeek-R1 71.7%
  118. 118 seed-oss-36b-instruct 71.5%
  119. 119 Claude Haiku 4.5 32K 71.2%
  120. 120 Qwen3-235B-A22B 70.7%
  121. 121 Qwen3-30B-A3B-Thinking Jul 2025 70.1%
  122. 122 GPT-5 nano high 69.4%
  123. 123 GPT-4.5 68.7%
  124. 124 DeepSeek-V3 Mar 2025 67.6%
  125. 125 Llama 4 Maverick FP8 67%
  126. 126 GPT-4.1 66.9%
  127. 127 Gemini 2.5 Pro May 2025 66.7%
  128. 128 GPT-4.1 mini 65.8%
  129. 129 Qwen3-32B 65.7%
  130. 130 Gemini 2.0 Pro 65.7%
  131. 131 QWQ-Plus 65.4%
  132. 132 QwQ-32B 65.3%
  133. 133 DeepSeek-R1-Distill-Qwen-32B 64.1%
  134. 134 Gemini 2.0 Flash Feb 2025 64.1%
  135. 135 Qwen3-14B 63.8%
  136. 136 o1-mini high 62.4%
  137. 137 Qwen3-30B-A3B 61.7%
  138. 138 gpt-oss-20b medium 60.8%
  139. 139 glm-4.7-flash 60.5%
  140. 140 Mistral Medium 3 59.5%
  141. 141 Gemini 1.5 Pro Sep 2024 57.2%
  142. 142 Gemini 2.0 Flash Thinking Jan 2025 57.1%
  143. 143 Qwen3-8B 56.8%
  144. 144 DeepSeek-V3 56.5%
  145. 145 Qwen2.5-Max 56.1%
  146. 146 Phi-4 56.1%
  147. 147 Magistral Small 1.0 56.1%
  148. 148 DeepSeek-R1-Distill-Llama-70B 55.7%
  149. 149 Qwen3-30B-A3B-Instruct Jul 2025 55.6%
  150. 150 Claude 3.5 Sonnet (October 2024) 55.3%
  151. 151 Claude 3.5 Sonnet Jun 2024 54%
  152. 152 Grok-2 Dec 2024 53.8%
  153. 153 Qwen3-4B 52.3%
  154. 154 Llama 4 Scout 51.8%
  155. 155 Mistral Large 2 Nov 2024 51.3%
  156. 156 Llama 3.1-405B 50.9%
  157. 157 o1-preview 50.3%
  158. 158 GPT-4o Aug 2024 49.2%
  159. 159 Qwen2.5-72B 49.1%
  160. 160 Mistral Small 3.2 49%
  161. 161 Mistral Large 2 Jul 2024 49%
  162. 162 GPT-4.1 nano 48.9%
  163. 163 GPT-4o May 2024 48.9%
  164. 164 Qwen Plus Jan 2025 48.1%
  165. 165 GPT-4o Nov 2024 47.9%
  166. 166 Gemma 3 27B 47.7%
  167. 167 Magistral Small 1.2 47.6%
  168. 168 Mistral Small 3.1 47.5%
  169. 169 Llama 3.3 70B 47.4%
  170. 170 Gemini 1.5 Flash Sep 2024 47.3%
  171. 171 Mistral Small 3 47.3%
  172. 172 Claude 3 Opus 47.2%
  173. 173 GPT-4 Turbo Apr 2024 46.6%
  174. 174 Tulu 3 (Tülu 3) 70B 46.3%
  175. 175 Qwen2.5-32B 46.1%
  176. 176 Gemini 1.5 Pro May 2024 45.9%
  177. 177 qwen3-4b-instruct-2507 45.8%
  178. 178 glm-4.7-flash_none none 45.1%
  179. 179 DeepSeek-R1-Distill-Qwen-14B 44.7%
  180. 180 Llama 3.1-70B 44.2%
  181. 181 WizardLM-2 8x22B 43.4%
  182. 182 GPT-4 Turbo Nov 2023 42.4%
  183. 183 Qwen-Turbo 41.8%
  184. 184 Llama 3.2 90B 41%
  185. 185 Qwen2-72B 40.8%
  186. 186 Claude 3 Sonnet 40.6%
  187. 187 Llama 3-70B 40.6%
  188. 188 Gemini 1.5 Flash May 2024 40.4%
  189. 189 Gemma 3 12B 39.5%
  190. 190 Mistral Large 38.8%
  191. 191 Claude 3.5 Haiku Oct 2024 38.1%
  192. 192 Qwen3-1.7B 38%
  193. 193 GPT-4o mini 37.7%
  194. 194 Hermes 2 Theta Llama-3 70B 37.5%
  195. 195 Gemma 2 27B 36.5%
  196. 196 Claude 3 Haiku 36.3%
  197. 197 GPT-4 Mar 2023 35.7%
  198. 198 Qwen2.5-7B 35.5%
  199. 199 Claude 2 34.7%
  200. 200 Mixtral 8x22B 34.1%
  201. 201 Gemini 1.0 Pro 34%
  202. 202 Eurus-2-7B-PRIME 33.9%
  203. 203 DeepSeek-R1-Distill-Qwen-1.5B 33.6%
  204. 204 Claude 2.1 33%
  205. 205 Gemini 1.5 Flash 8B 33%
  206. 206 DBRX 32.9%
  207. 207 Yi-1.5-34B 32%
  208. 208 Qwen1.5-32B 30.7%
  209. 209 GPT-4 Jun 2023 30.6%
  210. 210 Mixtral 8x7B 30.6%
  211. 211 Mistral NeMo 29.9%
  212. 212 Qwen1.5-72B 28.8%
  213. 213 granite-4.0-micro 28.3%
  214. 214 GPT-3.5 Turbo Nov 2023 28%
  215. 215 phi-3-medium 14B 27.6%
  216. 216 Gemma 2 9B 27.5%
  217. 217 GPT-3.5 Turbo Jan 2024 27.2%
  218. 218 Ministral 8B 27.1%
  219. 219 Llama 3.1-8B 27%
  220. 220 Llama 2-70B 26.3%
  221. 221 Llama 3-8B 26.1%
  222. 222 Ministral 3B 25.3%
  223. 223 DeepSeek LLM 67B 24.6%
  224. 224 granite-4.0-1b 24%
  225. 225 Llama 3.2 1B 23.9%
  226. 226 Gemma 3 4B 23.2%
  227. 227 Gemma 3 1B 19.9%
  228. 228 Mistral 7B v0.3 15.2%
  229. 229 Yi-34B 14.7%
  230. 230 granite-4.0-350m 11.2%
  231. 231 deepseek-r1-0528-qwen3-8b 9.28%

Sources: Official GPQA Diamond leaderboard and Epoch AI runs (CC BY 4.0)

408 models. Scroll sideways for the rest.

  1. 97.0 GPT-6.2 Astra
  2. 97.0 Gemini 4 Carbon
  3. 96.8 Gemini 4 Hydrogen
  4. 96.4 Gemini 4 Argon
  5. 96.0 Claude Fable 5.2
  6. 96.0 GPT-6 Astra
  7. 96.0 GPT-6.2 Sol
  8. 95.6 Claude Sonnet 5.5
  9. 95.4 Gemini 3.8 Flash
  10. 95.4 GPT-6.1 Sol
  11. 95.0 Grok 4.6
  12. 94.8 Gemini 3.7 Flash
  13. 94.6 GPT-5.4 Pro
  14. 94.6 GPT-5.6 Sol
  15. 94.5 Claude Mythos Preview
  16. 94.4 Gemini 3.1 Pro
  17. 94.3 GPT-6 Sol
  18. 94.3 GPT-6.1 Terra
  19. 94.2 Claude Opus 4.7
  20. 94.2 Kimi K3.1 Pro
  21. 94.1 Gemini 3.6 Flash
  22. 94.1 Claude Opus 5.5
  23. 94.0 GPT-5.5
  24. 93.9 GPT-5.5 Pro
  25. 93.9 Claude Fable 5
  26. 93.9 Claude Opus 5
  27. 93.6 Claude Opus 4.8
  28. 93.5 Kimi K3
  29. 93.5 Step 5 Preview
  30. 93.4 Grok 4.5
  31. 93.3 GPT-5.6 Terra
  32. 93.3 GPT-5.4
  33. 93.2 GPT-5.2 Pro
  34. 93.2 DeepSeek V4.1 Flash 1017
  35. 93.1 Doubao Seed Evolving
  36. 93.0 Inkling 2 Small
  37. 92.8 Gemini 3.5 Flash
  38. 92.7 Grok 4.7
  39. 92.7 Qwen 3.8 Max
  40. 92.6 Gemini 3 Pro
  41. 92.4 GPT-5.2
  42. 92.4 Qwen3.7-Max
  43. 92.3 GPT-5.6 Luna
  44. 92.3 Tencent Hy4 preview
  45. 92.3 Qwen3.8 Max (0902)
  46. 91.9 GLM-5.2
  47. 91.7 Qwen3.8 Flash
  48. 91.7 DeepSeek V4 Pro 0813
  49. 91.3 Claude Opus 4.6
  50. 91.0 DeepSeek V4 Flash 0731
  51. 91.0 ERNIE 5.1
  52. 91.0 Qwen3.8-Omni-Flash
  53. 90.9 DeepSeek-V4-Pro
  54. 90.9 MiniMax-M3
  55. 90.9 GLM-5.3
  56. 90.9 DeepSeek V4.1 Flash
  57. 90.8 Kimi K2.6
  58. 90.5 Claude Sonnet 5
  59. 90.5 Beam 1.0
  60. 90.5 GPT-6 Luna
  61. 90.4 Gemini 3 Flash
  62. 90.4 Qwen 3.6 Plus
  63. 90.4 Tencent Hy3
  64. 90.3 Qwen3.7-Plus
  65. 90.2 GLM-5.3-Flash
  66. 90.2 Mistral Large 4
  67. 89.9 Claude Sonnet 4.6
  68. 89.9 GLM-5.1
  69. 89.8 Muse Spark
  70. 89.8 MiniMax-M2.7
  71. 89.7 Claude Haiku 5.5
  72. 89.6 Doubao Seed 2.1 Turbo
  73. 89.5 Nemotron 3.5 Super VL
  74. 89.5 Inkling-Small
  75. 89.4 GPT-5
  76. 89.3 Grok 4.20
  77. 89.3 Doubao Seed 2.1 Pro
  78. 89.2 Mercury 3
  79. 89.2 Qwen 3.8 27B
  80. 89.0 Solar Pro 4
  81. 89.0 Muse Spark Open
  82. 88.9 Seed2.0 Pro
  83. 88.9 LongCat-2.0
  84. 88.8 Grok 4.3 Beta
  85. 88.4 Grok 4 Heavy
  86. 88.4 Qwen3.5 397B-A17B
  87. 88.4 Seed2.0 Lite (0428)
  88. 88.3 Ring-2.6-1T
  89. 88.3 Inkling
  90. 88.2 Doubao-Seed-2.0 Pro
  91. 88.1 Doubao Seed 2.0 Lite
  92. 88.1 GPT-5.1
  93. 88.1 DeepSeek-V4-Flash
  94. 88.1 Mistral Large 4 Preview
  95. 88.0 GPT-5.4 Mini
  96. 87.9 Kimi K2.7 Code
  97. 87.8 GLM-5
  98. 87.8 Qwen3.6 27B
  99. 87.6 Kimi K2.5
  100. 87.5 Grok 4
  101. 87.4 Qwen3-Max-2026-01-23
  102. 87.4 Qwen 3.6 Max (Preview)
  103. 87.2 Tencent Hy3 preview
  104. 87.0 Claude Opus 4.5
  105. 87.0 Nemotron 3 Ultra
  106. 86.9 Gemini 3.1 Flash-Lite
  107. 86.6 Qwen3.5-122B-A10B
  108. 86.6 Inkling 2 Mini
  109. 86.4 Nemotron 3.5 Bolt 74B-A9B
  110. 86.4 Gemini 2.5 Pro
  111. 86.4 ERNIE 5.0
  112. 86.3 Solar Open 2
  113. 86.0 Qwen 3.6 35B-A3B
  114. 85.7 Grok 4 Fast
  115. 85.7 DeepSeek-V3.2-Speciale
  116. 85.7 GLM-4.7
  117. 85.6 GPT-5.5 Instant
  118. 85.5 Qwen3.5-27B
  119. 85.2 LongCat-Flash-Thinking-2601
  120. 85.2 MiniMax-M2.5
  121. 84.8 Qwen 3.5 Plus (hosted 397B-A17B)
  122. 84.8 Claude 3.7 Sonnet
  123. 84.6 Grok 3
  124. 84.6 MAI-Code-1-Flash
  125. 84.5 Kimi K2 Thinking
  126. 84.3 MiMo-V2-Flash
  127. 84.3 Gemma 4 31B IT
  128. 84.2 Qwen3.5-35B-A3B
  129. 84.2 MAI-Thinking-1
  130. 84.0 Grok-3 mini
  131. 84.0 Gemini 2.5 Pro
  132. 84.0 o3-pro
  133. 83.9 Qwen3.5-Omni-Plus
  134. 83.8 Claude Sonnet 4
  135. 83.8 Seed1.8
  136. 83.5 Step 3.5 Flash
  137. 83.5 Muse Glimmer
  138. 83.4 DeepSeek-V3.2
  139. 83.4 Claude Sonnet 4.5
  140. 83.3 Qwen 3.6 Flash
  141. 83.3 Gemini 3.5 Flash-Lite
  142. 83.3 o3
  143. 83.3 Claude Opus 4
  144. 83.3 gemini-robotics-er-1.5-preview
  145. 83.2 Gemma 4 26B A4B
  146. 83.0 MiniMax-M2.1
  147. 82.8 Gemini 2.5 Flash
  148. 82.8 GPT-5.4 Nano
  149. 82.3 Qwen 3.5 Flash (hosted 35B-A3B)
  150. 82.3 Qwen3.7 Flash
  151. 82.3 GPT-5 mini
  152. 82.2 K-EXAONE 2.0
  153. 81.7 Qwen3.5-9B
  154. 81.5 Seed1.6-Thinking
  155. 81.5 LongCat-Flash-Thinking
  156. 81.4 o4-mini
  157. 81.4 Nova 2.0 Pro Preview
  158. 81.1 Qwen3-235B-A22B-Thinking
  159. 81.0 DeepSeek-R1
  160. 81.0 GLM-4.6
  161. 80.9 Claude Opus 4.1
  162. 80.8 Gemini 2.5 Flash
  163. 80.7 DeepSeek-V3.1-Terminus
  164. 80.5 EXAONE 4.5 33B
  165. 80.1 gpt-oss-120b
  166. 80.1 DeepSeek-V3.1
  167. 79.9 DeepSeek-V3.2-Exp
  168. 79.7 o3-mini
  169. 79.6 Nova 2 Lite
  170. 79.2 Nemotron 3 Super
  171. 79.1 GLM-4.5
  172. 79.1 K-EXAONE
  173. 79.0 Mercury 2.5
  174. 78.8 Gemma 4 12B
  175. 78.7 Sarvam 105B
  176. 78.6 Ring-1T
  177. 78.3 o1-preview
  178. 78.3 Gemini 2.5 Flash
  179. 78.0 MiniMax-M2
  180. 77.7 Cogito v2.1
  181. 77.6 Doubao-Seed-1.6
  182. 77.3 Seed-Thinking-v1.5
  183. 77.3 Intern-S1
  184. 77.2 Qwen3-Next-80B-A3B
  185. 77.1 Qwen3-VL-235B-A22B
  186. 77.1 Spark-X2.6-4B
  187. 76.8 o1
  188. 76.5 Nemotron 3.5 Lightning 30B-A3B
  189. 76.3 Trinity Large Thinking
  190. 76.3 Magistral Medium 1.2
  191. 76.2 Qwen3.5-4B
  192. 76.2 Ling-2.6-1T
  193. 76.1 Nemotron-Cascade 2 30B-A3B
  194. 76.0 Cogito v2 Preview 671B MoE
  195. 76.0 Llama-3.1-Nemotron-Ultra-253B-v1
  196. 75.4 EXAONE 4.0 32B
  197. 75.2 glm-4.7-flash
  198. 75.1 Kimi K2
  199. 75.0 GLM-4.5-Air
  200. 74.5 Qwen3-Coder-Next
  201. 74.4 LFM2.5-24B-A2B
  202. 74.4 LongCat-Flash-Omni
  203. 74.4 INTELLECT-3
  204. 74.2 Gemini 2.0 Flash Thinking
  205. 74.0 Mercury 2
  206. 73.7 Llama 4 Behemoth
  207. 73.2 LongCat-Flash-Chat
  208. 73.2 InternVL3.5-241B-A28B
  209. 73.2 DiffusionGemma 26B A4B
  210. 73.0 Nemotron 3 Nano 30B-A3B
  211. 73.0 Step 3
  212. 73.0 Claude Haiku 4.5
  213. 72.6 Qwen3-Max
  214. 72.4 Beam 1.0 Base
  215. 72.2 Nemotron 3 Nano Omni 30B-A3B
  216. 72.0 Llama-3.3-Nemotron-Super-49B-v1.5
  217. 71.9 Solar Pro 3 (March 2026 update)
  218. 71.7 DeepSeek-R1
  219. 71.7 Gemini 2.5 Flash-Lite
  220. 71.5 seed-oss-36b-instruct
  221. 71.5 gpt-oss-20b
  222. 71.5 Magistral Medium 1.1
  223. 71.4 GPT-4.5
  224. 71.2 Hunyuan-A13B-Instruct
  225. 71.2 GPT-5 nano
  226. 71.2 Ministral 3 14B
  227. 71.2 Mistral Small 4
  228. 71.1 Qwen3-235B-A22B
  229. 70.8 STEP3-VL-10B
  230. 70.8 Magistral Medium 1.0
  231. 70.6 Hermes 4 405B
  232. 70.1 Qwen3-30B-A3B-Thinking
  233. 70.1 Magistral Small 1.2
  234. 70.0 MiniMax-M1-80k
  235. 69.8 Llama 4 Maverick
  236. 69.6 Qwen3-Omni-30B-A3B
  237. 69.3 Hunyuan-T1
  238. 69.3 Phi-4-Reasoning-plus
  239. 68.4 Qwen3-32B
  240. 68.2 Magistral Small 1.0
  241. 68.1 Solar Open 100B
  242. 67.6 DeepSeek-V3
  243. 67.1 Phi-4-reasoning
  244. 66.9 GPT-4.1
  245. 66.8 INTELLECT-2
  246. 66.7 Llama-3.3-Nemotron-Super-49B-v1
  247. 66.7 Gemini 2.5 Flash-Lite
  248. 66.7 Gemini 2.5 Pro
  249. 66.5 Sarvam 30B
  250. 66.4 Granite 4.2 30B
  251. 66.2 Nemotron 3.5 Super 120B-A12B Base
  252. 66.1 EXAONE Deep 32B
  253. 66.1 GLM-Z1-32B-0414
  254. 65.8 GPT-4.1 mini
  255. 65.8 Qwen3-30B-A3B
  256. 65.8 Magistral Small 1.1
  257. 65.7 Gemini 2.0 Pro
  258. 65.5 Hermes 4.3 36B
  259. 65.4 QWQ-Plus
  260. 65.3 QwQ-32B
  261. 65.2 DeepSeek-R1-Distill-Llama-70B
  262. 65.0 Claude 3.5 Sonnet (October 2024)
  263. 64.1 DeepSeek-R1-Distill-Qwen-32B
  264. 64.1 Gemini 2.0 Flash
  265. 64.1 Nemotron Nano 12B v2 VL
  266. 64.0 Qwen3-14B
  267. 64.0 nvidia-nemotron-nano-9b-v2
  268. 63.4 LFM3-1.7B
  269. 63.3 Trinity Large Preview
  270. 62.4 o1-mini
  271. 62.1 Gemini 2.0 Flash
  272. 62.0 Qwen3-8B
  273. 61.3 Falcon H1R 7B
  274. 61.1 Reka Flash 3
  275. 60.6 Cogito v1 Preview 70B
  276. 59.5 Mistral Medium 3
  277. 59.4 Claude 3.5 Sonnet
  278. 59.1 DeepSeek-V3
  279. 59.1 DeepSeek-R1-Distill-Qwen-14B
  280. 58.6 Gemma 4 E4B
  281. 58.5 Trinity Mini
  282. 58.1 Olmo 3 32B Think
  283. 57.5 Hunyuan-TurboS
  284. 57.5 Olmo 3.1 32B Think
  285. 57.2 Gemini 1.5 Pro
  286. 57.2 Llama 4 Scout
  287. 57.1 Amazon Nova Premier
  288. 56.1 Qwen2.5-Max
  289. 56.1 Phi-4
  290. 56.0 Grok-2
  291. 55.9 Qwen3-4B
  292. 55.6 Qwen3-30B-A3B-Instruct
  293. 54.4 MiniMax-Text-01
  294. 54.4 MiMo-7B-RL
  295. 53.8 Grok-2
  296. 53.6 GPT-4o
  297. 53.2 Nemotron 3 Nano 4B
  298. 52.0 Phi-4-mini-reasoning
  299. 51.6 Qwen3.5-2B
  300. 51.5 Gemini 2.0 Flash-Lite
  301. 51.3 Mistral Large 2
  302. 51.1 Llama 3.1-405B
  303. 51.0 Mercury
  304. 50.8 Cohere Command A
  305. 50.5 Llama 3.3 70B Instruct
  306. 50.4 Claude 3 Opus
  307. 50.3 GPT-4.1 nano
  308. 50.0 Nemotron 3 Ultra 550B-A55B Base
  309. 49.7 Falcon-H1-34B
  310. 49.5 Qwen2.5-32B
  311. 49.3 GPT-4 Turbo
  312. 49.2 GPT-4o
  313. 49.1 Qwen2.5-72B
  314. 49.0 Mistral Small 3.2
  315. 49.0 Mistral Large 2
  316. 49.0 Qwen2.5-VL-72B
  317. 48.1 Qwen Plus
  318. 48.0 Sarvam-M
  319. 47.9 GPT-4o
  320. 47.7 Gemma 3 27B
  321. 47.5 Mistral Small 3.1
  322. 47.4 Llama 3.3 70B
  323. 47.3 Gemini 1.5 Flash
  324. 47.3 Mistral Small 3
  325. 46.7 Llama 3.1-70B
  326. 46.3 Tulu 3 (Tülu 3) 70B
  327. 46.2 Gemini 1.5 Pro
  328. 45.8 qwen3-4b-instruct-2507
  329. 45.8 Granite 4.1 30B
  330. 45.5 Qwen2.5-14B
  331. 45.1 glm-4.7-flash_none
  332. 45.1 Phi-4-mini-flash-reasoning
  333. 43.9 Mistral Large 3
  334. 43.4 WizardLM-2 8x22B
  335. 43.4 Gemma 4 E2B
  336. 42.4 Qwen2-72B
  337. 42.4 GPT-4 Turbo
  338. 42.3 Qwen-Turbo
  339. 42.3 Kimi-VL-A3B-Thinking-2506
  340. 41.6 Claude 3.5 Haiku
  341. 41.5 Gemini 1.5 Pro
  342. 41.0 Llama 3.2 90B
  343. 40.9 Gemma 3 12B
  344. 40.6 Granite 4.0 H Small
  345. 40.6 Code World Model (CWM)
  346. 40.6 Claude 3 Sonnet
  347. 40.6 Llama 3-70B
  348. 40.4 Gemini 1.5 Flash
  349. 40.2 GPT-4o mini
  350. 40.1 Qwen3-1.7B
  351. 39.9 Qwen2.5-14B-Instruct-1M
  352. 38.9 LFM2.5-1.2B-Instruct
  353. 38.8 Mistral Large
  354. 37.9 LFM2.5-1.2B-Thinking
  355. 37.5 Hermes 2 Theta Llama-3 70B
  356. 37.4 InternLM3-8B-Instruct
  357. 36.8 Phi-3.5-MoE
  358. 36.5 Gemma 2 27B
  359. 36.4 Qwen2.5-7B
  360. 36.3 Claude 3 Haiku
  361. 35.9 OLMo 2 32B Instruct
  362. 35.7 GPT-4
  363. 35.7 GLM-4
  364. 34.7 Claude 2
  365. 34.3 phi-3-small 7.4B
  366. 34.2 Llama 3-8B
  367. 34.1 Mixtral 8x22B
  368. 34.0 Gemini 1.0 Pro
  369. 33.9 Eurus-2-7B-PRIME
  370. 33.8 DeepSeek-R1-Distill-Qwen-1.5B
  371. 33.3 Nemotron 3.5 Lightning 30B-A3B Base
  372. 33.0 Claude 2.1
  373. 33.0 Gemini 1.5 Flash 8B
  374. 32.9 DBRX
  375. 32.8 phi-3-mini 3.8B
  376. 32.8 Llama 3.1-8B
  377. 32.0 Yi-1.5-34B
  378. 31.5 LFM2-1.2B
  379. 30.8 Gemma 3 4B
  380. 30.8 Qwen2.5-Omni-7B
  381. 30.7 Qwen1.5-32B
  382. 30.6 GPT-4
  383. 30.6 Mixtral 8x7B
  384. 30.4 Phi-4 Mini
  385. 29.9 granite-4.0-1b
  386. 29.9 Mistral NeMo
  387. 29.3 LFM2-8B-A1B
  388. 28.8 Qwen1.5-72B
  389. 28.3 granite-4.0-micro
  390. 28.0 GPT-3.5 Turbo
  391. 27.8 AFM-4.5B
  392. 27.6 phi-3-medium 14B
  393. 27.5 Gemma 2 9B
  394. 27.2 Phi-3.5-mini
  395. 27.2 GPT-3.5 Turbo
  396. 27.1 Ministral 8B
  397. 26.8 ChatGLM3-6B
  398. 26.3 Llama 2-70B
  399. 25.3 Ministral 3B
  400. 24.6 DeepSeek LLM 67B
  401. 23.9 Llama 3.2 1B
  402. 23.7 Gemma 3n E4B
  403. 19.9 Gemma 3 1B
  404. 15.2 Mistral 7B v0.3
  405. 14.7 Yi-34B
  406. 11.9 Qwen3.5-0.8B
  407. 11.2 granite-4.0-350m
  408. 9.28 deepseek-r1-0528-qwen3-8b
  1. 1 GPT-6.2 Astra 97%
  2. 2 Gemini 4 Carbon 97%
  3. 3 Gemini 4 Hydrogen xhigh 96.8%
  4. 4 Gemini 4 Argon high 96.4%
  5. 5 Claude Fable 5.2 with fallback, max 96%
  6. 6 GPT-6 Astra 96%
  7. 7 GPT-6.2 Sol 96%
  8. 8 Claude Sonnet 5.5 max 95.6%
  9. 9 Gemini 3.8 Flash high 95.4%
  10. 10 GPT-6.1 Sol max 95.4%
  11. 11 Grok 4.6 95%
  12. 12 Gemini 3.7 Flash high 94.8%
  13. 13 GPT-5.4 Pro xhigh 94.6%
  14. 14 GPT-5.6 Sol 94.6%
  15. 15 Claude Mythos Preview 94.5%
  16. 16 Gemini 3.1 Pro high 94.4%
  17. 17 GPT-6 Sol max 94.3%
  18. 18 GPT-6.1 Terra max 94.3%
  19. 19 Claude Opus 4.7 94.2%
  20. 20 Kimi K3.1 Pro 94.2%
  21. 21 Gemini 3.6 Flash high 94.1%
  22. 22 Claude Opus 5.5 with fallback, max 94.1%
  23. 23 GPT-5.5 xhigh 94%
  24. 24 GPT-5.5 Pro xhigh 93.9%
  25. 25 Claude Fable 5 with fallback, max 93.9%
  26. 26 Claude Opus 5 max 93.9%
  27. 27 Claude Opus 4.8 93.6%
  28. 28 Kimi K3 93.5%
  29. 29 Step 5 Preview 93.5%
  30. 30 Grok 4.5 high 93.4%
  31. 31 GPT-5.6 Terra max 93.3%
  32. 32 GPT-5.4 xhigh 93.3%
  33. 33 GPT-5.2 Pro 93.2%
  34. 34 DeepSeek V4.1 Flash 1017 max 93.2%
  35. 35 Doubao Seed Evolving Nov 2026, high 93.1%
  36. 36 Inkling 2 Small 93%
  37. 37 Gemini 3.5 Flash high 92.8%
  38. 38 Grok 4.7 xhigh 92.7%
  39. 39 Qwen 3.8 Max xhigh 92.7%
  40. 40 Gemini 3 Pro 92.6%
  41. 41 GPT-5.2 92.4%
  42. 42 Qwen3.7-Max 92.4%
  43. 43 GPT-5.6 Luna 92.3%
  44. 44 Tencent Hy4 preview 92.3%
  45. 45 Qwen3.8 Max (0902) xhigh 92.3%
  46. 46 GLM-5.2 max 91.9%
  47. 47 Qwen3.8 Flash 91.7%
  48. 48 DeepSeek V4 Pro 0813 max 91.7%
  49. 49 Claude Opus 4.6 91.3%
  50. 50 DeepSeek V4 Flash 0731 max 91%
  51. 51 ERNIE 5.1 91%
  52. 52 Qwen3.8-Omni-Flash 91%
  53. 53 DeepSeek-V4-Pro high 90.9%
  54. 54 MiniMax-M3 90.9%
  55. 55 GLM-5.3 max 90.9%
  56. 56 DeepSeek V4.1 Flash 90.9%
  57. 57 Kimi K2.6 90.8%
  58. 58 Claude Sonnet 5 xhigh 90.5%
  59. 59 Beam 1.0 90.5%
  60. 60 GPT-6 Luna max 90.5%
  61. 61 Gemini 3 Flash 90.4%
  62. 62 Qwen 3.6 Plus 90.4%
  63. 63 Tencent Hy3 90.4%
  64. 64 Qwen3.7-Plus 90.3%
  65. 65 GLM-5.3-Flash max 90.2%
  66. 66 Mistral Large 4 high 90.2%
  67. 67 Claude Sonnet 4.6 89.9%
  68. 68 GLM-5.1 89.9%
  69. 69 Muse Spark 89.8%
  70. 70 MiniMax-M2.7 89.8%
  71. 71 Claude Haiku 5.5 max 89.7%
  72. 72 Doubao Seed 2.1 Turbo high 89.6%
  73. 73 Nemotron 3.5 Super VL 89.5%
  74. 74 Inkling-Small 89.5%
  75. 75 GPT-5 89.4%
  76. 76 Grok 4.20 89.3%
  77. 77 Doubao Seed 2.1 Pro high 89.3%
  78. 78 Mercury 3 89.2%
  79. 79 Qwen 3.8 27B 89.2%
  80. 80 Solar Pro 4 89%
  81. 81 Muse Spark Open 89%
  82. 82 Seed2.0 Pro 88.9%
  83. 83 LongCat-2.0 88.9%
  84. 84 Grok 4.3 Beta high 88.8%
  85. 85 Grok 4 Heavy 88.4%
  86. 86 Qwen3.5 397B-A17B 88.4%
  87. 87 Seed2.0 Lite (0428) 88.4%
  88. 88 Ring-2.6-1T 88.3%
  89. 89 Inkling xhigh 88.3%
  90. 90 Doubao-Seed-2.0 Pro high 88.2%
  91. 91 Doubao Seed 2.0 Lite Apr 2026, high 88.1%
  92. 92 GPT-5.1 88.1%
  93. 93 DeepSeek-V4-Flash 88.1%
  94. 94 Mistral Large 4 Preview high 88.1%
  95. 95 GPT-5.4 Mini 88%
  96. 96 Kimi K2.7 Code 87.9%
  97. 97 GLM-5 87.8%
  98. 98 Qwen3.6 27B 87.8%
  99. 99 Kimi K2.5 Fireworks 87.6%
  100. 100 Grok 4 87.5%
  101. 101 Qwen3-Max-2026-01-23 87.4%
  102. 102 Qwen 3.6 Max (Preview) 87.4%
  103. 103 Tencent Hy3 preview 87.2%
  104. 104 Claude Opus 4.5 87%
  105. 105 Nemotron 3 Ultra 87%
  106. 106 Gemini 3.1 Flash-Lite 86.9%
  107. 107 Qwen3.5-122B-A10B 86.6%
  108. 108 Inkling 2 Mini 86.6%
  109. 109 Nemotron 3.5 Bolt 74B-A9B 86.4%
  110. 110 Gemini 2.5 Pro Jun 2025 86.4%
  111. 111 ERNIE 5.0 86.4%
  112. 112 Solar Open 2 86.3%
  113. 113 Qwen 3.6 35B-A3B 86%
  114. 114 Grok 4 Fast 85.7%
  115. 115 DeepSeek-V3.2-Speciale 85.7%
  116. 116 GLM-4.7 85.7%
  117. 117 GPT-5.5 Instant 85.6%
  118. 118 Qwen3.5-27B 85.5%
  119. 119 LongCat-Flash-Thinking-2601 85.2%
  120. 120 MiniMax-M2.5 85.2%
  121. 121 Qwen 3.5 Plus (hosted 397B-A17B) 84.8%
  122. 122 Claude 3.7 Sonnet 84.8%
  123. 123 Grok 3 84.6%
  124. 124 MAI-Code-1-Flash 84.6%
  125. 125 Kimi K2 Thinking 84.5%
  126. 126 MiMo-V2-Flash 84.3%
  127. 127 Gemma 4 31B IT 84.3%
  128. 128 Qwen3.5-35B-A3B 84.2%
  129. 129 MAI-Thinking-1 84.2%
  130. 130 Grok-3 mini 84%
  131. 131 Gemini 2.5 Pro Mar 2025 84%
  132. 132 o3-pro 84%
  133. 133 Qwen3.5-Omni-Plus 83.9%
  134. 134 Claude Sonnet 4 83.8%
  135. 135 Seed1.8 83.8%
  136. 136 Step 3.5 Flash 83.5%
  137. 137 Muse Glimmer 83.5%
  138. 138 DeepSeek-V3.2 Thinking 83.4%
  139. 139 Claude Sonnet 4.5 83.4%
  140. 140 Qwen 3.6 Flash 2026-04-16 83.3%
  141. 141 Gemini 3.5 Flash-Lite high 83.3%
  142. 142 o3 83.3%
  143. 143 Claude Opus 4 83.3%
  144. 144 gemini-robotics-er-1.5-preview 83.3%
  145. 145 Gemma 4 26B A4B 83.2%
  146. 146 MiniMax-M2.1 83%
  147. 147 Gemini 2.5 Flash Jun 2025 82.8%
  148. 148 GPT-5.4 Nano 82.8%
  149. 149 Qwen 3.5 Flash (hosted 35B-A3B) 82.3%
  150. 150 Qwen3.7 Flash 82.3%
  151. 151 GPT-5 mini 82.3%
  152. 152 K-EXAONE 2.0 82.2%
  153. 153 Qwen3.5-9B 81.7%
  154. 154 Seed1.6-Thinking 81.5%
  155. 155 LongCat-Flash-Thinking 81.5%
  156. 156 o4-mini 81.4%
  157. 157 Nova 2.0 Pro Preview 81.4%
  158. 158 Qwen3-235B-A22B-Thinking Jul 2025 81.1%
  159. 159 DeepSeek-R1 May 2025 81%
  160. 160 GLM-4.6 81%
  161. 161 Claude Opus 4.1 80.9%
  162. 162 Gemini 2.5 Flash Sep 2025 80.8%
  163. 163 DeepSeek-V3.1-Terminus 80.7%
  164. 164 EXAONE 4.5 33B 80.5%
  165. 165 gpt-oss-120b 80.1%
  166. 166 DeepSeek-V3.1 80.1%
  167. 167 DeepSeek-V3.2-Exp 79.9%
  168. 168 o3-mini 79.7%
  169. 169 Nova 2 Lite 79.6%
  170. 170 Nemotron 3 Super 79.2%
  171. 171 GLM-4.5 79.1%
  172. 172 K-EXAONE 79.1%
  173. 173 Mercury 2.5 79%
  174. 174 Gemma 4 12B 78.8%
  175. 175 Sarvam 105B 78.7%
  176. 176 Ring-1T 78.6%
  177. 177 o1-preview 78.3%
  178. 178 Gemini 2.5 Flash Apr 2025 78.3%
  179. 179 MiniMax-M2 78%
  180. 180 Cogito v2.1 77.7%
  181. 181 Doubao-Seed-1.6 thinking 77.6%
  182. 182 Seed-Thinking-v1.5 77.3%
  183. 183 Intern-S1 77.3%
  184. 184 Qwen3-Next-80B-A3B 77.2%
  185. 185 Qwen3-VL-235B-A22B 77.1%
  186. 186 Spark-X2.6-4B 77.1%
  187. 187 o1 high 76.8%
  188. 188 Nemotron 3.5 Lightning 30B-A3B 76.5%
  189. 189 Trinity Large Thinking 76.3%
  190. 190 Magistral Medium 1.2 76.3%
  191. 191 Qwen3.5-4B 76.2%
  192. 192 Ling-2.6-1T 76.2%
  193. 193 Nemotron-Cascade 2 30B-A3B 76.1%
  194. 194 Cogito v2 Preview 671B MoE 76%
  195. 195 Llama-3.1-Nemotron-Ultra-253B-v1 76%
  196. 196 EXAONE 4.0 32B 75.4%
  197. 197 glm-4.7-flash 75.2%
  198. 198 Kimi K2 Jul 2025 75.1%
  199. 199 GLM-4.5-Air 75%
  200. 200 Qwen3-Coder-Next 74.5%
  201. 201 LFM2.5-24B-A2B 74.4%
  202. 202 LongCat-Flash-Omni 74.4%
  203. 203 INTELLECT-3 74.4%
  204. 204 Gemini 2.0 Flash Thinking Jan 2025 74.2%
  205. 205 Mercury 2 74%
  206. 206 Llama 4 Behemoth 73.7%
  207. 207 LongCat-Flash-Chat 73.2%
  208. 208 InternVL3.5-241B-A28B 73.2%
  209. 209 DiffusionGemma 26B A4B 73.2%
  210. 210 Nemotron 3 Nano 30B-A3B 73%
  211. 211 Step 3 73%
  212. 212 Claude Haiku 4.5 73%
  213. 213 Qwen3-Max 72.6%
  214. 214 Beam 1.0 Base 72.4%
  215. 215 Nemotron 3 Nano Omni 30B-A3B 72.2%
  216. 216 Llama-3.3-Nemotron-Super-49B-v1.5 72%
  217. 217 Solar Pro 3 (March 2026 update) 71.9%
  218. 218 DeepSeek-R1 71.7%
  219. 219 Gemini 2.5 Flash-Lite Sep 2025 71.7%
  220. 220 seed-oss-36b-instruct 71.5%
  221. 221 gpt-oss-20b 71.5%
  222. 222 Magistral Medium 1.1 71.5%
  223. 223 GPT-4.5 71.4%
  224. 224 Hunyuan-A13B-Instruct 71.2%
  225. 225 GPT-5 nano 71.2%
  226. 226 Ministral 3 14B 71.2%
  227. 227 Mistral Small 4 71.2%
  228. 228 Qwen3-235B-A22B 71.1%
  229. 229 STEP3-VL-10B 70.8%
  230. 230 Magistral Medium 1.0 70.8%
  231. 231 Hermes 4 405B 70.6%
  232. 232 Qwen3-30B-A3B-Thinking Jul 2025 70.1%
  233. 233 Magistral Small 1.2 70.1%
  234. 234 MiniMax-M1-80k 70%
  235. 235 Llama 4 Maverick 69.8%
  236. 236 Qwen3-Omni-30B-A3B 69.6%
  237. 237 Hunyuan-T1 69.3%
  238. 238 Phi-4-Reasoning-plus 69.3%
  239. 239 Qwen3-32B 68.4%
  240. 240 Magistral Small 1.0 68.2%
  241. 241 Solar Open 100B 68.1%
  242. 242 DeepSeek-V3 Mar 2025 67.6%
  243. 243 Phi-4-reasoning 67.1%
  244. 244 GPT-4.1 66.9%
  245. 245 INTELLECT-2 66.8%
  246. 246 Llama-3.3-Nemotron-Super-49B-v1 66.7%
  247. 247 Gemini 2.5 Flash-Lite Jun 2025 66.7%
  248. 248 Gemini 2.5 Pro May 2025 66.7%
  249. 249 Sarvam 30B 66.5%
  250. 250 Granite 4.2 30B 66.4%
  251. 251 Nemotron 3.5 Super 120B-A12B Base 66.2%
  252. 252 EXAONE Deep 32B 66.1%
  253. 253 GLM-Z1-32B-0414 66.1%
  254. 254 GPT-4.1 mini 65.8%
  255. 255 Qwen3-30B-A3B 65.8%
  256. 256 Magistral Small 1.1 65.8%
  257. 257 Gemini 2.0 Pro 65.7%
  258. 258 Hermes 4.3 36B 65.5%
  259. 259 QWQ-Plus 65.4%
  260. 260 QwQ-32B 65.3%
  261. 261 DeepSeek-R1-Distill-Llama-70B 65.2%
  262. 262 Claude 3.5 Sonnet (October 2024) 65%
  263. 263 DeepSeek-R1-Distill-Qwen-32B 64.1%
  264. 264 Gemini 2.0 Flash Feb 2025 64.1%
  265. 265 Nemotron Nano 12B v2 VL 64.1%
  266. 266 Qwen3-14B 64%
  267. 267 nvidia-nemotron-nano-9b-v2 64%
  268. 268 LFM3-1.7B 63.4%
  269. 269 Trinity Large Preview 63.3%
  270. 270 o1-mini high 62.4%
  271. 271 Gemini 2.0 Flash Dec 2024 62.1%
  272. 272 Qwen3-8B 62%
  273. 273 Falcon H1R 7B 61.3%
  274. 274 Reka Flash 3 61.1%
  275. 275 Cogito v1 Preview 70B 60.6%
  276. 276 Mistral Medium 3 59.5%
  277. 277 Claude 3.5 Sonnet 59.4%
  278. 278 DeepSeek-V3 59.1%
  279. 279 DeepSeek-R1-Distill-Qwen-14B 59.1%
  280. 280 Gemma 4 E4B 58.6%
  281. 281 Trinity Mini 58.5%
  282. 282 Olmo 3 32B Think 58.1%
  283. 283 Hunyuan-TurboS 57.5%
  284. 284 Olmo 3.1 32B Think 57.5%
  285. 285 Gemini 1.5 Pro Sep 2024 57.2%
  286. 286 Llama 4 Scout 57.2%
  287. 287 Amazon Nova Premier 57.1%
  288. 288 Qwen2.5-Max 56.1%
  289. 289 Phi-4 56.1%
  290. 290 Grok-2 Aug 2024 56%
  291. 291 Qwen3-4B 55.9%
  292. 292 Qwen3-30B-A3B-Instruct Jul 2025 55.6%
  293. 293 MiniMax-Text-01 54.4%
  294. 294 MiMo-7B-RL 54.4%
  295. 295 Grok-2 Dec 2024 53.8%
  296. 296 GPT-4o May 2024 53.6%
  297. 297 Nemotron 3 Nano 4B 53.2%
  298. 298 Phi-4-mini-reasoning 52%
  299. 299 Qwen3.5-2B 51.6%
  300. 300 Gemini 2.0 Flash-Lite 51.5%
  301. 301 Mistral Large 2 Nov 2024 51.3%
  302. 302 Llama 3.1-405B 51.1%
  303. 303 Mercury 51%
  304. 304 Cohere Command A 50.8%
  305. 305 Llama 3.3 70B Instruct 50.5%
  306. 306 Claude 3 Opus 50.4%
  307. 307 GPT-4.1 nano 50.3%
  308. 308 Nemotron 3 Ultra 550B-A55B Base 50%
  309. 309 Falcon-H1-34B 49.7%
  310. 310 Qwen2.5-32B 49.5%
  311. 311 GPT-4 Turbo Apr 2024 49.3%
  312. 312 GPT-4o Aug 2024 49.2%
  313. 313 Qwen2.5-72B 49.1%
  314. 314 Mistral Small 3.2 49%
  315. 315 Mistral Large 2 Jul 2024 49%
  316. 316 Qwen2.5-VL-72B 49%
  317. 317 Qwen Plus Jan 2025 48.1%
  318. 318 Sarvam-M 48%
  319. 319 GPT-4o Nov 2024 47.9%
  320. 320 Gemma 3 27B 47.7%
  321. 321 Mistral Small 3.1 47.5%
  322. 322 Llama 3.3 70B 47.4%
  323. 323 Gemini 1.5 Flash Sep 2024 47.3%
  324. 324 Mistral Small 3 47.3%
  325. 325 Llama 3.1-70B 46.7%
  326. 326 Tulu 3 (Tülu 3) 70B 46.3%
  327. 327 Gemini 1.5 Pro May 2024 46.2%
  328. 328 qwen3-4b-instruct-2507 45.8%
  329. 329 Granite 4.1 30B 45.8%
  330. 330 Qwen2.5-14B 45.5%
  331. 331 glm-4.7-flash_none none 45.1%
  332. 332 Phi-4-mini-flash-reasoning 45.1%
  333. 333 Mistral Large 3 43.9%
  334. 334 WizardLM-2 8x22B 43.4%
  335. 335 Gemma 4 E2B 43.4%
  336. 336 Qwen2-72B 42.4%
  337. 337 GPT-4 Turbo Nov 2023 42.4%
  338. 338 Qwen-Turbo 42.3%
  339. 339 Kimi-VL-A3B-Thinking-2506 42.3%
  340. 340 Claude 3.5 Haiku 41.6%
  341. 341 Gemini 1.5 Pro Feb 2024 41.5%
  342. 342 Llama 3.2 90B 41%
  343. 343 Gemma 3 12B 40.9%
  344. 344 Granite 4.0 H Small 40.6%
  345. 345 Code World Model (CWM) 40.6%
  346. 346 Claude 3 Sonnet 40.6%
  347. 347 Llama 3-70B 40.6%
  348. 348 Gemini 1.5 Flash May 2024 40.4%
  349. 349 GPT-4o mini 40.2%
  350. 350 Qwen3-1.7B 40.1%
  351. 351 Qwen2.5-14B-Instruct-1M 39.9%
  352. 352 LFM2.5-1.2B-Instruct 38.9%
  353. 353 Mistral Large 38.8%
  354. 354 LFM2.5-1.2B-Thinking 37.9%
  355. 355 Hermes 2 Theta Llama-3 70B 37.5%
  356. 356 InternLM3-8B-Instruct 37.4%
  357. 357 Phi-3.5-MoE 36.8%
  358. 358 Gemma 2 27B 36.5%
  359. 359 Qwen2.5-7B 36.4%
  360. 360 Claude 3 Haiku 36.3%
  361. 361 OLMo 2 32B Instruct 35.9%
  362. 362 GPT-4 Mar 2023 35.7%
  363. 363 GLM-4 35.7%
  364. 364 Claude 2 34.7%
  365. 365 phi-3-small 7.4B 34.3%
  366. 366 Llama 3-8B 34.2%
  367. 367 Mixtral 8x22B 34.1%
  368. 368 Gemini 1.0 Pro 34%
  369. 369 Eurus-2-7B-PRIME 33.9%
  370. 370 DeepSeek-R1-Distill-Qwen-1.5B 33.8%
  371. 371 Nemotron 3.5 Lightning 30B-A3B Base 33.3%
  372. 372 Claude 2.1 33%
  373. 373 Gemini 1.5 Flash 8B 33%
  374. 374 DBRX 32.9%
  375. 375 phi-3-mini 3.8B 32.8%
  376. 376 Llama 3.1-8B 32.8%
  377. 377 Yi-1.5-34B 32%
  378. 378 LFM2-1.2B 31.5%
  379. 379 Gemma 3 4B 30.8%
  380. 380 Qwen2.5-Omni-7B 30.8%
  381. 381 Qwen1.5-32B 30.7%
  382. 382 GPT-4 Jun 2023 30.6%
  383. 383 Mixtral 8x7B 30.6%
  384. 384 Phi-4 Mini 30.4%
  385. 385 granite-4.0-1b 29.9%
  386. 386 Mistral NeMo 29.9%
  387. 387 LFM2-8B-A1B 29.3%
  388. 388 Qwen1.5-72B 28.8%
  389. 389 granite-4.0-micro 28.3%
  390. 390 GPT-3.5 Turbo Nov 2023 28%
  391. 391 AFM-4.5B 27.8%
  392. 392 phi-3-medium 14B 27.6%
  393. 393 Gemma 2 9B 27.5%
  394. 394 Phi-3.5-mini 27.2%
  395. 395 GPT-3.5 Turbo Jan 2024 27.2%
  396. 396 Ministral 8B 27.1%
  397. 397 ChatGLM3-6B 26.8%
  398. 398 Llama 2-70B 26.3%
  399. 399 Ministral 3B 25.3%
  400. 400 DeepSeek LLM 67B 24.6%
  401. 401 Llama 3.2 1B 23.9%
  402. 402 Gemma 3n E4B 23.7%
  403. 403 Gemma 3 1B 19.9%
  404. 404 Mistral 7B v0.3 15.2%
  405. 405 Yi-34B 14.7%
  406. 406 Qwen3.5-0.8B 11.9%
  407. 407 granite-4.0-350m 11.2%
  408. 408 deepseek-r1-0528-qwen3-8b 9.28%

Sources: Labs’ model cards, official GPQA Diamond leaderboard and Epoch AI runs (CC BY 4.0)

#ModelScoreSettingReleasedRun onSource
1 Gemini 4 Carbon 97% Oct 2026 Nov 2026 Official leaderboard
2 Grok 4.6 95% Aug 2026 Oct 2026 Official leaderboard
3 GPT-6 Astra 95% Sep 2026 Oct 2026 Official leaderboard
4 Gemini 4 Argon 95% Sep 2026 Oct 2026 Official leaderboard
5 Gemini 3.1 Pro 93.9% Feb 2026 Oct 2026 Official leaderboard
6 GPT-6.1 Sol 93.9% Sep 2026 Oct 2026 Official leaderboard
7 Gemini 3.8 Flash 92.9% Sep 2026 Oct 2026 Official leaderboard
8 Claude Opus 5 92.9% Jul 2026 Oct 2026 Official leaderboard
9 Grok 4.7 92.6% Sep 2026 Oct 2026 Official leaderboard
10 GPT-6 Sol 91.9% Sep 2026 Oct 2026 Official leaderboard
11 Claude Sonnet 5.5 91.9% Sep 2026 Oct 2026 Official leaderboard
12 Claude Opus 5.5 90.8% Sep 2026 Oct 2026 Official leaderboard
13 Gemini 3.6 Flash 89.9% Jul 2026 Oct 2026 Official leaderboard
14 DeepSeek V4.1 Flash 1017 89.4% Oct 2026 Nov 2026 Official leaderboard
15 Claude Haiku 5.5 84.8% Oct 2026 Oct 2026 Official leaderboard
16 Gemma 4 26B A4B 83.2% Apr 2026 Oct 2026 Official leaderboard
17 Gemma 4 31B IT 82.8% Apr 2026 Oct 2026 Official leaderboard
18 GPT-6 Luna 81.8% Sep 2026 Oct 2026 Official leaderboard
19 GPT-5.6 Luna 80.8% Jul 2026 Oct 2026 Official leaderboard
20 GPT-5.6 Terra 79.3% Jul 2026 Oct 2026 Official leaderboard
#ModelScoreSettingDateSource
1 Gemini 4 Carbon 97% Oct 2026 Official leaderboard
2 GPT-6.2 Astra 96.8% max Nov 2026 Epoch AI run
3 Gemini 4 Hydrogen 96.8% xhigh Nov 2026 Epoch AI run
4 Gemini 4 Argon 96.4% high Oct 2026 Epoch AI run
5 Claude Fable 5.2 96% with fallback, max Nov 2026 Epoch AI run
6 GPT-6 Astra 95.8% max Sep 2026 Epoch AI run
7 Claude Sonnet 5.5 95.6% max Sep 2026 Epoch AI run
8 Gemini 3.8 Flash 95.4% high Sep 2026 Epoch AI run
9 GPT-6.1 Sol 95.4% max Sep 2026 Epoch AI run
10 Grok 4.6 95% Aug 2026 Official leaderboard
11 Gemini 3.7 Flash 94.8% high Aug 2026 Epoch AI run
12 GPT-5.4 Pro 94.6% xhigh Mar 2026 Epoch AI run
13 Gemini 3.1 Pro 94.4% high Feb 2026 Epoch AI run
14 GPT-6 Sol 94.3% max Sep 2026 Epoch AI run
15 GPT-6.1 Terra 94.3% max Oct 2026 Epoch AI run
16 Kimi K3.1 Pro 94.2% Together, max Oct 2026 Epoch AI run
17 Gemini 3.6 Flash 94.1% high Jul 2026 Epoch AI run
18 Claude Opus 5.5 94.1% with fallback, max Sep 2026 Epoch AI run
19 GPT-5.5 94% xhigh Apr 2026 Epoch AI run
20 GPT-5.5 Pro 93.9% xhigh Apr 2026 Epoch AI run
21 Claude Fable 5 93.9% with fallback, max Jun 2026 Epoch AI run
22 Claude Opus 5 93.9% max Jul 2026 Epoch AI run
23 GPT-5.6 Sol 93.5% max Jul 2026 Epoch AI run
24 Grok 4.5 93.4% high Jul 2026 Epoch AI run
25 GPT-5.6 Terra 93.3% max Jul 2026 Epoch AI run
26 GPT-5.4 93.3% xhigh Mar 2026 Epoch AI run
27 DeepSeek V4.1 Flash 1017 93.2% max Oct 2026 Epoch AI run
28 Kimi K3 93.1% max Jul 2026 Epoch AI run
29 Doubao Seed Evolving Nov 2026 93.1% high Nov 2026 Epoch AI run
30 Gemini 3.5 Flash 92.8% high May 2026 Epoch AI run
31 Grok 4.7 92.7% xhigh Sep 2026 Epoch AI run
32 Qwen 3.8 Max 92.7% xhigh Aug 2026 Epoch AI run
33 Gemini 3 Pro 92.6% Nov 2025 Epoch AI run
34 Qwen3.8 Max (0902) 92.3% xhigh Sep 2026 Epoch AI run
35 GLM-5.2 91.9% max Jun 2026 Epoch AI run
36 DeepSeek V4 Pro 0813 91.7% max Aug 2026 Epoch AI run
37 GPT-5.6 Luna 91.6% max Jul 2026 Epoch AI run
38 GPT-5.2 91.4% xhigh Dec 2025 Epoch AI run
39 Claude Opus 4.8 91% max May 2026 Epoch AI run
40 DeepSeek V4 Flash 0731 91% max Jul 2026 Epoch AI run
41 DeepSeek-V4-Pro 90.9% high Apr 2026 Epoch AI run
42 Qwen3.7-Max 90.9% May 2026 Epoch AI run
43 MiniMax-M3 90.9% Jun 2026 Epoch AI run
44 GLM-5.3 90.9% max Aug 2026 Epoch AI run
45 Kimi K2.6 90.8% Apr 2026 Epoch AI run
46 Claude Opus 4.6 90.5% 32k thinking Feb 2026 Epoch AI run
47 Claude Sonnet 5 90.5% xhigh Jun 2026 Epoch AI run
48 GPT-6 Luna 90.5% max Sep 2026 Epoch AI run
49 Claude Opus 4.7 90.2% xhigh Apr 2026 Epoch AI run
50 GLM-5.3-Flash 90.2% max Aug 2026 Epoch AI run
51 Mistral Large 4 90.2% high Oct 2026 Epoch AI run
52 GLM-5.1 89.9% Apr 2026 Epoch AI run
53 DeepSeek V4.1 Flash 89.8% max Sep 2026 Epoch AI run
54 Muse Spark 89.8% Apr 2026 Epoch AI run
55 Claude Haiku 5.5 89.7% max Oct 2026 Epoch AI run
56 Doubao Seed 2.1 Turbo 89.6% high Jun 2026 Epoch AI run
57 Gemini 3 Flash 89.4% high Dec 2025 Epoch AI run
58 Grok 4.20 89.3% Feb 2026 Epoch AI run
59 Doubao Seed 2.1 Pro 89.3% high Jun 2026 Epoch AI run
60 Grok 4.3 Beta 88.8% high Apr 2026 Epoch AI run
61 Muse Spark Open 88.6% xhigh Oct 2026 Epoch AI run
62 Inkling-Small 88.5% xhigh Jul 2026 Epoch AI run
63 Qwen 3.6 Plus 88.4% 2026-04-02 Mar 2026 Epoch AI run
64 Inkling 88.3% xhigh Jul 2026 Epoch AI run
65 Doubao-Seed-2.0 Pro 88.2% high Feb 2026 Epoch AI run
66 Doubao Seed 2.0 Lite Apr 2026 88.1% high Apr 2026 Epoch AI run
67 Mistral Large 4 Preview 88.1% high Oct 2026 Epoch AI run
68 Qwen3.7-Plus 87.9% Jun 2026 Epoch AI run
69 Kimi K2.7 Code 87.9% Jun 2026 Epoch AI run
70 GLM-5 87.8% Feb 2026 Epoch AI run
71 GPT-5.1 87.6% high Nov 2025 Epoch AI run
72 Kimi K2.5 87.6% Fireworks Jan 2026 Epoch AI run
73 Claude Sonnet 4.6 87.4% 32k thinking Feb 2026 Epoch AI run
74 Qwen 3.6 Max (Preview) 87.4% Apr 2026 Epoch AI run
75 Grok 4 87% Jul 2025 Epoch AI run
76 GPT-5.4 Mini 86.9% xhigh Mar 2026 Epoch AI run
77 Qwen3.5 397B-A17B 86.4% none Feb 2026 Epoch AI run
78 GPT-5 86.2% high Aug 2025 Epoch AI run
79 Claude Opus 4.5 86% 32k thinking Nov 2025 Epoch AI run
80 Qwen3.6 27B 85.9% Apr 2026 Epoch AI run
81 Nemotron 3 Ultra 85.3% Jun 2026 Epoch AI run
82 Gemini 2.5 Pro Jun 2025 85.3% Jun 2025 Epoch AI run
83 Qwen 3.5 Plus (hosted 397B-A17B) 84.8% Feb 2026 Epoch AI run
84 Qwen 3.6 35B-A3B 84.8% none Apr 2026 Epoch AI run
85 Kimi K2 Thinking 84.2% Nov 2025 Epoch AI run
86 Gemini 2.5 Pro Mar 2025 83.8% Mar 2025 Epoch AI run
87 Qwen3.5-35B-A3B 83.5% Feb 2026 Epoch AI run
88 DeepSeek-V3.2 83.4% Thinking Dec 2025 Epoch AI run
89 GLM-4.7 83.3% Dec 2025 Epoch AI run
90 Qwen 3.6 Flash 83.3% 2026-04-16 Apr 2026 Epoch AI run
91 Gemini 3.5 Flash-Lite 83.3% high Jul 2026 Epoch AI run
92 Gemma 4 26B A4B 83.2% Apr 2026 Official leaderboard
93 Gemma 4 31B IT 82.8% Apr 2026 Official leaderboard
94 GPT-5.5 Instant 82.5% May 2026 Epoch AI run
95 Claude Sonnet 4.5 82.3% 59k thinking Sep 2025 Epoch AI run
96 Qwen 3.5 Flash (hosted 35B-A3B) 82.3% Feb 2026 Epoch AI run
97 Qwen3.7 Flash 82.3% Jul 2026 Epoch AI run
98 o3 81.8% high Apr 2025 Epoch AI run
99 Gemini 3.1 Flash-Lite 81.8% high Mar 2026 Epoch AI run
100 Qwen3-235B-A22B-Thinking Jul 2025 80% Jul 2025 Epoch AI run
101 Claude 3.7 Sonnet 79.7% 64k thinking Feb 2025 Epoch AI run
102 o4-mini 79.6% high Apr 2025 Epoch AI run
103 Claude Sonnet 4 79.2% 59K May 2025 Epoch AI run
104 Qwen3.5-9B 79% Feb 2026 Epoch AI run
105 GPT-5.4 Nano 78.5% high Mar 2026 Epoch AI run
106 Doubao-Seed-1.6 77.6% thinking Jun 2025 Epoch AI run
107 Claude Opus 4.1 77.3% 16K Aug 2025 Epoch AI run
108 o3-mini 77% high Jan 2025 Epoch AI run
109 o1 76.8% high Dec 2024 Epoch AI run
110 DeepSeek-R1 May 2025 76.3% May 2025 Epoch AI run
111 Grok-3 mini 76.3% low Apr 2025 Epoch AI run
112 Claude Opus 4 76.3% 16K May 2025 Epoch AI run
113 Grok 3 75.8% Apr 2025 Epoch AI run
114 gpt-oss-120b 75.8% high Aug 2025 Epoch AI run
115 GPT-5 mini 75% high Aug 2025 Epoch AI run
116 Qwen3-Max 72.6% Sep 2025 Epoch AI run
117 DeepSeek-R1 71.7% Jan 2025 Epoch AI run
118 seed-oss-36b-instruct 71.5% Aug 2025 Epoch AI run
119 Claude Haiku 4.5 71.2% 32K Oct 2025 Epoch AI run
120 Qwen3-235B-A22B 70.7% Apr 2025 Epoch AI run
121 Qwen3-30B-A3B-Thinking Jul 2025 70.1% Jul 2025 Epoch AI run
122 GPT-5 nano 69.4% high Aug 2025 Epoch AI run
123 GPT-4.5 68.7% Feb 2025 Epoch AI run
124 DeepSeek-V3 Mar 2025 67.6% Mar 2025 Epoch AI run
125 Llama 4 Maverick 67% FP8 Apr 2025 Epoch AI run
126 GPT-4.1 66.9% Apr 2025 Epoch AI run
127 Gemini 2.5 Pro May 2025 66.7% May 2025 Epoch AI run
128 GPT-4.1 mini 65.8% Apr 2025 Epoch AI run
129 Qwen3-32B 65.7% Apr 2025 Epoch AI run
130 Gemini 2.0 Pro 65.7% Feb 2025 Epoch AI run
131 QWQ-Plus 65.4% Apr 2025 Epoch AI run
132 QwQ-32B 65.3% Mar 2025 Epoch AI run
133 DeepSeek-R1-Distill-Qwen-32B 64.1% Jan 2025 Epoch AI run
134 Gemini 2.0 Flash Feb 2025 64.1% Feb 2025 Epoch AI run
135 Qwen3-14B 63.8% Apr 2025 Epoch AI run
136 o1-mini 62.4% high Sep 2024 Epoch AI run
137 Qwen3-30B-A3B 61.7% Apr 2025 Epoch AI run
138 gpt-oss-20b 60.8% medium Aug 2025 Epoch AI run
139 glm-4.7-flash 60.5% Jan 2026 Epoch AI run
140 Mistral Medium 3 59.5% May 2025 Epoch AI run
141 Gemini 1.5 Pro Sep 2024 57.2% Sep 2024 Epoch AI run
142 Gemini 2.0 Flash Thinking Jan 2025 57.1% Jan 2025 Epoch AI run
143 Qwen3-8B 56.8% Apr 2025 Epoch AI run
144 DeepSeek-V3 56.5% Dec 2024 Epoch AI run
145 Qwen2.5-Max 56.1% Jan 2025 Epoch AI run
146 Phi-4 56.1% Dec 2024 Epoch AI run
147 Magistral Small 1.0 56.1% Jun 2025 Epoch AI run
148 DeepSeek-R1-Distill-Llama-70B 55.7% Jan 2025 Epoch AI run
149 Qwen3-30B-A3B-Instruct Jul 2025 55.6% Jul 2025 Epoch AI run
150 Claude 3.5 Sonnet (October 2024) 55.3% Oct 2024 Epoch AI run
151 Claude 3.5 Sonnet 54% Jun 2024 Jun 2024 Epoch AI run
152 Grok-2 Dec 2024 53.8% Dec 2024 Epoch AI run
153 Qwen3-4B 52.3% Apr 2025 Epoch AI run
154 Llama 4 Scout 51.8% Apr 2025 Epoch AI run
155 Mistral Large 2 Nov 2024 51.3% Nov 2024 Epoch AI run
156 Llama 3.1-405B 50.9% Jul 2024 Epoch AI run
157 o1-preview 50.3% Sep 2024 Epoch AI run
158 GPT-4o Aug 2024 49.2% Aug 2024 Epoch AI run
159 Qwen2.5-72B 49.1% Sep 2024 Epoch AI run
160 Mistral Small 3.2 49% Jun 2025 Epoch AI run
161 Mistral Large 2 Jul 2024 49% Jul 2024 Epoch AI run
162 GPT-4.1 nano 48.9% Apr 2025 Epoch AI run
163 GPT-4o May 2024 48.9% May 2024 Epoch AI run
164 Qwen Plus Jan 2025 48.1% Jan 2025 Epoch AI run
165 GPT-4o Nov 2024 47.9% Nov 2024 Epoch AI run
166 Gemma 3 27B 47.7% Mar 2025 Epoch AI run
167 Magistral Small 1.2 47.6% Sep 2025 Epoch AI run
168 Mistral Small 3.1 47.5% Mar 2025 Epoch AI run
169 Llama 3.3 70B 47.4% Dec 2024 Epoch AI run
170 Gemini 1.5 Flash Sep 2024 47.3% Sep 2024 Epoch AI run
171 Mistral Small 3 47.3% Jan 2025 Epoch AI run
172 Claude 3 Opus 47.2% Feb 2024 Epoch AI run
173 GPT-4 Turbo Apr 2024 46.6% Apr 2024 Epoch AI run
174 Tulu 3 (Tülu 3) 70B 46.3% Nov 2024 Epoch AI run
175 Qwen2.5-32B 46.1% Sep 2024 Epoch AI run
176 Gemini 1.5 Pro May 2024 45.9% May 2024 Epoch AI run
177 qwen3-4b-instruct-2507 45.8% Aug 2025 Epoch AI run
178 glm-4.7-flash_none 45.1% none Epoch AI run
179 DeepSeek-R1-Distill-Qwen-14B 44.7% Jan 2025 Epoch AI run
180 Llama 3.1-70B 44.2% Jul 2024 Epoch AI run
181 WizardLM-2 8x22B 43.4% Apr 2024 Epoch AI run
182 GPT-4 Turbo Nov 2023 42.4% Nov 2023 Epoch AI run
183 Qwen-Turbo 41.8% Nov 2024 Epoch AI run
184 Llama 3.2 90B 41% Sep 2024 Epoch AI run
185 Qwen2-72B 40.8% Jun 2024 Epoch AI run
186 Claude 3 Sonnet 40.6% Feb 2024 Epoch AI run
187 Llama 3-70B 40.6% Apr 2024 Epoch AI run
188 Gemini 1.5 Flash May 2024 40.4% May 2024 Epoch AI run
189 Gemma 3 12B 39.5% Mar 2025 Epoch AI run
190 Mistral Large 38.8% Feb 2024 Epoch AI run
191 Claude 3.5 Haiku 38.1% Oct 2024 Oct 2024 Epoch AI run
192 Qwen3-1.7B 38% Apr 2025 Epoch AI run
193 GPT-4o mini 37.7% Jul 2024 Epoch AI run
194 Hermes 2 Theta Llama-3 70B 37.5% Jun 2024 Epoch AI run
195 Gemma 2 27B 36.5% Jun 2024 Epoch AI run
196 Claude 3 Haiku 36.3% Mar 2024 Epoch AI run
197 GPT-4 Mar 2023 35.7% Mar 2023 Epoch AI run
198 Qwen2.5-7B 35.5% Sep 2024 Epoch AI run
199 Claude 2 34.7% Jul 2023 Epoch AI run
200 Mixtral 8x22B 34.1% Apr 2024 Epoch AI run
201 Gemini 1.0 Pro 34% Dec 2023 Epoch AI run
202 Eurus-2-7B-PRIME 33.9% Dec 2024 Epoch AI run
203 DeepSeek-R1-Distill-Qwen-1.5B 33.6% Jan 2025 Epoch AI run
204 Claude 2.1 33% Nov 2023 Epoch AI run
205 Gemini 1.5 Flash 8B 33% Oct 2024 Epoch AI run
206 DBRX 32.9% Mar 2024 Epoch AI run
207 Yi-1.5-34B 32% May 2024 Epoch AI run
208 Qwen1.5-32B 30.7% Apr 2024 Epoch AI run
209 GPT-4 Jun 2023 30.6% Jun 2023 Epoch AI run
210 Mixtral 8x7B 30.6% Dec 2023 Epoch AI run
211 Mistral NeMo 29.9% Jul 2024 Epoch AI run
212 Qwen1.5-72B 28.8% Feb 2024 Epoch AI run
213 granite-4.0-micro 28.3% Oct 2025 Epoch AI run
214 GPT-3.5 Turbo Nov 2023 28% Nov 2023 Epoch AI run
215 phi-3-medium 14B 27.6% Apr 2024 Epoch AI run
216 Gemma 2 9B 27.5% Jun 2024 Epoch AI run
217 GPT-3.5 Turbo Jan 2024 27.2% Jan 2024 Epoch AI run
218 Ministral 8B 27.1% Oct 2024 Epoch AI run
219 Llama 3.1-8B 27% Jul 2024 Epoch AI run
220 Llama 2-70B 26.3% Jul 2023 Epoch AI run
221 Llama 3-8B 26.1% Apr 2024 Epoch AI run
222 Ministral 3B 25.3% Oct 2024 Epoch AI run
223 DeepSeek LLM 67B 24.6% Nov 2023 Epoch AI run
224 granite-4.0-1b 24% Oct 2025 Epoch AI run
225 Llama 3.2 1B 23.9% Sep 2024 Epoch AI run
226 Gemma 3 4B 23.2% Mar 2025 Epoch AI run
227 Gemma 3 1B 19.9% Mar 2025 Epoch AI run
228 Mistral 7B v0.3 15.2% May 2024 Epoch AI run
229 Yi-34B 14.7% Nov 2023 Epoch AI run
230 granite-4.0-350m 11.2% Oct 2025 Epoch AI run
231 deepseek-r1-0528-qwen3-8b 9.28% May 2025 Epoch AI run
#ModelScoreSettingDateSource
1 GPT-6.2 Astra 97% Nov 2026 Lab model card
2 Gemini 4 Carbon 97% Oct 2026 Official leaderboard
3 Gemini 4 Hydrogen 96.8% xhigh Nov 2026 Epoch AI run
4 Gemini 4 Argon 96.4% high Oct 2026 Epoch AI run
5 Claude Fable 5.2 96% with fallback, max Nov 2026 Epoch AI run
6 GPT-6 Astra 96% Sep 2026 Lab model card
7 GPT-6.2 Sol 96% Nov 2026 Lab model card
8 Claude Sonnet 5.5 95.6% max Sep 2026 Epoch AI run
9 Gemini 3.8 Flash 95.4% high Sep 2026 Epoch AI run
10 GPT-6.1 Sol 95.4% max Sep 2026 Epoch AI run
11 Grok 4.6 95% Aug 2026 Official leaderboard
12 Gemini 3.7 Flash 94.8% high Aug 2026 Epoch AI run
13 GPT-5.4 Pro 94.6% xhigh Mar 2026 Epoch AI run
14 GPT-5.6 Sol 94.6% Jul 2026 Lab model card
15 Claude Mythos Preview 94.5% Apr 2026 Lab model card
16 Gemini 3.1 Pro 94.4% high Feb 2026 Epoch AI run
17 GPT-6 Sol 94.3% max Sep 2026 Epoch AI run
18 GPT-6.1 Terra 94.3% max Oct 2026 Epoch AI run
19 Claude Opus 4.7 94.2% Apr 2026 Lab model card
20 Kimi K3.1 Pro 94.2% Oct 2026 Lab model card
21 Gemini 3.6 Flash 94.1% high Jul 2026 Epoch AI run
22 Claude Opus 5.5 94.1% with fallback, max Sep 2026 Epoch AI run
23 GPT-5.5 94% xhigh Apr 2026 Epoch AI run
24 GPT-5.5 Pro 93.9% xhigh Apr 2026 Epoch AI run
25 Claude Fable 5 93.9% with fallback, max Jun 2026 Epoch AI run
26 Claude Opus 5 93.9% max Jul 2026 Epoch AI run
27 Claude Opus 4.8 93.6% May 2026 Lab model card
28 Kimi K3 93.5% Jul 2026 Lab model card
29 Step 5 Preview 93.5% Sep 2026 Lab model card
30 Grok 4.5 93.4% high Jul 2026 Epoch AI run
31 GPT-5.6 Terra 93.3% max Jul 2026 Epoch AI run
32 GPT-5.4 93.3% xhigh Mar 2026 Epoch AI run
33 GPT-5.2 Pro 93.2% Dec 2025 Lab model card
34 DeepSeek V4.1 Flash 1017 93.2% max Oct 2026 Epoch AI run
35 Doubao Seed Evolving Nov 2026 93.1% high Nov 2026 Epoch AI run
36 Inkling 2 Small 93% Nov 2026 Lab model card
37 Gemini 3.5 Flash 92.8% high May 2026 Epoch AI run
38 Grok 4.7 92.7% xhigh Sep 2026 Epoch AI run
39 Qwen 3.8 Max 92.7% xhigh Aug 2026 Epoch AI run
40 Gemini 3 Pro 92.6% Nov 2025 Epoch AI run
41 GPT-5.2 92.4% Dec 2025 Lab model card
42 Qwen3.7-Max 92.4% May 2026 Lab model card
43 GPT-5.6 Luna 92.3% Jul 2026 Lab model card
44 Tencent Hy4 preview 92.3% Aug 2026 Lab model card
45 Qwen3.8 Max (0902) 92.3% xhigh Sep 2026 Epoch AI run
46 GLM-5.2 91.9% max Jun 2026 Epoch AI run
47 Qwen3.8 Flash 91.7% Aug 2026 Lab model card
48 DeepSeek V4 Pro 0813 91.7% max Aug 2026 Epoch AI run
49 Claude Opus 4.6 91.3% Feb 2026 Lab model card
50 DeepSeek V4 Flash 0731 91% max Jul 2026 Epoch AI run
51 ERNIE 5.1 91% May 2026 Lab model card
52 Qwen3.8-Omni-Flash 91% Sep 2026 Lab model card
53 DeepSeek-V4-Pro 90.9% high Apr 2026 Epoch AI run
54 MiniMax-M3 90.9% Jun 2026 Epoch AI run
55 GLM-5.3 90.9% max Aug 2026 Epoch AI run
56 DeepSeek V4.1 Flash 90.9% Sep 2026 Lab model card
57 Kimi K2.6 90.8% Apr 2026 Epoch AI run
58 Claude Sonnet 5 90.5% xhigh Jun 2026 Epoch AI run
59 Beam 1.0 90.5% Oct 2026 Lab model card
60 GPT-6 Luna 90.5% max Sep 2026 Epoch AI run
61 Gemini 3 Flash 90.4% Dec 2025 Lab model card
62 Qwen 3.6 Plus 90.4% Apr 2026 Lab model card
63 Tencent Hy3 90.4% Jul 2026 Lab model card
64 Qwen3.7-Plus 90.3% Jun 2026 Lab model card
65 GLM-5.3-Flash 90.2% max Aug 2026 Epoch AI run
66 Mistral Large 4 90.2% high Oct 2026 Epoch AI run
67 Claude Sonnet 4.6 89.9% Feb 2026 Lab model card
68 GLM-5.1 89.9% Apr 2026 Epoch AI run
69 Muse Spark 89.8% Apr 2026 Epoch AI run
70 MiniMax-M2.7 89.8% May 2026 Lab model card
71 Claude Haiku 5.5 89.7% max Oct 2026 Epoch AI run
72 Doubao Seed 2.1 Turbo 89.6% high Jun 2026 Epoch AI run
73 Nemotron 3.5 Super VL 89.5% Oct 2026 Lab model card
74 Inkling-Small 89.5% Jul 2026 Lab model card
75 GPT-5 89.4% Aug 2025 Lab model card
76 Grok 4.20 89.3% Feb 2026 Epoch AI run
77 Doubao Seed 2.1 Pro 89.3% high Jun 2026 Epoch AI run
78 Mercury 3 89.2% Oct 2026 Lab model card
79 Qwen 3.8 27B 89.2% Aug 2026 Lab model card
80 Solar Pro 4 89% Aug 2026 Lab model card
81 Muse Spark Open 89% Oct 2026 Lab model card
82 Seed2.0 Pro 88.9% Feb 2026 Lab model card
83 LongCat-2.0 88.9% Jul 2026 Lab model card
84 Grok 4.3 Beta 88.8% high Apr 2026 Epoch AI run
85 Grok 4 Heavy 88.4% Jul 2025 Lab model card
86 Qwen3.5 397B-A17B 88.4% Feb 2026 Lab model card
87 Seed2.0 Lite (0428) 88.4% Apr 2026 Lab model card
88 Ring-2.6-1T 88.3% May 2026 Lab model card
89 Inkling 88.3% xhigh Jul 2026 Epoch AI run
90 Doubao-Seed-2.0 Pro 88.2% high Feb 2026 Epoch AI run
91 Doubao Seed 2.0 Lite Apr 2026 88.1% high Apr 2026 Epoch AI run
92 GPT-5.1 88.1% Nov 2025 Lab model card
93 DeepSeek-V4-Flash 88.1% Apr 2026 Lab model card
94 Mistral Large 4 Preview 88.1% high Oct 2026 Epoch AI run
95 GPT-5.4 Mini 88% Mar 2026 Lab model card
96 Kimi K2.7 Code 87.9% Jun 2026 Epoch AI run
97 GLM-5 87.8% Feb 2026 Epoch AI run
98 Qwen3.6 27B 87.8% Apr 2026 Lab model card
99 Kimi K2.5 87.6% Fireworks Jan 2026 Epoch AI run
100 Grok 4 87.5% Jul 2025 Lab model card
101 Qwen3-Max-2026-01-23 87.4% Jan 2026 Lab model card
102 Qwen 3.6 Max (Preview) 87.4% Apr 2026 Epoch AI run
103 Tencent Hy3 preview 87.2% Apr 2026 Lab model card
104 Claude Opus 4.5 87% Nov 2025 Lab model card
105 Nemotron 3 Ultra 87% Jun 2026 Lab model card
106 Gemini 3.1 Flash-Lite 86.9% Mar 2026 Lab model card
107 Qwen3.5-122B-A10B 86.6% Feb 2026 Lab model card
108 Inkling 2 Mini 86.6% Nov 2026 Lab model card
109 Nemotron 3.5 Bolt 74B-A9B 86.4% Oct 2026 Lab model card
110 Gemini 2.5 Pro Jun 2025 86.4% Jun 2025 Lab model card
111 ERNIE 5.0 86.4% Feb 2026 Lab model card
112 Solar Open 2 86.3% Jul 2026 Lab model card
113 Qwen 3.6 35B-A3B 86% Apr 2026 Lab model card
114 Grok 4 Fast 85.7% Sep 2025 Lab model card
115 DeepSeek-V3.2-Speciale 85.7% Dec 2025 Lab model card
116 GLM-4.7 85.7% Dec 2025 Lab model card
117 GPT-5.5 Instant 85.6% May 2026 Lab model card
118 Qwen3.5-27B 85.5% Feb 2026 Lab model card
119 LongCat-Flash-Thinking-2601 85.2% Jan 2026 Lab model card
120 MiniMax-M2.5 85.2% Feb 2026 Lab model card
121 Qwen 3.5 Plus (hosted 397B-A17B) 84.8% Feb 2026 Epoch AI run
122 Claude 3.7 Sonnet 84.8% Feb 2025 Lab model card
123 Grok 3 84.6% Feb 2025 Lab model card
124 MAI-Code-1-Flash 84.6% Jun 2026 Lab model card
125 Kimi K2 Thinking 84.5% Nov 2025 Lab model card
126 MiMo-V2-Flash 84.3% Jan 2026 Lab model card
127 Gemma 4 31B IT 84.3% Apr 2026 Lab model card
128 Qwen3.5-35B-A3B 84.2% Feb 2026 Lab model card
129 MAI-Thinking-1 84.2% Jun 2026 Lab model card
130 Grok-3 mini 84% Feb 2025 Lab model card
131 Gemini 2.5 Pro Mar 2025 84% Mar 2025 Lab model card
132 o3-pro 84% Jun 2025 Lab model card
133 Qwen3.5-Omni-Plus 83.9% Mar 2026 Lab model card
134 Claude Sonnet 4 83.8% May 2025 Lab model card
135 Seed1.8 83.8% Dec 2025 Lab model card
136 Step 3.5 Flash 83.5% Feb 2026 Lab model card
137 Muse Glimmer 83.5% Aug 2026 Lab model card
138 DeepSeek-V3.2 83.4% Thinking Dec 2025 Epoch AI run
139 Claude Sonnet 4.5 83.4% Sep 2025 Lab model card
140 Qwen 3.6 Flash 83.3% 2026-04-16 Apr 2026 Epoch AI run
141 Gemini 3.5 Flash-Lite 83.3% high Jul 2026 Epoch AI run
142 o3 83.3% Apr 2025 Lab model card
143 Claude Opus 4 83.3% May 2025 Lab model card
144 gemini-robotics-er-1.5-preview 83.3% Sep 2025 Lab model card
145 Gemma 4 26B A4B 83.2% Apr 2026 Official leaderboard
146 MiniMax-M2.1 83% Dec 2025 Lab model card
147 Gemini 2.5 Flash Jun 2025 82.8% Jun 2025 Lab model card
148 GPT-5.4 Nano 82.8% Mar 2026 Lab model card
149 Qwen 3.5 Flash (hosted 35B-A3B) 82.3% Feb 2026 Epoch AI run
150 Qwen3.7 Flash 82.3% Jul 2026 Epoch AI run
151 GPT-5 mini 82.3% Aug 2025 Lab model card
152 K-EXAONE 2.0 82.2% Jul 2026 Lab model card
153 Qwen3.5-9B 81.7% Mar 2026 Lab model card
154 Seed1.6-Thinking 81.5% Jun 2025 Lab model card
155 LongCat-Flash-Thinking 81.5% Sep 2025 Lab model card
156 o4-mini 81.4% Apr 2025 Lab model card
157 Nova 2.0 Pro Preview 81.4% Dec 2025 Lab model card
158 Qwen3-235B-A22B-Thinking Jul 2025 81.1% Jul 2025 Lab model card
159 DeepSeek-R1 May 2025 81% May 2025 Lab model card
160 GLM-4.6 81% Sep 2025 Lab model card
161 Claude Opus 4.1 80.9% Aug 2025 Lab model card
162 Gemini 2.5 Flash Sep 2025 80.8% Sep 2025 Lab model card
163 DeepSeek-V3.1-Terminus 80.7% Sep 2025 Lab model card
164 EXAONE 4.5 33B 80.5% Apr 2026 Lab model card
165 gpt-oss-120b 80.1% Aug 2025 Lab model card
166 DeepSeek-V3.1 80.1% Aug 2025 Lab model card
167 DeepSeek-V3.2-Exp 79.9% Sep 2025 Lab model card
168 o3-mini 79.7% Jan 2025 Lab model card
169 Nova 2 Lite 79.6% Dec 2025 Lab model card
170 Nemotron 3 Super 79.2% Mar 2026 Lab model card
171 GLM-4.5 79.1% Jul 2025 Lab model card
172 K-EXAONE 79.1% Dec 2025 Lab model card
173 Mercury 2.5 79% Sep 2026 Lab model card
174 Gemma 4 12B 78.8% Jun 2026 Lab model card
175 Sarvam 105B 78.7% Mar 2026 Lab model card
176 Ring-1T 78.6% Oct 2025 Lab model card
177 o1-preview 78.3% Sep 2024 Lab model card
178 Gemini 2.5 Flash Apr 2025 78.3% Apr 2025 Lab model card
179 MiniMax-M2 78% Oct 2025 Lab model card
180 Cogito v2.1 77.7% Nov 2025 Lab model card
181 Doubao-Seed-1.6 77.6% thinking Jun 2025 Epoch AI run
182 Seed-Thinking-v1.5 77.3% Apr 2025 Lab model card
183 Intern-S1 77.3% Jul 2025 Lab model card
184 Qwen3-Next-80B-A3B 77.2% Sep 2025 Lab model card
185 Qwen3-VL-235B-A22B 77.1% Nov 2025 Lab model card
186 Spark-X2.6-4B 77.1% Oct 2026 Lab model card
187 o1 76.8% high Dec 2024 Epoch AI run
188 Nemotron 3.5 Lightning 30B-A3B 76.5% Oct 2026 Lab model card
189 Trinity Large Thinking 76.3% Apr 2026 Lab model card
190 Magistral Medium 1.2 76.3% Sep 2025 Lab model card
191 Qwen3.5-4B 76.2% Mar 2026 Lab model card
192 Ling-2.6-1T 76.2% Jun 2026 Lab model card
193 Nemotron-Cascade 2 30B-A3B 76.1% Mar 2026 Lab model card
194 Cogito v2 Preview 671B MoE 76% Jul 2025 Lab model card
195 Llama-3.1-Nemotron-Ultra-253B-v1 76% Apr 2025 Lab model card
196 EXAONE 4.0 32B 75.4% Jul 2025 Lab model card
197 glm-4.7-flash 75.2% Jan 2026 Lab model card
198 Kimi K2 Jul 2025 75.1% Jul 2025 Lab model card
199 GLM-4.5-Air 75% Aug 2025 Lab model card
200 Qwen3-Coder-Next 74.5% Feb 2026 Lab model card
201 LFM2.5-24B-A2B 74.4% Oct 2026 Lab model card
202 LongCat-Flash-Omni 74.4% Oct 2025 Lab model card
203 INTELLECT-3 74.4% Nov 2025 Lab model card
204 Gemini 2.0 Flash Thinking Jan 2025 74.2% Jan 2025 Lab model card
205 Mercury 2 74% Feb 2026 Lab model card
206 Llama 4 Behemoth 73.7% Apr 2025 Lab model card
207 LongCat-Flash-Chat 73.2% Aug 2025 Lab model card
208 InternVL3.5-241B-A28B 73.2% Aug 2025 Lab model card
209 DiffusionGemma 26B A4B 73.2% Jun 2026 Lab model card
210 Nemotron 3 Nano 30B-A3B 73% Dec 2025 Lab model card
211 Step 3 73% Jul 2025 Lab model card
212 Claude Haiku 4.5 73% Oct 2025 Lab model card
213 Qwen3-Max 72.6% Sep 2025 Epoch AI run
214 Beam 1.0 Base 72.4% Oct 2026 Lab model card
215 Nemotron 3 Nano Omni 30B-A3B 72.2% Apr 2026 Lab model card
216 Llama-3.3-Nemotron-Super-49B-v1.5 72% Jul 2025 Lab model card
217 Solar Pro 3 (March 2026 update) 71.9% Mar 2026 Lab model card
218 DeepSeek-R1 71.7% Jan 2025 Epoch AI run
219 Gemini 2.5 Flash-Lite Sep 2025 71.7% Sep 2025 Lab model card
220 seed-oss-36b-instruct 71.5% Aug 2025 Epoch AI run
221 gpt-oss-20b 71.5% Aug 2025 Lab model card
222 Magistral Medium 1.1 71.5% Jul 2025 Lab model card
223 GPT-4.5 71.4% Feb 2025 Lab model card
224 Hunyuan-A13B-Instruct 71.2% Jun 2025 Lab model card
225 GPT-5 nano 71.2% Aug 2025 Lab model card
226 Ministral 3 14B 71.2% Dec 2025 Lab model card
227 Mistral Small 4 71.2% Mar 2026 Lab model card
228 Qwen3-235B-A22B 71.1% Apr 2025 Lab model card
229 STEP3-VL-10B 70.8% Jan 2026 Lab model card
230 Magistral Medium 1.0 70.8% Jun 2025 Lab model card
231 Hermes 4 405B 70.6% Aug 2025 Lab model card
232 Qwen3-30B-A3B-Thinking Jul 2025 70.1% Jul 2025 Epoch AI run
233 Magistral Small 1.2 70.1% Sep 2025 Lab model card
234 MiniMax-M1-80k 70% Jun 2025 Lab model card
235 Llama 4 Maverick 69.8% Apr 2025 Lab model card
236 Qwen3-Omni-30B-A3B 69.6% Sep 2025 Lab model card
237 Hunyuan-T1 69.3% Mar 2025 Lab model card
238 Phi-4-Reasoning-plus 69.3% Apr 2025 Lab model card
239 Qwen3-32B 68.4% May 2025 Lab model card
240 Magistral Small 1.0 68.2% Jun 2025 Lab model card
241 Solar Open 100B 68.1% Jan 2026 Lab model card
242 DeepSeek-V3 Mar 2025 67.6% Mar 2025 Epoch AI run
243 Phi-4-reasoning 67.1% Apr 2025 Lab model card
244 GPT-4.1 66.9% Apr 2025 Epoch AI run
245 INTELLECT-2 66.8% May 2025 Lab model card
246 Llama-3.3-Nemotron-Super-49B-v1 66.7% May 2025 Lab model card
247 Gemini 2.5 Flash-Lite Jun 2025 66.7% Jun 2025 Lab model card
248 Gemini 2.5 Pro May 2025 66.7% May 2025 Epoch AI run
249 Sarvam 30B 66.5% Mar 2026 Lab model card
250 Granite 4.2 30B 66.4% Aug 2026 Lab model card
251 Nemotron 3.5 Super 120B-A12B Base 66.2% Oct 2026 Lab model card
252 EXAONE Deep 32B 66.1% Mar 2025 Lab model card
253 GLM-Z1-32B-0414 66.1% Apr 2025 Lab model card
254 GPT-4.1 mini 65.8% Apr 2025 Epoch AI run
255 Qwen3-30B-A3B 65.8% May 2025 Lab model card
256 Magistral Small 1.1 65.8% Jul 2025 Lab model card
257 Gemini 2.0 Pro 65.7% Feb 2025 Epoch AI run
258 Hermes 4.3 36B 65.5% Dec 2025 Lab model card
259 QWQ-Plus 65.4% Apr 2025 Epoch AI run
260 QwQ-32B 65.3% Mar 2025 Epoch AI run
261 DeepSeek-R1-Distill-Llama-70B 65.2% Jan 2025 Lab model card
262 Claude 3.5 Sonnet (October 2024) 65% Oct 2024 Lab model card
263 DeepSeek-R1-Distill-Qwen-32B 64.1% Jan 2025 Epoch AI run
264 Gemini 2.0 Flash Feb 2025 64.1% Feb 2025 Epoch AI run
265 Nemotron Nano 12B v2 VL 64.1% Nov 2025 Lab model card
266 Qwen3-14B 64% May 2025 Lab model card
267 nvidia-nemotron-nano-9b-v2 64% Aug 2025 Lab model card
268 LFM3-1.7B 63.4% Oct 2026 Lab model card
269 Trinity Large Preview 63.3% Feb 2026 Lab model card
270 o1-mini 62.4% high Sep 2024 Epoch AI run
271 Gemini 2.0 Flash Dec 2024 62.1% Dec 2024 Lab model card
272 Qwen3-8B 62% May 2025 Lab model card
273 Falcon H1R 7B 61.3% Jan 2026 Lab model card
274 Reka Flash 3 61.1% Mar 2025 Lab model card
275 Cogito v1 Preview 70B 60.6% Apr 2025 Lab model card
276 Mistral Medium 3 59.5% May 2025 Epoch AI run
277 Claude 3.5 Sonnet 59.4% Jun 2024 Lab model card
278 DeepSeek-V3 59.1% Dec 2024 Lab model card
279 DeepSeek-R1-Distill-Qwen-14B 59.1% Jan 2025 Lab model card
280 Gemma 4 E4B 58.6% Apr 2026 Lab model card
281 Trinity Mini 58.5% Dec 2025 Lab model card
282 Olmo 3 32B Think 58.1% Nov 2025 Lab model card
283 Hunyuan-TurboS 57.5% Feb 2025 Lab model card
284 Olmo 3.1 32B Think 57.5% Dec 2025 Lab model card
285 Gemini 1.5 Pro Sep 2024 57.2% Sep 2024 Epoch AI run
286 Llama 4 Scout 57.2% Apr 2025 Lab model card
287 Amazon Nova Premier 57.1% Apr 2025 Lab model card
288 Qwen2.5-Max 56.1% Jan 2025 Epoch AI run
289 Phi-4 56.1% Dec 2024 Lab model card
290 Grok-2 Aug 2024 56% Aug 2024 Lab model card
291 Qwen3-4B 55.9% May 2025 Lab model card
292 Qwen3-30B-A3B-Instruct Jul 2025 55.6% Jul 2025 Epoch AI run
293 MiniMax-Text-01 54.4% Jan 2025 Lab model card
294 MiMo-7B-RL 54.4% Apr 2025 Lab model card
295 Grok-2 Dec 2024 53.8% Dec 2024 Epoch AI run
296 GPT-4o May 2024 53.6% May 2024 Lab model card
297 Nemotron 3 Nano 4B 53.2% Mar 2026 Lab model card
298 Phi-4-mini-reasoning 52% Apr 2025 Lab model card
299 Qwen3.5-2B 51.6% Mar 2026 Lab model card
300 Gemini 2.0 Flash-Lite 51.5% Feb 2025 Lab model card
301 Mistral Large 2 Nov 2024 51.3% Nov 2024 Epoch AI run
302 Llama 3.1-405B 51.1% Jul 2024 Lab model card
303 Mercury 51% Jun 2025 Lab model card
304 Cohere Command A 50.8% Apr 2025 Lab model card
305 Llama 3.3 70B Instruct 50.5% Dec 2024 Lab model card
306 Claude 3 Opus 50.4% Mar 2024 Lab model card
307 GPT-4.1 nano 50.3% Apr 2025 Lab model card
308 Nemotron 3 Ultra 550B-A55B Base 50% Jun 2026 Lab model card
309 Falcon-H1-34B 49.7% May 2025 Lab model card
310 Qwen2.5-32B 49.5% Dec 2024 Lab model card
311 GPT-4 Turbo Apr 2024 49.3% Apr 2024 Lab model card
312 GPT-4o Aug 2024 49.2% Aug 2024 Epoch AI run
313 Qwen2.5-72B 49.1% Sep 2024 Epoch AI run
314 Mistral Small 3.2 49% Jun 2025 Epoch AI run
315 Mistral Large 2 Jul 2024 49% Jul 2024 Epoch AI run
316 Qwen2.5-VL-72B 49% Feb 2025 Lab model card
317 Qwen Plus Jan 2025 48.1% Jan 2025 Epoch AI run
318 Sarvam-M 48% May 2025 Lab model card
319 GPT-4o Nov 2024 47.9% Nov 2024 Epoch AI run
320 Gemma 3 27B 47.7% Mar 2025 Epoch AI run
321 Mistral Small 3.1 47.5% Mar 2025 Epoch AI run
322 Llama 3.3 70B 47.4% Dec 2024 Epoch AI run
323 Gemini 1.5 Flash Sep 2024 47.3% Sep 2024 Epoch AI run
324 Mistral Small 3 47.3% Jan 2025 Epoch AI run
325 Llama 3.1-70B 46.7% Jul 2024 Lab model card
326 Tulu 3 (Tülu 3) 70B 46.3% Nov 2024 Epoch AI run
327 Gemini 1.5 Pro May 2024 46.2% May 2024 Lab model card
328 qwen3-4b-instruct-2507 45.8% Aug 2025 Epoch AI run
329 Granite 4.1 30B 45.8% Apr 2026 Lab model card
330 Qwen2.5-14B 45.5% Dec 2024 Lab model card
331 glm-4.7-flash_none 45.1% none Epoch AI run
332 Phi-4-mini-flash-reasoning 45.1% Jul 2025 Lab model card
333 Mistral Large 3 43.9% Dec 2025 Lab model card
334 WizardLM-2 8x22B 43.4% Apr 2024 Epoch AI run
335 Gemma 4 E2B 43.4% Apr 2026 Lab model card
336 Qwen2-72B 42.4% Jun 2024 Lab model card
337 GPT-4 Turbo Nov 2023 42.4% Nov 2023 Epoch AI run
338 Qwen-Turbo 42.3% Dec 2024 Lab model card
339 Kimi-VL-A3B-Thinking-2506 42.3% Jun 2025 Lab model card
340 Claude 3.5 Haiku 41.6% Oct 2024 Lab model card
341 Gemini 1.5 Pro Feb 2024 41.5% Feb 2024 Lab model card
342 Llama 3.2 90B 41% Sep 2024 Epoch AI run
343 Gemma 3 12B 40.9% Mar 2025 Lab model card
344 Granite 4.0 H Small 40.6% Oct 2025 Lab model card
345 Code World Model (CWM) 40.6% Sep 2025 Lab model card
346 Claude 3 Sonnet 40.6% Feb 2024 Epoch AI run
347 Llama 3-70B 40.6% Apr 2024 Epoch AI run
348 Gemini 1.5 Flash May 2024 40.4% May 2024 Epoch AI run
349 GPT-4o mini 40.2% Jul 2024 Lab model card
350 Qwen3-1.7B 40.1% May 2025 Lab model card
351 Qwen2.5-14B-Instruct-1M 39.9% Jan 2025 Lab model card
352 LFM2.5-1.2B-Instruct 38.9% Jan 2026 Lab model card
353 Mistral Large 38.8% Feb 2024 Epoch AI run
354 LFM2.5-1.2B-Thinking 37.9% Jan 2026 Lab model card
355 Hermes 2 Theta Llama-3 70B 37.5% Jun 2024 Epoch AI run
356 InternLM3-8B-Instruct 37.4% Jan 2025 Lab model card
357 Phi-3.5-MoE 36.8% Aug 2024 Lab model card
358 Gemma 2 27B 36.5% Jun 2024 Epoch AI run
359 Qwen2.5-7B 36.4% Dec 2024 Lab model card
360 Claude 3 Haiku 36.3% Mar 2024 Epoch AI run
361 OLMo 2 32B Instruct 35.9% Dec 2024 Lab model card
362 GPT-4 Mar 2023 35.7% Mar 2023 Epoch AI run
363 GLM-4 35.7% Jun 2024 Lab model card
364 Claude 2 34.7% Jul 2023 Epoch AI run
365 phi-3-small 7.4B 34.3% Aug 2024 Lab model card
366 Llama 3-8B 34.2% Apr 2024 Lab model card
367 Mixtral 8x22B 34.1% Apr 2024 Epoch AI run
368 Gemini 1.0 Pro 34% Dec 2023 Epoch AI run
369 Eurus-2-7B-PRIME 33.9% Dec 2024 Epoch AI run
370 DeepSeek-R1-Distill-Qwen-1.5B 33.8% Jan 2025 Lab model card
371 Nemotron 3.5 Lightning 30B-A3B Base 33.3% Oct 2026 Lab model card
372 Claude 2.1 33% Nov 2023 Epoch AI run
373 Gemini 1.5 Flash 8B 33% Oct 2024 Epoch AI run
374 DBRX 32.9% Mar 2024 Epoch AI run
375 phi-3-mini 3.8B 32.8% Aug 2024 Lab model card
376 Llama 3.1-8B 32.8% Nov 2024 Lab model card
377 Yi-1.5-34B 32% May 2024 Epoch AI run
378 LFM2-1.2B 31.5% Jul 2025 Lab model card
379 Gemma 3 4B 30.8% Mar 2025 Lab model card
380 Qwen2.5-Omni-7B 30.8% Mar 2025 Lab model card
381 Qwen1.5-32B 30.7% Apr 2024 Epoch AI run
382 GPT-4 Jun 2023 30.6% Jun 2023 Epoch AI run
383 Mixtral 8x7B 30.6% Dec 2023 Epoch AI run
384 Phi-4 Mini 30.4% Feb 2025 Lab model card
385 granite-4.0-1b 29.9% Oct 2025 Lab model card
386 Mistral NeMo 29.9% Jul 2024 Epoch AI run
387 LFM2-8B-A1B 29.3% Oct 2025 Lab model card
388 Qwen1.5-72B 28.8% Feb 2024 Epoch AI run
389 granite-4.0-micro 28.3% Oct 2025 Epoch AI run
390 GPT-3.5 Turbo Nov 2023 28% Nov 2023 Epoch AI run
391 AFM-4.5B 27.8% Jul 2025 Lab model card
392 phi-3-medium 14B 27.6% Apr 2024 Epoch AI run
393 Gemma 2 9B 27.5% Jun 2024 Epoch AI run
394 Phi-3.5-mini 27.2% Aug 2024 Lab model card
395 GPT-3.5 Turbo Jan 2024 27.2% Jan 2024 Epoch AI run
396 Ministral 8B 27.1% Oct 2024 Epoch AI run
397 ChatGLM3-6B 26.8% Jun 2024 Lab model card
398 Llama 2-70B 26.3% Jul 2023 Epoch AI run
399 Ministral 3B 25.3% Oct 2024 Epoch AI run
400 DeepSeek LLM 67B 24.6% Nov 2023 Epoch AI run
401 Llama 3.2 1B 23.9% Sep 2024 Epoch AI run
402 Gemma 3n E4B 23.7% Jun 2025 Lab model card
403 Gemma 3 1B 19.9% Mar 2025 Epoch AI run
404 Mistral 7B v0.3 15.2% May 2024 Epoch AI run
405 Yi-34B 14.7% Nov 2023 Epoch AI run
406 Qwen3.5-0.8B 11.9% Mar 2026 Lab model card
407 granite-4.0-350m 11.2% Oct 2025 Epoch AI run
408 deepseek-r1-0528-qwen3-8b 9.28% May 2025 Epoch AI run

Epoch AI has run 231 models. Labs report scores for 306 models in their cards. Switch the scores above to rank them together.

3 models have held number one on the official leaderboard since its release in November 2023 21 models have held number one across all independent runs since its release in November 2023 22 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, Epoch AI’s runs and what labs claim in their cards.

Google DeepMind xAI OpenAI Anthropic
Own leaderboard Passed 85% in Feb 2026, by Gemini 3.1 Pro
Epoch AI runs Passed 85% in Jun 2025, by Gemini 2.5 Pro
Lab claims Passed 85% in Jun 2025, by Gemini 2.5 Pro

Sources: Official GPQA Diamond leaderboard, Epoch AI runs (CC BY 4.0) and labs’ model cards

Google DeepMind’s own number for Gemini 2.5 Pro passed 85% in June 2025

That was 19 months after its release. By the same age, 32% 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 Run by Epoch AI Reported by the lab in its model card Best so far
0% 20% 40% 60% 80% 100% 2023 2024 2025 2026 2027 Near the ceiling (85%) Random guessing Highest possible score GPT-6.2 Astra GPT-5.4 Pro GPT-5 Gemini 2.5 Pro o3-mini Claude 3.5 Sonnet GPT-4o 0% 20% 40% 60% 80% 100% 2023 2024 2025 2026 2027 Near the ceiling (85%) Random guessing Highest possible score GPT-6.2 Astra GPT-5

Sources: Official GPQA Diamond leaderboard, Epoch AI runs (CC BY 4.0) and labs’ model cards

20 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
Meta
Microsoft
Qwen
xAI
DeepSeek
Shanghai AI Lab
MiniMax
Mistral AI
Tencent
Reka
Baidu
NVIDIA
LG AI Research
Deep Cogito
ByteDance Seed
Z.ai
Xiaomi Corp
Amazon
Prime Intellect
Technology Innovation Institute
Sarvam AI
Moonshot AI
Inception Labs
Liquid AI
Arcee AI
StepFun
Nous Research
Meituan
IBM
Ai2
Upstage
Ant Group
Thinking Machines
Reflection
iFlytek
DateLaunch postScoreAs the post writes it
Nov 5, 2026 Inkling 2 Small 93 GPQA Diamond, 93.0%
Oct 27, 2026 LFM3-1.7B 63.4 GPQA Diamond
Oct 24, 2026 Kimi K3.1 Pro 94.2 GPQA-Diamond
Oct 22, 2026 Spark-X2.6-4B 77.1 GPQA Diamond
Oct 19, 2026 Mercury 3 89.2 GPQA Diamond
Oct 15, 2026 Muse Spark Open 89 GPQA Diamond
Oct 15, 2026 Nemotron 3.5 Bolt 74B-A9B 86.4 GPQA Diamond
Oct 15, 2026 Nemotron 3.5 Super VL 89.5 GPQA-Diamond
Oct 13, 2026 LFM2.5-24B-A2B 74.4 GPQA Diamond
Oct 5, 2026 Beam 1.0 90.5 GPQA Diamond
Sep 20, 2026 Step 5 Preview 93.5 GPQA Diamond
Sep 18, 2026 Qwen3.8-Omni-Flash 91 GPQA Diamond
Sep 10, 2026 DeepSeek V4.1 Flash 90.9 GPQA Diamond (Pass@1)
Sep 8, 2026 Mercury 2.5 79 GPQA Diamond
Sep 3, 2026 GPT-6 Astra 96 GPQA Diamond
Aug 28, 2026 Tencent Hy4 preview 92.3 GPQA Diamond
Aug 26, 2026 Qwen3.8 Flash 91.7 Scientific reasoning GPQA Diamond
Aug 25, 2026 Granite 4.2 30B 66.4 GPQA
Aug 14, 2026 Qwen 3.8 27B 89.2 Scientific reasoning GPQA Diamond
Aug 11, 2026 Nemotron 3.5 Lightning 30B-A3B 75.4 GPQA Diamond (no tools)
Aug 11, 2026 Solar Pro 4 89 GPQA Diamond (Artificial Analysis score quoted by Upstage)
Aug 10, 2026 Muse Glimmer 83.5 GPQA Diamond (AA)
Aug 3, 2026 Qwen 3.8 Max 92.6 GPQA Diamond
Jul 31, 2026 K-EXAONE 2.0 82.2 GPQA-Diamond
Jul 30, 2026 Inkling-Small 89.5 GPQA Diamond
Jul 22, 2026 Solar Open 2 86.3 GPQA-Diamond
Jul 16, 2026 Kimi K3 93.5 GPQA Diamond
Jul 15, 2026 Inkling 87.2 GPQA Diamond (Artificial Analysis)
Jul 9, 2026 GPT-5.6 Luna 92.3 GPQA Diamond
Jul 9, 2026 GPT-5.6 Terra 92.9 GPQA Diamond
Jul 9, 2026 GPT-5.6 Sol 94.6 GPQA Diamond
Jul 5, 2026 LongCat-2.0 88.9 GPQA-diamond
Jul 2, 2026 Tencent Hy3 90.4 GPQA Diamond
Jun 16, 2026 GLM-5.2 91.2 GPQA-Diamond
Jun 10, 2026 DiffusionGemma 26B A4B 73.2 GPQA Diamond
Jun 4, 2026 Nemotron 3 Ultra 87 GPQA (no tools)
Jun 3, 2026 Gemma 4 12B 78.8 GPQA Diamond
Jun 2, 2026 MAI-Code-1-Flash 84.6 GPQA Diamond
Jun 2, 2026 MAI-Thinking-1 84.2 GPQA Diamond
Jun 1, 2026 Qwen3.7-Plus 90.3 GPQA Diamond
May 28, 2026 Claude Opus 4.8 93.6 GPQA Diamond
May 20, 2026 Qwen3.7-Max 92.4 GPQA Diamond
May 14, 2026 Ring-2.6-1T 88.3 GPQA Diamond (xhigh)
May 9, 2026 ERNIE 5.1 91 GPQA (pass@1)
May 5, 2026 GPT-5.5 Instant 85.6 GPQA (PhD-Level Science)
Apr 29, 2026 Granite 4.1 30B 45.8 GPQA (0-shot, CoT; subset not stated)
Apr 28, 2026 Seed2.0 Lite (0428) 88.4 GPQA Diamond
Apr 24, 2026 DeepSeek-V4-Flash 88.1 GPQA Diamond (Pass@1), V4-Flash Max
Apr 24, 2026 DeepSeek-V4-Pro 90.1 GPQA Diamond (Pass@1)
Apr 23, 2026 Tencent Hy3 preview 87.2 GPQA-Diamond
Apr 23, 2026 GPT-5.5 93.6 GPQA Diamond
Apr 22, 2026 Qwen3.6 27B 87.8 GPQA Diamond
Apr 20, 2026 Kimi K2.6 90.5 GPQA-Diamond
Apr 16, 2026 Claude Opus 4.7 94.2 Graduate-level reasoning GPQA Diamond
Apr 15, 2026 Qwen 3.6 35B-A3B 86 GPQA
Apr 9, 2026 EXAONE 4.5 33B 80.5 GPQA-Diamond
Apr 8, 2026 Muse Spark 89.5 GPQA Diamond (PhD Level Reasoning)
Apr 7, 2026 GLM-5.1 86.2 GPQA-Diamond
Apr 7, 2026 Claude Mythos Preview 94.5 GPQA Diamond
Apr 2, 2026 Gemma 4 E4B 58.6 GPQA Diamond
Apr 2, 2026 Gemma 4 E2B 43.4 GPQA Diamond
Apr 2, 2026 Gemma 4 26B A4B 82.3 GPQA Diamond
Apr 2, 2026 Qwen 3.6 Plus 90.4 GPQA
Apr 2, 2026 Gemma 4 31B IT 84.3 GPQA Diamond
Apr 1, 2026 Trinity Large Thinking 76.3 GPQA-Diamond
Mar 30, 2026 Qwen3.5-Omni-Plus 83.9 GPQA
Mar 24, 2026 Solar Pro 3 (March 2026 update) 71.9 GPQA-Diamond
Mar 19, 2026 Nemotron-Cascade 2 30B-A3B 76.1 GPQA-Diamond
Mar 17, 2026 GPT-5.4 Nano 82.8 GPQA Diamond
Mar 17, 2026 GPT-5.4 Mini 88 GPQA Diamond
Mar 16, 2026 Nemotron 3 Nano 4B 53.2 GPQA (reasoning on)
Mar 16, 2026 Mistral Small 4 71.2 GPQA Diamond (reasoning; instruct = 59.1)
Mar 11, 2026 Nemotron 3 Super 79.2 GPQA (no tools)
Mar 6, 2026 Sarvam 30B 66.5 GPQA Diamond
Mar 6, 2026 Sarvam 105B 78.7 GPQA Diamond
Mar 5, 2026 GPT-5.4 Pro 94.4 GPQA Diamond
Mar 5, 2026 GPT-5.4 92.8 GPQA Diamond (GPT-5.4)
Mar 3, 2026 Gemini 3.1 Flash-Lite 86.9 GPQA Diamond (No tools)
Mar 2, 2026 Qwen3.5-0.8B 11.9 GPQA
Mar 2, 2026 Qwen3.5-2B 51.6 GPQA
Mar 2, 2026 Qwen3.5-4B 76.2 GPQA Diamond
Mar 2, 2026 Qwen3.5-9B 81.7 GPQA Diamond
Feb 24, 2026 Qwen3.5-35B-A3B 84.2 GPQA Diamond
Feb 24, 2026 Qwen3.5-27B 85.5 GPQA Diamond
Feb 24, 2026 Mercury 2 74 GPQA Diamond
Feb 24, 2026 Qwen3.5-122B-A10B 86.6 GPQA Diamond
Feb 19, 2026 Gemini 3.1 Pro 94.3 GPQA Diamond (No tools)
Feb 17, 2026 Claude Sonnet 4.6 89.9 Graduate-level reasoning GPQA Diamond
Feb 16, 2026 Qwen3.5 397B-A17B 88.4 GPQA
Feb 14, 2026 Seed2.0 Pro 88.9 GPQA Diamond
Feb 12, 2026 MiniMax-M2.5 85.2 GPQA-D
Feb 11, 2026 GLM-5 86 GPQA-Diamond
Feb 6, 2026 ERNIE 5.0 86.4 GPQA-Diamond
Feb 5, 2026 Claude Opus 4.6 91.3 Graduate-level reasoning GPQA Diamond
Jan 27, 2026 Trinity Large Preview 63.3 GPQA-Diamond
Jan 27, 2026 Kimi K2.5 87.6 GPQA-Diamond
Jan 23, 2026 Qwen3-Max-2026-01-23 87.4 GPQA
Jan 20, 2026 LFM2.5-1.2B-Thinking 37.9 GPQA Diamond (± 0.83)
Jan 19, 2026 glm-4.7-flash 75.2 GPQA
Jan 14, 2026 LongCat-Flash-Thinking-2601 85.2 Best of GPQA-Diamond (Avg@16) 80.5 / Heavy Thinking 85.2
Jan 5, 2026 Falcon H1R 7B 61.3 GPQA-D
Jan 5, 2026 LFM2.5-1.2B-Instruct 38.9 GPQA
Jan 5, 2026 Solar Open 100B 68.1 GPQA-Diamond
Dec 31, 2025 K-EXAONE 79.1 GPQA-Diamond
Dec 23, 2025 MiniMax-M2.1 83 GPQA-D
Dec 22, 2025 GLM-4.7 85.7 GPQA-Diamond
Dec 18, 2025 Seed1.8 83.8 GPQA-Diamond
Dec 17, 2025 Gemini 3 Flash 90.4 GPQA Diamond (No tools)
Dec 16, 2025 MiMo-V2-Flash 83.7 GPQA-Diamond
Dec 15, 2025 Nemotron 3 Nano 30B-A3B 73 GPQA (no tools)
Dec 12, 2025 Olmo 3.1 32B Think 57.5 GPQA
Dec 11, 2025 GPT-5.2 Pro 93.2 GPQA Diamond (no tools)
Dec 11, 2025 GPT-5.2 92.4 GPQA Diamond (no tools) Science questions
Dec 3, 2025 Hermes 4.3 36B 65.5 GPQA Diamond
Dec 2, 2025 Ministral 3 14B 71.2 GPQA Diamond 0.712 (reasoning)
Dec 2, 2025 Nova 2 Lite 79.6 GPQA Diamond acc
Dec 2, 2025 Nova 2.0 Pro Preview 81.4 GPQA Diamond acc
Dec 2, 2025 Mistral Large 3 43.9 GPQA-Diamond (5-shot, no CoT) [base]
Dec 1, 2025 Trinity Mini 58.5 GPQA-Diamond
Dec 1, 2025 DeepSeek-V3.2 82.4 GPQA Diamond (Pass@1)
Nov 26, 2025 INTELLECT-3 74.4 GPQA
Nov 24, 2025 Claude Opus 4.5 87 Graduate-level reasoning GPQA Diamond
Nov 20, 2025 Olmo 3 32B Think 58.1 GPQA
Nov 19, 2025 Cogito v2.1 77.7 GPQA Diamond
Nov 18, 2025 Gemini 3 Pro 91.9 GPQA Diamond (No tools)
Nov 13, 2025 GPT-5.1 88.1 GPQA Diamond (no tools)
Nov 6, 2025 Kimi K2 Thinking 84.5 GPQA, no tools
Oct 31, 2025 LongCat-Flash-Omni 74.4 GPQA-diamond(acc)
Oct 28, 2025 granite-4.0-1b 29.9 GPQA (0-shot, CoT; subset not stated)
Oct 27, 2025 MiniMax-M2 78 GPQA-Diamond (AA)
Oct 15, 2025 Claude Haiku 4.5 73 Graduate-level reasoning GPQA Diamond
Oct 7, 2025 LFM2-8B-A1B 29.3 GPQA
Oct 2, 2025 Granite 4.0 H Small 40.6 GPQA (0-shot, CoT; subset not stated)
Sep 30, 2025 GLM-4.6 81 GPQA
Sep 29, 2025 DeepSeek-V3.2-Exp 79.9 GPQA-Diamond
Sep 29, 2025 Claude Sonnet 4.5 83.4 Graduate-level reasoning GPQA Diamond
Sep 25, 2025 Gemini 2.5 Flash-Lite 71.7 GPQA diamond, Thinking
Sep 25, 2025 Gemini 2.5 Flash 80.8 GPQA diamond single attempt, model card
Sep 24, 2025 Qwen3-Max GPQA (Thinking Heavy w/ Python)
Sep 22, 2025 Qwen3-Omni-30B-A3B 69.6 GPQA
Sep 22, 2025 DeepSeek-V3.1-Terminus 80.7 GPQA-Diamond
Sep 21, 2025 LongCat-Flash-Thinking 81.5 GPQA-Diamond(Mean@16)
Sep 19, 2025 Grok 4 Fast 85.7 GPQA Diamond pass@1
Sep 17, 2025 Magistral Small 1.2 70.1 GPQA Diamond
Sep 17, 2025 Magistral Medium 1.2 76.3 GPQA Diamond
Sep 11, 2025 Qwen3-Next-80B-A3B 77.2 GPQA
Aug 29, 2025 LongCat-Flash-Chat 73.2 GPQA-diamond(acc)
Aug 26, 2025 Hermes 4 405B 70.5 GPQA Diamond (reasoning)
Aug 25, 2025 InternVL3.5-241B-A28B 73.2 GPQA
Aug 21, 2025 DeepSeek-V3.1 80.1 GPQA-Diamond (Pass@1)
Aug 20, 2025 seed-oss-36b-instruct 71.4 GPQA-D
Aug 18, 2025 nvidia-nemotron-nano-9b-v2 64 GPQA
Aug 7, 2025 GPT-5 nano 71.2 GPQA diamond (no tools)
Aug 7, 2025 GPT-5 mini 82.3 GPQA diamond (no tools)
Aug 7, 2025 GPT-5 89.4 GPQA Diamond, GPT-5 pro (python)
Aug 5, 2025 gpt-oss-20b 71.5 GPQA Diamond (without tools)
Aug 5, 2025 Claude Opus 4.1 80.9 Graduate-level reasoning GPQA Diamond
Aug 5, 2025 gpt-oss-120b 80.1 GPQA Diamond (without tools)
Jul 31, 2025 Cogito v2 Preview 671B MoE 76 GPQA - Diamond (thinking)
Jul 31, 2025 Step 3 73 GPQA-Diamond
Jul 29, 2025 AFM-4.5B 27.8 GPQA-D-Zero
Jul 28, 2025 GLM-4.5 79.1 GPQA
Jul 25, 2025 Llama-3.3-Nemotron-Super-49B-v1.5 72 GPQA (pass@1, avg of 4)
Jul 25, 2025 Qwen3-235B-A22B-Thinking 81.1 GPQA
Jul 24, 2025 Magistral Small 1.1 65.8 GPQA Diamond
Jul 24, 2025 Magistral Medium 1.1 71.5 GPQA Diamond
Jul 24, 2025 Intern-S1 77.3 GPQA
Jul 15, 2025 EXAONE 4.0 32B 75.4 GPQA-Diamond (reasoning)
Jul 11, 2025 Kimi K2 75.1 GPQA-Diamond, Avg@8
Jul 10, 2025 LFM2-1.2B 31.5 GPQA
Jul 9, 2025 Phi-4-mini-flash-reasoning 45.1 GPQA Diamond
Jul 9, 2025 Grok 4 87.5 GPQA (Science), no tools
Jul 9, 2025 Grok 4 Heavy 88.4 GPQA (Science) [Grok 4 Heavy]
Jun 27, 2025 Hunyuan-A13B-Instruct 71.2 GPQA-Diamond
Jun 26, 2025 Gemma 3n E4B 23.7 GPQA Diamond 0-shot (IT)
Jun 26, 2025 Mercury 51 GPQA Diamond (% accuracy)
Jun 25, 2025 Seed1.6-Thinking 81.5 GPQA-Diamond
Jun 21, 2025 Kimi-VL-A3B-Thinking-2506 42.3 GPQA-Diamond
Jun 20, 2025 Mistral Small 3.2 46.1 GPQA Diamond (5-shot CoT)
Jun 17, 2025 Gemini 2.5 Flash 82.8 GPQA diamond single attempt
Jun 17, 2025 Gemini 2.5 Flash-Lite 66.7 GPQA diamond, Thinking
Jun 17, 2025 Gemini 2.5 Pro 86.4 GPQA diamond, single attempt (pass@1)
Jun 16, 2025 MiniMax-M1-80k 70 GPQA Diamond
Jun 10, 2025 Magistral Small 1.0 68.2 GPQA Diamond
Jun 10, 2025 o3-pro 84 PhD Science Questions (GPQA Diamond), pass@1
Jun 10, 2025 Magistral Medium 1.0 70.8 GPQA Diamond
May 28, 2025 DeepSeek-R1 81 GPQA-Diamond (Pass@1)
May 23, 2025 Sarvam-M 48 GPQA Diamond (0.48)
May 22, 2025 Claude Sonnet 4 83.8 Graduate-level reasoning GPQA Diamond (parallel test-time compute)
May 22, 2025 Claude Opus 4 83.3 Graduate-level reasoning GPQA Diamond (parallel test-time compute)
May 20, 2025 Falcon-H1-34B 49.7 GPQA_Diamond
May 11, 2025 INTELLECT-2 66.8 GPQA-Diamond
May 7, 2025 Mistral Medium 3 57.1 GPQA Diamond 5-shot CoT
Apr 30, 2025 Phi-4-reasoning 65.8 GPQA-D
Apr 30, 2025 Phi-4-mini-reasoning 52 GPQA Diamond
Apr 30, 2025 Amazon Nova Premier 57.1 GPQA Diamond
Apr 30, 2025 Phi-4-Reasoning-plus 68.9 GPQA-D
Apr 29, 2025 MiMo-7B-RL 54.4 GPQA Diamond (Pass@1)
Apr 29, 2025 Qwen3-235B-A22B 71.1 GPQA-Diamond
Apr 17, 2025 Gemini 2.5 Flash 78.3 GPQA diamond single attempt (pass@1)
Apr 16, 2025 o4-mini 81.4 GPQA Diamond (no tools)
Apr 16, 2025 o3 83.3 GPQA Diamond PhD-Level Science Questions, o3 (no tools)
Apr 14, 2025 GPT-4.1 nano 50.3 GPQA Diamond (model-extracted answers)
Apr 14, 2025 GPT-4.1 mini 65 GPQA Diamond (model-extracted answers)
Apr 14, 2025 GLM-Z1-32B-0414 66.1 GPQA
Apr 10, 2025 Seed-Thinking-v1.5 77.3 GPQA diamond
Apr 8, 2025 Cogito v1 Preview 70B 60.6 GPQA - Diamond (thinking)
Apr 7, 2025 Llama-3.1-Nemotron-Ultra-253B-v1 76 GPQA (reasoning on)
Apr 5, 2025 Llama 4 Scout 57.2 GPQA Diamond
Apr 5, 2025 Llama 4 Maverick 69.8 GPQA Diamond
Apr 5, 2025 Llama 4 Behemoth 73.7 GPQA Diamond
Mar 27, 2025 Qwen2.5-Omni-7B 30.8 GPQA
Mar 25, 2025 Gemini 2.5 Pro 84 GPQA diamond, single attempt (pass@1)
Mar 24, 2025 DeepSeek-V3 59.1 GPQA Diamond 59.1 (the original DeepSeek-V3 card. 68.4 is DeepSeek-V3-0324)
Mar 21, 2025 Hunyuan-T1 69.3 GPQA Diamond
Mar 18, 2025 EXAONE Deep 32B 66.1 GPQA Diamond (pass@1)
Mar 18, 2025 Llama-3.3-Nemotron-Super-49B-v1 66.7 GPQA (reasoning on)
Mar 17, 2025 Mistral Small 3.1 46 GPQA Diamond (5-shot CoT)
Mar 16, 2025 ERNIE 4.5 GPQA
Mar 12, 2025 Gemma 3 27B 42.4 GPQA Diamond 0-shot (IT); PT GPQA 5-shot = 24.3
Mar 10, 2025 Reka Flash 3 61.1 GPQA
Feb 27, 2025 Hunyuan-TurboS 57.5 GPQA-diamond
Feb 27, 2025 GPT-4.5 71.4 GPQA (science)
Feb 26, 2025 Phi-4 Mini 30.4 GPQA (0-shot, CoT), subset not stated
Feb 24, 2025 Claude 3.7 Sonnet 84.8 Graduate-level reasoning GPQA Diamond (64K extended thinking, parallel test-time compute)
Feb 19, 2025 Grok-3 mini 84 GPQA (cons@64; pass@1 = 80.3) [Grok 3 mini Think]
Feb 19, 2025 Grok 3 84.6 GPQA (Graduate-Level Google-Proof Q&A (Diamond)) (cons@64; pass@1 = 80.2)
Feb 5, 2025 Gemini 2.0 Flash-Lite 51.5 GPQA (diamond)
Feb 5, 2025 Gemini 2.0 Flash 60.1 GPQA (diamond)
Feb 5, 2025 Gemini 2.0 Pro 64.7 GPQA (diamond)
Jan 31, 2025 o3-mini 79.7 PhD-level Science Questions (GPQA Diamond)
Jan 30, 2025 Mistral Small 3 45.3 gpqa_main_cot_5shot_instruct
Jan 28, 2025 Qwen2.5-Max GPQA-Diamond
Jan 21, 2025 Gemini 2.0 Flash Thinking 74.2 GPQA Diamond (Science)
Jan 20, 2025 DeepSeek-R1 71.5 GPQA-Diamond (Pass@1)
Jan 15, 2025 MiniMax-Text-01 54.4 GPQA* (diamond)
Jan 13, 2025 InternLM3-8B-Instruct 37.4 GPQA-Diamond(0-shot)
Dec 26, 2024 DeepSeek-V3 59.1 GPQA-Diamond (Pass@1)
Dec 17, 2024 o1 75.7 GPQA diamond
Dec 12, 2024 Phi-4 56.1 GPQA (simple-evals)
Dec 11, 2024 Gemini 2.0 Flash 62.1 GPQA (diamond)
Dec 6, 2024 Llama 3.3 70B Instruct 50.5 GPQA Diamond (CoT), 0-shot
Oct 22, 2024 Claude 3.5 Sonnet (October 2024) 65 GPQA (Diamond) (0-shot CoT)
Sep 19, 2024 Qwen2.5-72B 49 GPQA
Sep 12, 2024 o1-preview 78.3 GPQA Diamond cons@64
Aug 20, 2024 Phi-3.5-MoE 36.8 GPQA (0-shot, CoT)
Aug 13, 2024 Grok-2 56 GPQA
Jul 23, 2024 Llama 3.1-405B 51.1 GPQA (0-shot, CoT)
Jul 18, 2024 GPT-4o mini 40.2 GPQA
Jun 20, 2024 Claude 3.5 Sonnet 67.2 GPQA (Diamond) (Maj@32 5-shot CoT)
Jun 7, 2024 Qwen2-72B 42.4 GPQA
May 14, 2024 Gemini 1.5 Pro 46.2 GPQA, 0-shot
May 13, 2024 GPT-4o 53.6 GPQA (0-shot)
Apr 22, 2024 phi-3-medium 14B GPQA (2-Shot; CoT)
Apr 18, 2024 Llama 3-70B 39.5 GPQA (0-shot) [instruct]
Apr 11, 2024 GPT-4 Turbo 49.3 GPQA%
Mar 4, 2024 Claude 3 Opus 59.5 GPQA (Diamond) (Maj@32 5-shot CoT)
Feb 15, 2024 Gemini 1.5 Pro 41.5 GPQA, 0-shot (4-shot = 37.9%)

168 system cards report it, from 32 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
Nov 20, 2026 Inkling 2 Mini model card 86.6 GPQA Diamond Capabilities
Nov 17, 2026 GPT-6.2 Sol system card 96 GPQA Diamond (no tools), accuracy (Table 2, 2.1.1.1.1) Bio and chem risk
Nov 17, 2026 GPT-6.2 Astra system card 97 GPQA Diamond (no tools), accuracy (Table 2, 2.1.1.1.1) Bio and chem risk
Oct 19, 2026 Muse Glimmer technical report 83.5 GPQA Diamond, high, sourced from Artificial Analysis, 85.6 xhigh (Tables 2 and 5) Capabilities
Oct 15, 2026 Nemotron 3.5 Super VL technical report 89.5 GPQAD, mean of 8 repeats (Table 10) Capabilities
Oct 15, 2026 Nemotron 3.5 Super 120B-A12B Base technical report 66.2 GPQA Diamond, 5-shot CoT exact match, Table 6 Capabilities
Oct 15, 2026 Nemotron 3.5 Lightning 30B-A3B technical report 76.5 GPQA Diamond (no tools), BF16 acc. (Table 22) Capabilities
Oct 15, 2026 Nemotron 3.5 Lightning 30B-A3B Base technical report 33.3 GPQA Diamond, 5-shot CoT exact match, Table 6 Capabilities
Oct 15, 2026 Nemotron 3.5 Bolt 74B-A9B technical report 86.4 GPQA Diamond, released 24GB checkpoint (Table 7). BF16 88.83 Capabilities
Oct 5, 2026 Beam 1.0 Base technical report 72.4 GPQA Diamond, 0-shot temperature 0.7, Table 23 Capabilities
Sep 22, 2026 Qwen3.8-Omni-Flash technical report 91 GPQA Diamond (Table 2) Capabilities
Sep 10, 2026 DeepSeek V4.1 Flash technical report 90.9 GPQA Diamond (Pass@1), Max effort (Table 3) Capabilities
Aug 5, 2026 K-EXAONE 2.0 technical report 82.2 GPQA-Diamond (Table 6, Reasoning mode) Capabilities
Jul 31, 2026 DiffusionGemma 26B A4B technical report 73.2 GPQA Diamond, TD, 64.6 no-think, 79.8 AR (Table 3) Capabilities
Jul 30, 2026 Inkling-Small model card 89.5 GPQA Diamond (5. Evaluations table) Capabilities
Jul 27, 2026 Kimi K3 technical report 93.5 GPQA Diamond, max effort (Table 2) Capabilities
Jul 24, 2026 Gemma 4 E4B technical report 58.6 GPQA Diamond, thinking (Table 5) Capabilities
Jul 24, 2026 Gemma 4 E2B technical report 43.4 GPQA Diamond, thinking (Table 5) Capabilities
Jul 24, 2026 Gemma 4 31B IT technical report 84.3 GPQA Diamond, thinking (Table 5) Capabilities
Jul 24, 2026 Gemma 4 26B A4B technical report 82.3 GPQA Diamond, thinking (Table 5) Capabilities
Jul 22, 2026 Solar Open 2 technical report 86.3 GPQA-Diamond (Table 3) Capabilities
Jul 15, 2026 Inkling model card 87.2 GPQA Diamond (5. Evaluations table, effort 0.99) Capabilities
Jun 13, 2026 Ring-2.6-1T technical report 85.9 GPQA-Diamond (Avg@16), xhigh (Table 6). High gives 76.10 Capabilities
Jun 13, 2026 Ling-2.6-1T technical report 76.2 GPQA-Diamond, Mean@4, CoT (Table 5) Capabilities
Jun 9, 2026 Nemotron 3 Ultra technical report 87 GPQA (no tools) (Table 10) Capabilities
Jun 4, 2026 Nemotron 3 Ultra 550B-A55B Base model card 50 GPQA, 5-shot CoT EM Capabilities
Jun 2, 2026 MAI-Thinking-1 technical report 84.2 GPQA Diamond, pass@1 averaged over 16 rollouts (Table 11) Capabilities
Jun 2, 2026 MAI-Code-1-Flash model card 84.6 GPQA Diamond, Acc (Core reasoning table) Capabilities
May 28, 2026 Claude Opus 4.8 system card 93.6 GPQA Diamond, averaged over 25 trials (Table 8.1.A, 8.6) Capabilities
May 26, 2026 MiniMax-M2 technical report 78 GPQA-Diamond, MiniMax-M2 bar, printed label (Figure 9) Capabilities
May 26, 2026 MiniMax-M2.7 technical report 89.8 GPQA-Diamond, AA Index v4.0 protocol, pass@1 (Table 4) Capabilities
May 26, 2026 MiniMax-M2.5 technical report 85.2 GPQA-Diamond, AA Index v4.0 protocol, pass@1 (Table 4) Capabilities
Apr 27, 2026 Nemotron 3 Nano Omni 30B-A3B technical report 72.2 GPQA (no tools), GPQA-Diamond average of 4 runs (Table 10 and Section 4.4) Capabilities
Apr 26, 2026 DeepSeek-V4-Pro technical report 90.1 GPQA Diamond (Pass@1), DS-V4-Pro Max (Table 6) Capabilities
Apr 26, 2026 DeepSeek-V4-Flash technical report 88.1 GPQA Diamond (Pass@1), DeepSeek-V4-Flash Max (Table 7) Capabilities
Apr 17, 2026 Qwen3.5-Omni-Plus technical report 83.9 GPQA (Table 4) Capabilities
Apr 16, 2026 Claude Opus 4.7 system card 94.2 GPQA Diamond, average of 10 trials (Table 8.1.A, 8.4) Capabilities
Apr 9, 2026 EXAONE 4.5 33B technical report 80.5 GPQA-Diamond (Table 3, Reasoning mode) Capabilities
Apr 7, 2026 Claude Mythos Preview system card 94.5 GPQA Diamond, adaptive thinking, max effort, average of 5 trials (Table 6.3.A; 94.55 in 6.6) Capabilities
Mar 21, 2026 Seed1.8 model card 83.8 GPQA-Diamond (Table 1) Capabilities
Mar 19, 2026 Nemotron-Cascade 2 30B-A3B technical report 76.1 GPQA-Diamond (Table 1) Capabilities
Mar 11, 2026 Nemotron 3 Super technical report 79.2 GPQA (no tools), 82.70 with tools (Table 5) Capabilities
Mar 3, 2026 Gemini 3.1 Flash-Lite model card 86.9 GPQA Diamond, no tools (results table, p.4) Capabilities
Feb 28, 2026 Qwen3-Coder-Next technical report 74.5 GPQA, subset not stated (Table 8) Capabilities
Feb 19, 2026 Gemini 3.1 Pro model card 94.3 GPQA Diamond, no tools (results table, p.4) Capabilities
Feb 19, 2026 Trinity Large Preview technical report 63.3 GPQA Diamond, Trinity Large Preview (Table 4) Capabilities
Feb 17, 2026 GLM-5 technical report 86 GPQA-Diamond (Table 7) Capabilities
Feb 17, 2026 Claude Sonnet 4.6 system card 89.9 GPQA Diamond, adaptive thinking, max effort, average of 10 trials (Table 2.1.A, 2.9) Capabilities
Feb 14, 2026 Seed2.0 Pro model card 88.9 GPQA Diamond (Table 3) Capabilities
Feb 11, 2026 Step 3.5 Flash technical report 83.5 GPQA-Diamond (Table 5). PaCoRe 85.0, with Python 84.4 (Table 12) Capabilities
Feb 5, 2026 Claude Opus 4.6 system card 91.3 GPQA Diamond, adaptive thinking, max effort, average of 5 trials (Table 2.3.A; 91.31 in 2.11) Capabilities
Feb 4, 2026 ERNIE 5.0 technical report 86.4 GPQA-Diamond (Table 2) Capabilities
Jan 30, 2026 Kimi K2.5 technical report 87.6 GPQA-Diamond, Avg@8 (Table 4) Capabilities
Jan 23, 2026 LongCat-Flash-Thinking-2601 technical report 85.2 GPQA-Diamond (Avg@16), heavy mode (Table 2). Default mode 80.5 Capabilities
Jan 14, 2026 STEP3-VL-10B technical report 70.8 GPQA-Diamond, SeRe (Tables 2 and 3). PaCoRe 73.99 Capabilities
Jan 13, 2026 Ministral 3 14B technical report 71.2 GPQA Diamond, reported as pass@16 (Table 5) Capabilities
Jan 11, 2026 Solar Open 100B technical report 68.1 GPQA-Diamond (Table 6) Capabilities
Jan 6, 2026 MiMo-V2-Flash technical report 84.3 GPQA-Diamond (Table 9). The launch model card prints 83.7 Capabilities
Jan 5, 2026 Falcon H1R 7B technical report 61.3 GPQA-Diamond (Table 6). DeepConf@512 70.2 (Table 7) Capabilities
Jan 5, 2026 K-EXAONE technical report 79.1 GPQA-Diamond (Table 3, Reasoning mode). Non-reasoning 70.6 (Table 4) Capabilities
Dec 23, 2025 Nemotron 3 Nano 30B-A3B technical report 73 GPQA (no tools) (Table 3). With tools 75.00 Capabilities
Dec 18, 2025 INTELLECT-3 technical report 74.4 GPQA (Diamond subset), Avg@4 (Table 2, Appendix A.1) Capabilities
Dec 15, 2025 Olmo 3 32B Think technical report 58.1 GPQA, Final Think 3.0 column (Table 14) Capabilities
Dec 15, 2025 Olmo 3.1 32B Think technical report 57.5 GPQA (Table 1). Table 14 prints 56.7 for Final Think 3.1 Capabilities
Dec 2, 2025 Nova 2 Lite technical report 79.6 GPQA Diamond acc (Table 1) Capabilities
Dec 2, 2025 Nova 2.0 Pro Preview technical report 81.4 GPQA Diamond acc (Table 1) Capabilities
Dec 1, 2025 DeepSeek-V3.2 technical report 82.4 GPQA Diamond (Pass@1), DeepSeek-V3.2 Thinking (Table 2) Capabilities
Dec 1, 2025 DeepSeek-V3.2-Speciale technical report 85.7 GPQA Diamond (Pass@1), DeepSeek-V3.2-Speciale (Table 3) Capabilities
Nov 28, 2025 LFM2-8B-A1B technical report 29.3 GPQA, LFM2-8B-A1B (Table 7) Capabilities
Nov 28, 2025 LFM2-1.2B technical report 31.5 GPQA, LFM2-1.2B (Table 6) Capabilities
Nov 26, 2025 Qwen3-VL-235B-A22B technical report 77.1 GPQA (Table 6) Capabilities
Nov 24, 2025 Claude Opus 4.5 system card 87 GPQA Diamond, 64k thinking, avg of 5 trials (Table 2.3.A; 86.95% in 2.18) Capabilities
Nov 6, 2025 Nemotron Nano 12B v2 VL technical report 64.1 GPQA, reasoning on, SFT stage 4 (Table 6), GPQA-Diamond in 4.2 Capabilities
Oct 31, 2025 LongCat-Flash-Omni technical report 74.4 GPQA-diamond (acc) (Table 13) Capabilities
Oct 21, 2025 Ring-1T technical report 78.6 GPQA-Diamond (Table 1) Capabilities
Sep 30, 2025 Code World Model (CWM) technical report 40.6 GPQA, without reasoning, subset not stated (Table 13) Capabilities
Sep 29, 2025 DeepSeek-V3.2-Exp technical report 79.9 GPQA-Diamond (Pass@1), DeepSeek-V3.2-Exp (Table 1) Capabilities
Sep 26, 2025 Gemini 2.5 Flash model card 80.8 GPQA diamond, single attempt (pass@1) (Table, p.4) Capabilities
Sep 25, 2025 gemini-robotics-er-1.5-preview technical report 83.3 GPQA (Table 20, thinking on). Thinking off 81.3 Capabilities
Sep 23, 2025 LongCat-Flash-Thinking technical report 81.5 GPQA-Diamond(Mean@16), LLM judge (Table 2) Capabilities
Sep 22, 2025 Qwen3-Omni-30B-A3B technical report 69.6 GPQA, Instruct (Table 4). Thinking 73.1 (Table 5) Capabilities
Sep 1, 2025 LongCat-Flash-Chat technical report 73.2 GPQA-diamond (acc) (Table 3) Capabilities
Aug 25, 2025 InternVL3.5-241B-A28B technical report 73.2 GPQA, cited without the Diamond label (Table 2) Capabilities
Aug 25, 2025 Hermes 4 405B technical report 70.6 GPQA Diamond, reasoning mode (Table 3). Non-reasoning 39.4. v1 printed 70.5 Capabilities
Aug 21, 2025 Intern-S1 technical report 77.3 GPQA, Diamond subset (Table 2) Capabilities
Aug 20, 2025 nvidia-nemotron-nano-9b-v2 technical report 64 GPQA-D, NVIDIA-Nemotron-Nano-9B-v2 (Figure 1) Capabilities
Aug 8, 2025 GLM-4.5 technical report 79.1 GPQA, Avg@8 (Table 4) Capabilities
Aug 8, 2025 GLM-4.5-Air technical report 75 GPQA, Avg@8 (Table 4) Capabilities
Aug 5, 2025 gpt-oss-20b model card 71.5 GPQA Diamond (no tools), high reasoning (with tools 74.2) (Table 3) Capabilities
Aug 5, 2025 gpt-oss-120b model card 80.1 GPQA Diamond (no tools), high reasoning (with tools 80.9) (Table 3) Capabilities
Jul 30, 2025 Falcon-H1-34B technical report 49.7 GPQA_Diamond, average accuracy over 3 repetitions (Table 24) Capabilities
Jul 21, 2025 Kimi K2 technical report 75.1 GPQA-Diamond (Avg@8) (Table 3) Capabilities
Jul 15, 2025 EXAONE 4.0 32B technical report 75.4 GPQA-Diamond, n=8 (Table 3, Reasoning). Non-reasoning 63.7 (Table 4) Capabilities
Jul 9, 2025 Phi-4-mini-flash-reasoning technical report 45.1 GPQA Diamond, pass@1 averaged over 8 samples (Table 4) Capabilities
Jul 7, 2025 Gemini 2.5 Pro technical report 86.4 GPQA (diamond), single attempt pass@1 (Table 3) Capabilities
Jul 7, 2025 Gemini 2.5 Flash technical report 82.8 GPQA (diamond), single attempt pass@1 (Table 3) Capabilities
Jun 26, 2025 Hunyuan-A13B-Instruct technical report 71.2 GPQA-Diamond, slow-thinking (Table 3). Fast-thinking 61.8 (Table 4) Capabilities
Jun 16, 2025 MiniMax-M1-80k technical report 70 GPQA Diamond, avg of 32 samples (Table 2) Capabilities
Jun 12, 2025 Magistral Small 1.0 technical report 68.2 GPQA, SFT + RL (Magistral Small) column (Table 3) Capabilities
Jun 12, 2025 Magistral Medium 1.0 technical report 70.8 GPQA (Table 2) Capabilities
May 14, 2025 Qwen3-8B technical report 62 GPQA-Diamond, thinking mode (Table 17). Non-thinking 39.3 (Table 18) Capabilities
May 14, 2025 Qwen3-4B technical report 55.9 GPQA-Diamond, thinking mode (Table 17). Non-thinking 41.7 (Table 18) Capabilities
May 14, 2025 Qwen3-32B technical report 68.4 GPQA-Diamond, thinking mode (Table 13). Non-thinking 54.6 (Table 14) Capabilities
May 14, 2025 Qwen3-30B-A3B technical report 65.8 GPQA-Diamond, thinking mode (Table 15). Non-thinking 54.8 (Table 16) Capabilities
May 14, 2025 Qwen3-235B-A22B technical report 71.1 GPQA-Diamond, thinking mode (Table 11). Non-thinking 62.9 (Table 12) Capabilities
May 14, 2025 Qwen3-14B technical report 64 GPQA-Diamond, thinking mode (Table 15). Non-thinking 54.8 (Table 16) Capabilities
May 14, 2025 Qwen3-1.7B technical report 40.1 GPQA-Diamond, thinking mode (Table 19). Non-thinking 28.6 (Table 20) Capabilities
May 12, 2025 MiMo-7B-RL technical report 54.4 GPQA Diamond (Pass@1), average of 8 runs (Table 4, Table 6) Capabilities
May 12, 2025 INTELLECT-2 technical report 66.8 GPQA-Diamond, evalchemy defaults, target length 10,000 tokens (Table 1) Capabilities
May 2, 2025 Llama-3.3-Nemotron-Super-49B-v1 technical report 66.7 GPQA-Diamond, reasoning on, reasoning off 50.0 (Table 4) Capabilities
May 2, 2025 Llama-3.1-Nemotron-Ultra-253B-v1 technical report 76 GPQA-Diamond, reasoning on, reasoning off 56.6 (Table 5) Capabilities
Apr 30, 2025 Phi-4-reasoning technical report 67.1 GPQA-D, average pass@1 (Table 1) Capabilities
Apr 30, 2025 Phi-4-Reasoning-plus technical report 69.3 GPQA-D, average pass@1 (Table 1) Capabilities
Apr 30, 2025 Phi-4-mini-reasoning technical report 52 GPQA Diamond, pass@1 (Table 3) Capabilities
Apr 30, 2025 Amazon Nova Premier technical report 57.1 GPQA Diamond, 0-shot CoT, +/-6.9 (Table 1) Capabilities
Apr 29, 2025 Gemini 2.5 Flash model card 78.3 GPQA diamond, single attempt (pass@1) (Table, p.4) Capabilities
Apr 28, 2025 Gemini 2.5 Pro model card 84 GPQA diamond, 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 60.1 GPQA (diamond) (Table, p.3, column Gemini 2.0 Flash (GA)) Capabilities
Apr 10, 2025 Gemini 2.0 Flash-Lite model card 51.5 GPQA (diamond) (Table, p.3) Capabilities
Apr 10, 2025 Seed-Thinking-v1.5 technical report 77.3 GPQA diamond, mean of 8 samples (Table 2) Capabilities
Apr 5, 2025 Llama 4 Scout model card 57.2 GPQA Diamond, 0-shot, accuracy, instruction tuned (Instruction tuned models table) Capabilities
Apr 5, 2025 Llama 4 Maverick model card 69.8 GPQA Diamond, 0-shot, accuracy, instruction tuned (Instruction tuned models table) Capabilities
Apr 1, 2025 Cohere Command A technical report 50.8 GPQA, Diamond subset, 0-shot CoT (Table 3, Table 15) Capabilities
Mar 26, 2025 Qwen2.5-Omni-7B technical report 30.8 GPQA (Table 1), read as GPQA Diamond as in the launch record Capabilities
Mar 25, 2025 Gemma 3 4B technical report 30.8 GPQA Diamond, IT, zero-shot (Table 6) Capabilities
Mar 25, 2025 Gemma 3 27B technical report 42.4 GPQA Diamond, IT, zero-shot (Table 6) Capabilities
Mar 25, 2025 Gemma 3 1B technical report 19.2 GPQA Diamond, IT, zero-shot (Table 6) Capabilities
Mar 25, 2025 Gemma 3 12B technical report 40.9 GPQA Diamond, IT, zero-shot (Table 6) Capabilities
Mar 16, 2025 EXAONE Deep 32B technical report 66.1 GPQA Diamond, pass@1 with k=16 (Table 3) Capabilities
Mar 3, 2025 Phi-4 Mini technical report 30.4 GPQA (0-Shot, CoT), subset not stated (Table 7). GPQA Diamond 36.9 in the CoT reasoning comparison (Table 9) Capabilities
Feb 19, 2025 Qwen2.5-VL-72B technical report 49 GPQA (Table 4) Capabilities
Jan 26, 2025 Qwen2.5-14B-Instruct-1M technical report 39.9 GPQA (Table 6), mapped to GPQA Diamond as the almanac alias does Capabilities
Jan 20, 2025 DeepSeek-R1 technical report 71.5 GPQA Diamond (Pass@1), DeepSeek-R1 (Table 8, same as final column of Table 3) Capabilities
Jan 20, 2025 DeepSeek-R1-Distill-Qwen-32B technical report 62.1 GPQA Diamond pass@1, DeepSeek-R1-Distill-Qwen-32B (Table 15) Capabilities
Jan 20, 2025 DeepSeek-R1-Distill-Qwen-14B technical report 59.1 GPQA Diamond pass@1, DeepSeek-R1-Distill-Qwen-14B (Table 15) Capabilities
Jan 20, 2025 DeepSeek-R1-Distill-Qwen-1.5B technical report 33.8 GPQA Diamond pass@1, DeepSeek-R1-Distill-Qwen-1.5B (Table 15) Capabilities
Jan 20, 2025 DeepSeek-R1-Distill-Llama-70B technical report 65.2 GPQA Diamond pass@1, DeepSeek-R1-Distill-Llama-70B (Table 15) Capabilities
Jan 14, 2025 MiniMax-Text-01 technical report 54.4 GPQA (diamond), 0-shot CoT (Table 8) Capabilities
Dec 31, 2024 OLMo 2 32B Instruct technical report 35.9 GPQA, unseen suite, 0-shot CoT, subset not stated (Table 24) Capabilities
Dec 26, 2024 DeepSeek-V3 technical report 59.1 GPQA-Diamond (Pass@1), DeepSeek-V3 (Table 6) Capabilities
Dec 19, 2024 Qwen2.5-7B technical report 36.4 GPQA, variant not stated, Qwen2.5-7B-Instruct (Table 8) Capabilities
Dec 19, 2024 Qwen2.5-72B technical report 49 GPQA, variant not stated, Qwen2.5-72B-Instruct (Table 6) Capabilities
Dec 19, 2024 Qwen2.5-32B technical report 49.5 GPQA, variant not stated, Qwen2.5-32B-Instruct (Table 7) Capabilities
Dec 19, 2024 Qwen2.5-14B technical report 45.5 GPQA, variant not stated, Qwen2.5-14B-Instruct (Table 7) Capabilities
Dec 19, 2024 Qwen-Turbo technical report 42.3 GPQA, variant not stated, Qwen2.5-Turbo (Table 7) Capabilities
Dec 12, 2024 Phi-4 technical report 56.1 GPQA, simple-evals diamond set (Table 1) Capabilities
Dec 6, 2024 Llama 3.3 70B Instruct model card 50.5 GPQA Diamond (CoT), 0-shot, acc (Instruction tuned models table) Capabilities
Nov 23, 2024 Llama 3.1-8B technical report 32.8 GPQA (0-shot, CoT), subset not stated, post-trained (Table 2) Capabilities
Nov 23, 2024 Llama 3.1-70B technical report 46.7 GPQA (0-shot, CoT), subset not stated, post-trained (Table 2) Capabilities
Nov 23, 2024 Llama 3.1-405B technical report 51.1 GPQA (0-shot, CoT), subset not stated, post-trained (Table 2) Capabilities
Oct 22, 2024 Claude 3.5 Sonnet (October 2024) model card 65 GPQA (Diamond), 0-shot CoT (Table 7) Capabilities
Oct 22, 2024 Claude 3.5 Haiku model card 41.6 GPQA (Diamond), 0-shot CoT (Table 8) Capabilities
Aug 30, 2024 phi-3-small 7.4B technical report 34.3 GPQA (2-Shot, CoT), subset not stated (Section 3 table) Capabilities
Aug 30, 2024 phi-3-mini 3.8B technical report 32.8 GPQA (2-Shot, CoT), subset not stated (Section 3 table) Capabilities
Aug 30, 2024 Phi-3.5-MoE technical report 36.8 GPQA (0-shot, CoT), subset not stated (Table 3) Capabilities
Aug 30, 2024 Phi-3.5-mini technical report 27.2 GPQA (0-shot, CoT), subset not stated (Table 3) Capabilities
Jul 23, 2024 Llama 3.1-8B model card 30.4 GPQA, 0-shot, em, subset not stated, instruction tuned (Instruction tuned models table) Capabilities
Jul 23, 2024 Llama 3.1-70B model card 46.7 GPQA, 0-shot, em, subset not stated, instruction tuned (Instruction tuned models table) Capabilities
Jul 23, 2024 Llama 3.1-405B model card 50.7 GPQA, 0-shot, em, subset not stated, instruction tuned (Instruction tuned models table) Capabilities
Jul 15, 2024 Qwen2-72B technical report 42.4 GPQA, variant not stated, Qwen2-72B-Instruct (Table 6) Capabilities
Jun 20, 2024 Claude 3.5 Sonnet model card 59.4 GPQA (Diamond), 0-shot CoT. Maj@32 5-shot CoT 67.2 (Table 1) Capabilities
Jun 18, 2024 GLM-4 technical report 35.7 GLM-4 (0116), GPQA, subset not stated (Table 2) Capabilities
Jun 18, 2024 ChatGLM3-6B technical report 26.8 ChatGLM3-6B-Base, GPQA, subset not stated (Table 1) Capabilities
Apr 18, 2024 Llama 3-8B model card 34.2 GPQA (0-shot), subset not stated, instruction tuned (Instruction tuned models table) Capabilities
Apr 18, 2024 Llama 3-70B model card 39.5 GPQA (0-shot), subset not stated, instruction tuned (Instruction tuned models table) Capabilities
Mar 4, 2024 Claude 3 Sonnet model card 40.4 GPQA (Diamond), 0-shot CoT, mean of 10 rollouts. 5-shot CoT 42.9, Maj@32 5-shot CoT 46.3 (Table 1, Table 8) Capabilities
Mar 4, 2024 Claude 3 Opus model card 50.4 GPQA (Diamond), 0-shot CoT, mean of 10 rollouts. 5-shot CoT 53.3, Maj@32 5-shot CoT 59.5 (Table 1, Table 8) Capabilities
Mar 4, 2024 Claude 3 Haiku model card 33.3 GPQA (Diamond), 0-shot CoT, mean of 10 rollouts. 5-shot CoT 36.4, Maj@32 5-shot CoT 40.1 (Table 1, Table 8) Capabilities

The lab's number comes out ahead in 94 of 123 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. 6 of them match, which usually means one side copied the other. Every benchmark.

Model Lab says Board says Gap What differs
o1-preview 78.3% GPQA Diamond cons@64 50.3% Epoch AI run +28 pts The lab reports consensus across 64 responses, while Epoch averages scores from individual responses.
Magistral Small 1.2 70.1% GPQA Diamond 47.6% Epoch AI run +22 pts
Gemini 2.0 Flash Thinking Jan 2025 74.2% GPQA Diamond (Science) 57.1% Epoch AI run +17 pts
glm-4.7-flash 75.2% GPQA 60.5% Epoch AI run +15 pts
DeepSeek-R1-Distill-Qwen-14B 59.1% GPQA Diamond pass@1, DeepSeek-R1-Distill-Qwen-14B (Table 15) 44.7% Epoch AI run +14 pts
GPT-5.6 Terra 92.9% GPQA Diamond 79.3% Leaderboard +14 pts
Magistral Small 1.0 68.2% GPQA, SFT + RL (Magistral Small) column (Table 3) 56.1% Epoch AI run +12 pts
GPT-5.6 Luna 92.3% GPQA Diamond 80.8% Leaderboard +11 pts
gpt-oss-20b 71.5% GPQA Diamond (without tools) 60.8% Epoch AI run, medium +11 pts OpenAI reports its evaluation at high reasoning effort without tools. The paired Epoch score uses medium reasoning effort.
Claude 3.5 Sonnet (October 2024) 65% GPQA (Diamond) (0-shot CoT) 55.3% Epoch AI run +9.7 pts
DeepSeek-R1-Distill-Llama-70B 65.2% GPQA Diamond pass@1, DeepSeek-R1-Distill-Llama-70B (Table 15) 55.7% Epoch AI run +9.5 pts
Grok 3 84.6% GPQA (Graduate-Level Google-Proof Q&A (Diamond)) (cons@64; pass@1 = 80.2) 75.8% Epoch AI run +8.8 pts
DeepSeek-V3 Mar 2025 59.1% GPQA Diamond 59.1 (the original DeepSeek-V3 card. 68.4 is DeepSeek-V3-0324) 67.6% Epoch AI run −8.5 pts
Llama 3-8B 34.2% GPQA (0-shot), subset not stated, instruction tuned (Instruction tuned models table) 26.1% Epoch AI run +8.1 pts
Grok-3 mini 84% GPQA (cons@64; pass@1 = 80.3) [Grok 3 mini Think] 76.3% Epoch AI run, low +7.7 pts
Gemma 3 4B 30.8% GPQA Diamond, IT, zero-shot (Table 6) 23.2% Epoch AI run +7.6 pts
GPT-5 mini 82.3% GPQA diamond (no tools) 75% Epoch AI run, high +7.3 pts
Claude Opus 4 83.3% Graduate-level reasoning GPQA Diamond (parallel test-time compute) 76.3% Epoch AI run, 16K +7.0 pts
granite-4.0-1b 29.9% GPQA (0-shot, CoT; subset not stated) 24% Epoch AI run +5.9 pts
Llama 3.1-8B 32.8% GPQA (0-shot, CoT), subset not stated, post-trained (Table 2) 27% Epoch AI run +5.8 pts
Llama 4 Scout 57.2% GPQA Diamond 51.8% Epoch AI run +5.4 pts
Claude 3.5 Sonnet 59.4% GPQA (Diamond), 0-shot CoT. Maj@32 5-shot CoT 67.2 (Table 1) 54% Epoch AI run, Jun 2024 +5.4 pts
Gemma 3 27B 42.4% GPQA Diamond 0-shot (IT); PT GPQA 5-shot = 24.3 47.7% Epoch AI run −5.3 pts
Qwen3-8B 62% GPQA-Diamond, thinking mode (Table 17). Non-thinking 39.3 (Table 18) 56.8% Epoch AI run +5.2 pts
Gemini 3.1 Flash-Lite 86.9% GPQA Diamond (No tools) 81.8% Epoch AI run, high +5.1 pts
Claude 3.7 Sonnet 84.8% Graduate-level reasoning GPQA Diamond (64K extended thinking, parallel test-time compute) 79.7% Epoch AI run, 64k thinking +5.1 pts
GPT-4o May 2024 53.6% GPQA (0-shot) 48.9% Epoch AI run +4.7 pts
DeepSeek-R1 May 2025 81% GPQA-Diamond (Pass@1) 76.3% Epoch AI run +4.7 pts
Claude Sonnet 4 83.8% Graduate-level reasoning GPQA Diamond (parallel test-time compute) 79.2% Epoch AI run, 59K +4.6 pts
gpt-oss-120b 80.1% GPQA Diamond (without tools) 75.8% Epoch AI run, high +4.3 pts
GPT-5.4 Nano 82.8% GPQA Diamond 78.5% Epoch AI run, high +4.3 pts
Qwen3-30B-A3B 65.8% GPQA-Diamond, thinking mode (Table 15). Non-thinking 54.8 (Table 16) 61.7% Epoch AI run +4.1 pts
Claude Opus 4.7 94.2% Graduate-level reasoning GPQA Diamond 90.2% Epoch AI run, xhigh +4.0 pts
Gemini 2.0 Flash Feb 2025 60.1% GPQA (diamond) 64.1% Epoch AI run −4.0 pts
GLM-5.1 86.2% GPQA-Diamond 89.9% Epoch AI run −3.7 pts
Claude Opus 4.1 80.9% Graduate-level reasoning GPQA Diamond 77.3% Epoch AI run, 16K +3.6 pts
Qwen3-4B 55.9% GPQA-Diamond, thinking mode (Table 17). Non-thinking 41.7 (Table 18) 52.3% Epoch AI run +3.6 pts
Claude 3.5 Haiku 41.6% GPQA (Diamond), 0-shot CoT (Table 8) 38.1% Epoch AI run, Oct 2024 +3.5 pts
Qwen2.5-32B 49.5% GPQA, variant not stated, Qwen2.5-32B-Instruct (Table 7) 46.1% Epoch AI run +3.4 pts
Claude 3 Opus 50.4% GPQA (Diamond), 0-shot CoT, mean of 10 rollouts. 5-shot CoT 53.3, Maj@32 5-shot CoT 59.5 (Table 1, Table 8) 47.2% Epoch AI run +3.2 pts
GPT-5 89.4% GPQA Diamond, GPT-5 pro (python) 86.2% Epoch AI run, high +3.2 pts
GPT-5.5 Instant 85.6% GPQA (PhD-Level Science) 82.5% Epoch AI run +3.1 pts
Claude 3 Haiku 33.3% GPQA (Diamond), 0-shot CoT, mean of 10 rollouts. 5-shot CoT 36.4, Maj@32 5-shot CoT 40.1 (Table 1, Table 8) 36.3% Epoch AI run −3.0 pts
Mistral Small 3.2 46.1% GPQA Diamond (5-shot CoT) 49% Epoch AI run −2.9 pts
Llama 4 Maverick 69.8% GPQA Diamond 67% Epoch AI run, FP8 +2.8 pts
Qwen3.5-9B 81.7% GPQA Diamond 79% Epoch AI run +2.7 pts
GPT-4.5 71.4% GPQA (science) 68.7% Epoch AI run +2.7 pts
GPT-4 Turbo Apr 2024 49.3% GPQA% 46.6% Epoch AI run +2.7 pts
o3-mini 79.7% PhD-level Science Questions (GPQA Diamond) 77% Epoch AI run, high +2.7 pts
Qwen3-32B 68.4% GPQA-Diamond, thinking mode (Table 13). Non-thinking 54.6 (Table 14) 65.7% Epoch AI run +2.7 pts
DeepSeek-V3 59.1% GPQA-Diamond (Pass@1) 56.5% Epoch AI run +2.6 pts
Claude Opus 4.8 93.6% GPQA Diamond 91% Epoch AI run, max +2.6 pts
Claude Sonnet 4.6 89.9% Graduate-level reasoning GPQA Diamond 87.4% Epoch AI run, 32k thinking +2.5 pts
Llama 3.1-70B 46.7% GPQA, 0-shot, em, subset not stated, instruction tuned (Instruction tuned models table) 44.2% Epoch AI run +2.5 pts
GPT-4o mini 40.2% GPQA 37.7% Epoch AI run +2.5 pts
Mistral Medium 3 57.1% GPQA Diamond 5-shot CoT 59.5% Epoch AI run −2.4 pts
Qwen3.7-Plus 90.3% GPQA Diamond 87.9% Epoch AI run +2.4 pts
GLM-4.7 85.7% GPQA-Diamond 83.3% Epoch AI run +2.4 pts
Qwen3-1.7B 40.1% GPQA-Diamond, thinking mode (Table 19). Non-thinking 28.6 (Table 20) 38% Epoch AI run +2.1 pts
Qwen3.5 397B-A17B 88.4% GPQA 86.4% Epoch AI run, none +2.0 pts
DeepSeek-R1-Distill-Qwen-32B 62.1% GPQA Diamond pass@1, DeepSeek-R1-Distill-Qwen-32B (Table 15) 64.1% Epoch AI run −2.0 pts
Qwen 3.6 Plus 90.4% GPQA 88.4% Epoch AI run, 2026-04-02 +2.0 pts
Mistral Small 3 45.3% gpqa_main_cot_5shot_instruct 47.3% Epoch AI run −2.0 pts
Qwen3.6 27B 87.8% GPQA Diamond 85.9% Epoch AI run +1.9 pts
GLM-5 86% GPQA-Diamond 87.8% Epoch AI run −1.8 pts
o4-mini 81.4% GPQA Diamond (no tools) 79.6% Epoch AI run, high +1.8 pts
Claude Haiku 4.5 73% Graduate-level reasoning GPQA Diamond 71.2% Epoch AI run, 32K +1.8 pts
GPT-5 nano 71.2% GPQA diamond (no tools) 69.4% Epoch AI run, high +1.8 pts
Nemotron 3 Ultra 87% GPQA (no tools) 85.3% Epoch AI run +1.7 pts
Qwen2-72B 42.4% GPQA 40.8% Epoch AI run +1.6 pts
Mistral Small 3.1 46% GPQA Diamond (5-shot CoT) 47.5% Epoch AI run −1.5 pts
Qwen3.7-Max 92.4% GPQA Diamond 90.9% Epoch AI run +1.5 pts
o3 83.3% GPQA Diamond PhD-Level Science Questions, o3 (no tools) 81.8% Epoch AI run, high +1.5 pts
Gemma 4 31B IT 84.3% GPQA Diamond 82.8% Leaderboard +1.5 pts
Gemma 3 12B 40.9% GPQA Diamond, IT, zero-shot (Table 6) 39.5% Epoch AI run +1.4 pts
GPT-4.1 nano 50.3% GPQA Diamond (model-extracted answers) 48.9% Epoch AI run +1.4 pts
Qwen 3.6 35B-A3B 86% GPQA 84.8% Epoch AI run, none +1.2 pts
GPT-5.4 Mini 88% GPQA Diamond 86.9% Epoch AI run, xhigh +1.1 pts
Gemini 2.5 Pro Jun 2025 86.4% GPQA diamond, single attempt (pass@1) 85.3% Epoch AI run +1.1 pts
GPT-5.6 Sol 94.6% GPQA Diamond 93.5% Epoch AI run, max +1.1 pts
Claude Sonnet 4.5 83.4% Graduate-level reasoning GPQA Diamond 82.3% Epoch AI run, 59k thinking +1.1 pts
o1 75.7% GPQA diamond 76.8% Epoch AI run, high −1.1 pts
Llama 3-70B 39.5% GPQA (0-shot) [instruct] 40.6% Epoch AI run −1.1 pts
Inkling 87.2% GPQA Diamond (Artificial Analysis) 88.3% Epoch AI run, xhigh −1.1 pts
DeepSeek V4.1 Flash 90.9% GPQA Diamond (Pass@1) 89.8% Epoch AI run, max +1.1 pts
Qwen3-235B-A22B-Thinking Jul 2025 81.1% GPQA 80% Epoch AI run +1.0 pts
GPT-6 Astra 96% GPQA Diamond 95% Leaderboard +1.0 pts
DeepSeek-V3.2 82.4% GPQA Diamond (Pass@1) 83.4% Epoch AI run, Thinking −1.0 pts
Gemini 3 Flash 90.4% GPQA Diamond (No tools) 89.4% Epoch AI run, high +1.0 pts
GPT-5.2 92.4% GPQA Diamond (no tools) Science questions 91.4% Epoch AI run, xhigh +1.0 pts
Inkling-Small 89.5% GPQA Diamond 88.5% Epoch AI run, xhigh +1.0 pts
Gemini 2.0 Pro 64.7% GPQA (diamond) 65.7% Epoch AI run −1.0 pts
Claude Opus 4.5 87% Graduate-level reasoning GPQA Diamond 86% Epoch AI run, 32k thinking +1.0 pts
Gemma 4 26B A4B 82.3% GPQA Diamond 83.2% Leaderboard −0.9 pts
Qwen2.5-7B 36.4% GPQA, variant not stated, Qwen2.5-7B-Instruct (Table 8) 35.5% Epoch AI run +0.9 pts
GPT-4.1 mini 65% GPQA Diamond (model-extracted answers) 65.8% Epoch AI run −0.8 pts
DeepSeek-V4-Pro 90.1% GPQA Diamond (Pass@1) 90.9% Epoch AI run, high −0.8 pts
Claude Opus 4.6 91.3% Graduate-level reasoning GPQA Diamond 90.5% Epoch AI run, 32k thinking +0.8 pts
Gemma 3 1B 19.2% GPQA Diamond, IT, zero-shot (Table 6) 19.9% Epoch AI run −0.8 pts
Qwen3.5-35B-A3B 84.2% GPQA Diamond 83.5% Epoch AI run +0.7 pts
Gemini 3 Pro 91.9% GPQA Diamond (No tools) 92.6% Epoch AI run −0.7 pts
GLM-5.2 91.2% GPQA-Diamond 91.9% Epoch AI run, max −0.7 pts
Qwen-Turbo 42.3% GPQA, variant not stated, Qwen2.5-Turbo (Table 7) 41.8% Epoch AI run +0.5 pts
Grok 4 87.5% GPQA (Science), no tools 87% Epoch AI run +0.5 pts
GPT-5.4 92.8% GPQA Diamond (GPT-5.4) 93.3% Epoch AI run, xhigh −0.5 pts
GPT-5.1 88.1% GPQA Diamond (no tools) 87.6% Epoch AI run, high +0.5 pts
Muse Spark Open 89% GPQA Diamond 88.6% Epoch AI run, xhigh +0.4 pts
GPT-5.5 93.6% GPQA Diamond 94% Epoch AI run, xhigh −0.4 pts
Qwen3-235B-A22B 71.1% GPQA-Diamond 70.7% Epoch AI run +0.4 pts
Kimi K3 93.5% GPQA Diamond 93.1% Epoch AI run, max +0.4 pts
Gemini 3.1 Pro 94.3% GPQA Diamond (No tools) 93.9% Leaderboard +0.4 pts
Gemini 1.5 Pro May 2024 46.2% GPQA, 0-shot 45.9% Epoch AI run +0.3 pts
Muse Spark 89.5% GPQA Diamond (PhD Level Reasoning) 89.8% Epoch AI run −0.3 pts
Kimi K2 Thinking 84.5% GPQA, no tools 84.2% Epoch AI run +0.3 pts
Kimi K2.6 90.5% GPQA-Diamond 90.8% Epoch AI run −0.3 pts
Qwen3-14B 64% GPQA-Diamond, thinking mode (Table 15). Non-thinking 54.8 (Table 16) 63.8% Epoch AI run +0.2 pts
DeepSeek-R1 71.5% GPQA-Diamond (Pass@1) 71.7% Epoch AI run −0.2 pts
DeepSeek-R1-Distill-Qwen-1.5B 33.8% GPQA Diamond pass@1, DeepSeek-R1-Distill-Qwen-1.5B (Table 15) 33.6% Epoch AI run +0.2 pts
GPT-5.4 Pro 94.4% GPQA Diamond 94.6% Epoch AI run, xhigh −0.2 pts
Claude 3 Sonnet 40.4% GPQA (Diamond), 0-shot CoT, mean of 10 rollouts. 5-shot CoT 42.9, Maj@32 5-shot CoT 46.3 (Table 1, Table 8) 40.6% Epoch AI run −0.2 pts
Llama 3.1-405B 51.1% GPQA (0-shot, CoT) 50.9% Epoch AI run +0.2 pts
Gemini 2.5 Pro Mar 2025 84% GPQA diamond, single attempt (pass@1) 83.8% Epoch AI run +0.2 pts
GPT-6.2 Astra 97% GPQA Diamond (no tools), accuracy (Table 2, 2.1.1.1.1) 96.8% Epoch AI run, max +0.2 pts
Qwen2.5-72B 49% GPQA 49.1% Epoch AI run Same
seed-oss-36b-instruct 71.4% GPQA-D 71.5% Epoch AI run Same
Qwen 3.8 Max 92.6% GPQA Diamond 92.7% Epoch AI run, xhigh Same
Phi-4 56.1% GPQA (simple-evals) 56.1% Epoch AI run Same
Kimi K3.1 Pro 94.2% GPQA-Diamond 94.2% Epoch AI run, Together, max Same
Kimi K2.5 87.6% GPQA-Diamond 87.6% Epoch AI run, Fireworks Same

More in Science and reasoning

All 203 in Science and reasoning
  • Terminal-Bench-Science In use 70 scientific research-workflow tasks across five science areas, run in Harbor containers. Hidden tests give the resolution rate. GPT-6 Astra 68.1%
  • BioMysteryBench In use Bioinformatics problems on anonymized real datasets that require real analysis with tools. Rubric-graded, with human-solvable and human-difficult splits. Claude Fable 5.2 83.7%
  • FrontierScience In use Models solve physics, chemistry, and biology problems in an Olympiad track graded by short answer and a Research track graded by 10-point rubrics. Intern-S2-397B 87%
  • HiPhO In use Models solve theory problems from 2024 and 2025 physics olympiad exams, some with diagrams. Official marking schemes grade answers and steps, mapped to medal levels. Gemini 3 Pro 78.3%
  • LABBench2 In use 11 biology research sub-tasks (literature, figures, tables, patents, trials and more) with tool access. Macro-averaged accuracy. GPT-5.2 60.9%
  • CritPt v2 In use Models solve unpublished research-level physics challenges written by working physicists, with answers graded automatically. The v2 release revised the public test challenges. GPT-6 Astra 83.1%

Data audit

10 of 11 checks pass, 1 warning. Look first at the Lab claims check. 7 of 129 pairs differ by more than 10 points, the largest for Magistral Small 1.2 (+22 pts). Every benchmark

Catalog record 2 pass
  • Pass Task access All tasks are public.
  • Pass Confidence Checked against a primary source.
Scores 4 pass 1 note
  • Pass Independent runs Scores from the official leaderboard (20 entries), Epoch AI’s runs (231 models), launch posts (254 scores) and system cards (168 scores).
  • Pass Models scored 408 models we track.
  • Pass Newest score The newest is from November 2026, for Inkling 2 Mini.
  • Pass Frontier models 9 of the top 10 have a score, led by GPT-6.2 Astra (#1).
  • Note Headroom Saturated. The best is 97%, past 85% since June 2025.
Leaderboard import 3 pass
  • Pass Importer We read the board on kaggle.com: 20 rows for models we track at the last read.
  • Pass Last read November 20th, 2026.
  • Pass Read worked The last read worked.
Consistency 1 warning 1 pass
  • Warning Lab claims 7 of 129 pairs differ by more than 10 points, the largest for Magistral Small 1.2 (+22 pts).
  • Pass Known issues No published audit found problems.

How we check