Benchmark Almanac

OTIS Mock AIME 2024-2025

GPT-5.5 100% leads since Apr 2026 Not in model cards

Models solve 45 problems from three OTIS Mock AIME exams written by students of the OTIS program. Integer answers are scored by exact match.

Epoch AI added it as a harder successor to MATH Level 5, which was nearing saturation.

Made by Epoch AI (problems by OTIS students) Released Dec 2024 Competition problems with answers All tasks public Last model added Oct 2026 Scores refreshed 31 Oct 2026
Level
Competition The strongest students, in olympiad-style contests
Scored
Checked automatically A program checks the result against an answer key, unit tests or the expected final state.
Answers
Short answer A number, word or short string matched to a key.
Leaderboard web.evanchen.cc
202
Models scored in Epoch AI data

13 models share the top score of 100%

Best score per model in Epoch AI’s data. Where a model ran with several settings or harnesses, we keep its best.

202 models. Scroll sideways for the rest.

  1. 100.0 GPT-5.5
  2. 100.0 GPT-5.5 Pro
  3. 100.0 Claude Fable 5
  4. 100.0 GPT-5.6 Sol
  5. 100.0 Claude Fable 5.1
  6. 100.0 Qwen3.8 Max (0902)
  7. 100.0 GPT-6 Astra
  8. 100.0 Claude Opus 5.5
  9. 100.0 GPT-6 Sol
  10. 100.0 Claude Sonnet 5.5
  11. 100.0 GPT-6.1 Sol
  12. 100.0 Gemini 4 Argon
  13. 100.0 GPT-6.1 Terra
  14. 99.7 GPT-5.6 Terra
  15. 99.4 Qwen 3.8 Max
  16. 99.4 Muse Wonder
  17. 99.4 DeepSeek V4.1 Flash 1017
  18. 99.2 Grok 4.6
  19. 99.2 Muse Spark 1.3
  20. 98.9 Claude Opus 5
  21. 98.9 Gemini 3.8 Flash
  22. 98.9 GPT-6 Luna
  23. 98.9 Claude Haiku 5.5
  24. 98.6 DeepSeek V4 Pro 0813
  25. 98.3 Claude Opus 4.8
  26. 98.3 GPT-5.6 Luna
  27. 98.3 DeepSeek V4.1 Flash
  28. 98.3 Mistral Large 4
  29. 98.1 Grok 4.7
  30. 98.1 Muse Spark Open
  31. 97.8 Claude Opus 4.7
  32. 97.8 GPT-5.4
  33. 97.8 Grok 4.5
  34. 97.2 Kimi K3
  35. 97.2 Gemini 3.7 Flash
  36. 96.7 DeepSeek-V4-Pro
  37. 96.1 GPT-5.2
  38. 96.1 Kimi K2.6
  39. 95.6 Gemini 3.1 Pro
  40. 95.6 Gemini 3 Flash
  41. 95.6 Gemini 3.5 Flash
  42. 95.6 Qwen3.7-Max
  43. 95.6 Kimi K2.7 Code
  44. 94.7 Claude Sonnet 5
  45. 94.4 Claude Opus 4.6
  46. 94.4 DeepSeek V4 Flash 0731
  47. 94.2 Gemini 3.6 Flash
  48. 93.9 GLM-5.3-Flash
  49. 93.3 Qwen 3.6 Plus
  50. 93.3 GLM-5.1
  51. 93.3 Grok 4.3 Beta
  52. 93.3 Qwen3.7-Plus
  53. 92.2 Grok 4.20
  54. 92.2 Kimi K2.5
  55. 91.4 GPT-5
  56. 91.4 Gemini 3 Pro
  57. 91.1 Qwen 3.6 Max (Preview)
  58. 91.1 Qwen3.6 27B
  59. 91.1 GLM-5.3
  60. 90.0 Inkling-Small
  61. 88.9 Muse Spark
  62. 88.9 gpt-oss-120b
  63. 88.9 Qwen3.5 397B-A17B
  64. 88.9 GPT-5.4 Mini
  65. 88.9 Inkling
  66. 88.6 GPT-5.1
  67. 87.8 DeepSeek-V3.2
  68. 87.8 GPT-5.4 Nano
  69. 86.7 Qwen3-235B-A22B-Thinking
  70. 86.7 GPT-5 mini
  71. 86.7 Qwen 3.5 Plus (hosted 397B-A17B)
  72. 86.7 Qwen 3.6 35B-A3B
  73. 86.7 Nemotron 3 Ultra
  74. 86.7 Qwen3.7 Flash
  75. 86.4 GLM-5.2
  76. 86.1 Claude Opus 4.5
  77. 85.8 Claude Sonnet 4.6
  78. 84.7 Gemini 2.5 Pro
  79. 84.4 o3
  80. 84.4 Qwen 3.5 Flash (hosted 35B-A3B)
  81. 84.4 Qwen 3.6 Flash
  82. 84.0 Grok 4
  83. 83.3 GLM-4.7
  84. 83.1 Kimi K2 Thinking
  85. 82.2 Gemma 4 26B A4B
  86. 81.7 o4-mini
  87. 81.1 GPT-5 nano
  88. 80.0 GLM-5
  89. 80.0 Gemini 3.1 Flash-Lite
  90. 77.8 Grok-3 mini
  91. 77.8 Claude Sonnet 4.5
  92. 76.9 o3-mini
  93. 73.3 o1
  94. 73.3 Qwen3-Max
  95. 73.3 Gemma 4 31B IT
  96. 73.1 Gemini 2.5 Flash
  97. 71.1 Claude Sonnet 4
  98. 71.1 MiniMax-M3
  99. 71.1 Gemini 3.5 Flash-Lite
  100. 70.8 Gemini 2.5 Flash
  101. 70.3 Qwen3-30B-A3B-Thinking
  102. 70.0 Qwen3.5-35B-A3B
  103. 68.9 Claude Opus 4.1
  104. 68.1 GPT-5.5 Instant
  105. 67.5 seed-oss-36b-instruct
  106. 66.9 Qwen3-32B
  107. 66.7 Claude Haiku 4.5
  108. 66.4 Qwen3-14B
  109. 66.4 DeepSeek-R1
  110. 65.3 gpt-oss-20b
  111. 64.4 Claude Opus 4
  112. 62.8 Qwen3-30B-A3B
  113. 62.2 Qwen3-30B-A3B-Instruct
  114. 61.7 Qwen3.5-9B
  115. 59.2 QwQ-32B
  116. 58.3 glm-4.7-flash
  117. 57.8 Gemini 2.0 Flash Thinking
  118. 57.8 Claude 3.7 Sonnet
  119. 56.1 Qwen3-8B
  120. 55.8 Qwen3.5-4B
  121. 55.6 DeepSeek-R1-Distill-Qwen-32B
  122. 55.6 Grok 3
  123. 53.3 DeepSeek-R1
  124. 52.2 qwen3-4b-instruct-2507
  125. 51.4 DeepSeek-R1-Distill-Llama-70B
  126. 50.6 DeepSeek-R1-Distill-Qwen-14B
  127. 46.9 o1-mini
  128. 44.7 GPT-4.1 mini
  129. 43.9 deepseek-r1-0528-qwen3-8b
  130. 38.3 GPT-4.1
  131. 37.8 GPT-4.5
  132. 37.8 DeepSeek-V3
  133. 32.2 Mistral Medium 3
  134. 31.1 o1-preview
  135. 31.1 Gemini 2.0 Flash
  136. 30.3 Mistral Small 3.2
  137. 30.0 Magistral Small 1.0
  138. 28.9 GPT-4.1 nano
  139. 28.1 Magistral Small 1.2
  140. 25.0 glm-4.7-flash_none
  141. 23.1 Gemini 1.5 Pro
  142. 22.5 Gemma 3 27B
  143. 21.4 DeepSeek-R1-Distill-Qwen-1.5B
  144. 20.6 Llama 4 Maverick
  145. 17.8 Qwen Plus
  146. 16.7 Gemma 3 12B
  147. 16.3 Gemini 1.5 Flash
  148. 16.1 Qwen2.5-Max
  149. 15.8 DeepSeek-V3
  150. 13.8 Phi-4
  151. 11.5 Grok-2
  152. 9.72 Llama 3.1-405B
  153. 8.47 Mistral Large 2
  154. 8.47 Claude 3.5 Sonnet (October 2024)
  155. 8.06 Qwen2.5-72B
  156. 8.06 Qwen3-1.7B
  157. 7.78 Mistral Large 2
  158. 7.78 Llama 4 Scout
  159. 7.50 Gemma 3 4B
  160. 7.36 Qwen2.5-32B
  161. 6.94 GPT-4o mini
  162. 6.81 Gemini 1.5 Pro
  163. 6.67 GPT-4 Turbo
  164. 6.67 Mistral Small 3
  165. 6.53 Claude 3.5 Sonnet
  166. 6.39 GPT-4o
  167. 6.25 GPT-4o
  168. 6.25 GPT-4o
  169. 6.11 Qwen-Turbo
  170. 5.83 Mistral Small 3.1
  171. 5.14 Llama 3.3 70B
  172. 4.72 Claude 3 Opus
  173. 4.58 Gemini 1.5 Flash 8B
  174. 4.44 Tulu 3 (Tülu 3) 70B
  175. 4.31 Llama 3-70B
  176. 4.31 Claude 3.5 Haiku
  177. 3.89 Gemini 1.5 Flash
  178. 3.61 Llama 3.1-70B
  179. 2.78 granite-4.0-micro
  180. 2.64 Llama 3.2 90B
  181. 2.50 Claude 2
  182. 2.50 Claude 3 Sonnet
  183. 2.50 Hermes 2 Theta Llama-3 70B
  184. 2.50 Qwen2.5-7B
  185. 2.22 GPT-3.5 Turbo
  186. 1.94 Claude 2.1
  187. 1.94 Mistral Large
  188. 1.94 Llama 3-8B
  189. 1.81 Claude 3 Haiku
  190. 1.67 Llama 3.1-8B
  191. 1.39 Gemma 2 27B
  192. 1.11 GPT-4
  193. 1.11 Gemini 1.0 Pro
  194. 1.11 Gemma 3 1B
  195. 0.83 DeepSeek LLM 67B
  196. 0.83 granite-4.0-1b
  197. 0.56 GPT-4
  198. 0.56 Gemma 2 9B
  199. 0.56 Llama 3.2 1B
  200. 0.28 Mistral 7B v0.3
  201. 0.28 granite-4.0-350m
  202. 0.0 Llama 2-70B
  1. 1 GPT-5.5 xhigh 100%
  2. 2 GPT-5.5 Pro xhigh 100%
  3. 3 Claude Fable 5 high 100%
  4. 4 GPT-5.6 Sol max 100%
  5. 5 Claude Fable 5.1 max 100%
  6. 6 Qwen3.8 Max (0902) xhigh 100%
  7. 7 GPT-6 Astra max 100%
  8. 8 Claude Opus 5.5 max 100%
  9. 9 GPT-6 Sol max 100%
  10. 10 Claude Sonnet 5.5 max 100%
  11. 11 GPT-6.1 Sol max 100%
  12. 12 Gemini 4 Argon high 100%
  13. 13 GPT-6.1 Terra max 100%
  14. 14 GPT-5.6 Terra max 99.7%
  15. 15 Qwen 3.8 Max xhigh 99.4%
  16. 16 Muse Wonder max 99.4%
  17. 17 DeepSeek V4.1 Flash 1017 max 99.4%
  18. 18 Grok 4.6 xhigh 99.2%
  19. 19 Muse Spark 1.3 xhigh 99.2%
  20. 20 Claude Opus 5 max 98.9%
  21. 21 Gemini 3.8 Flash high 98.9%
  22. 22 GPT-6 Luna max 98.9%
  23. 23 Claude Haiku 5.5 xhigh 98.9%
  24. 24 DeepSeek V4 Pro 0813 max 98.6%
  25. 25 Claude Opus 4.8 max 98.3%
  26. 26 GPT-5.6 Luna max 98.3%
  27. 27 DeepSeek V4.1 Flash max 98.3%
  28. 28 Mistral Large 4 high 98.3%
  29. 29 Grok 4.7 xhigh 98.1%
  30. 30 Muse Spark Open xhigh 98.1%
  31. 31 Claude Opus 4.7 xhigh 97.8%
  32. 32 GPT-5.4 high 97.8%
  33. 33 Grok 4.5 high 97.8%
  34. 34 Kimi K3 max 97.2%
  35. 35 Gemini 3.7 Flash high 97.2%
  36. 36 DeepSeek-V4-Pro max 96.7%
  37. 37 GPT-5.2 high 96.1%
  38. 38 Kimi K2.6 96.1%
  39. 39 Gemini 3.1 Pro 95.6%
  40. 40 Gemini 3 Flash high 95.6%
  41. 41 Gemini 3.5 Flash high 95.6%
  42. 42 Qwen3.7-Max 95.6%
  43. 43 Kimi K2.7 Code 95.6%
  44. 44 Claude Sonnet 5 xhigh 94.7%
  45. 45 Claude Opus 4.6 64k thinking 94.4%
  46. 46 DeepSeek V4 Flash 0731 max 94.4%
  47. 47 Gemini 3.6 Flash high 94.2%
  48. 48 GLM-5.3-Flash max 93.9%
  49. 49 Qwen 3.6 Plus 2026-04-02 93.3%
  50. 50 GLM-5.1 93.3%
  51. 51 Grok 4.3 Beta high 93.3%
  52. 52 Qwen3.7-Plus 93.3%
  53. 53 Grok 4.20 92.2%
  54. 54 Kimi K2.5 Fireworks 92.2%
  55. 55 GPT-5 high 91.4%
  56. 56 Gemini 3 Pro 91.4%
  57. 57 Qwen 3.6 Max (Preview) 91.1%
  58. 58 Qwen3.6 27B 91.1%
  59. 59 GLM-5.3 max 91.1%
  60. 60 Inkling-Small xhigh 90%
  61. 61 Muse Spark 88.9%
  62. 62 gpt-oss-120b high 88.9%
  63. 63 Qwen3.5 397B-A17B 88.9%
  64. 64 GPT-5.4 Mini xhigh 88.9%
  65. 65 Inkling xhigh 88.9%
  66. 66 GPT-5.1 high 88.6%
  67. 67 DeepSeek-V3.2 Thinking 87.8%
  68. 68 GPT-5.4 Nano high 87.8%
  69. 69 Qwen3-235B-A22B-Thinking Jul 2025 86.7%
  70. 70 GPT-5 mini high 86.7%
  71. 71 Qwen 3.5 Plus (hosted 397B-A17B) 86.7%
  72. 72 Qwen 3.6 35B-A3B 86.7%
  73. 73 Nemotron 3 Ultra 86.7%
  74. 74 Qwen3.7 Flash 86.7%
  75. 75 GLM-5.2 max 86.4%
  76. 76 Claude Opus 4.5 32k thinking 86.1%
  77. 77 Claude Sonnet 4.6 32k thinking 85.8%
  78. 78 Gemini 2.5 Pro Jun 2025 84.7%
  79. 79 o3 medium 84.4%
  80. 80 Qwen 3.5 Flash (hosted 35B-A3B) 84.4%
  81. 81 Qwen 3.6 Flash 2026-04-16 84.4%
  82. 82 Grok 4 84%
  83. 83 GLM-4.7 83.3%
  84. 84 Kimi K2 Thinking 83.1%
  85. 85 Gemma 4 26B A4B minimal 82.2%
  86. 86 o4-mini high 81.7%
  87. 87 GPT-5 nano high 81.1%
  88. 88 GLM-5 80%
  89. 89 Gemini 3.1 Flash-Lite high 80%
  90. 90 Grok-3 mini high 77.8%
  91. 91 Claude Sonnet 4.5 59k thinking 77.8%
  92. 92 o3-mini high 76.9%
  93. 93 o1 high 73.3%
  94. 94 Qwen3-Max 73.3%
  95. 95 Gemma 4 31B IT minimal 73.3%
  96. 96 Gemini 2.5 Flash Apr 2025 73.1%
  97. 97 Claude Sonnet 4 32K 71.1%
  98. 98 MiniMax-M3 71.1%
  99. 99 Gemini 3.5 Flash-Lite high 71.1%
  100. 100 Gemini 2.5 Flash May 2025 70.8%
  101. 101 Qwen3-30B-A3B-Thinking Jul 2025 70.3%
  102. 102 Qwen3.5-35B-A3B none 70%
  103. 103 Claude Opus 4.1 27K 68.9%
  104. 104 GPT-5.5 Instant 68.1%
  105. 105 seed-oss-36b-instruct 67.5%
  106. 106 Qwen3-32B 66.9%
  107. 107 Claude Haiku 4.5 32K 66.7%
  108. 108 Qwen3-14B 66.4%
  109. 109 DeepSeek-R1 May 2025 66.4%
  110. 110 gpt-oss-20b medium 65.3%
  111. 111 Claude Opus 4 27K 64.4%
  112. 112 Qwen3-30B-A3B 62.8%
  113. 113 Qwen3-30B-A3B-Instruct Jul 2025 62.2%
  114. 114 Qwen3.5-9B none 61.7%
  115. 115 QwQ-32B 59.2%
  116. 116 glm-4.7-flash 58.3%
  117. 117 Gemini 2.0 Flash Thinking Jan 2025 57.8%
  118. 118 Claude 3.7 Sonnet 64k thinking 57.8%
  119. 119 Qwen3-8B 56.1%
  120. 120 Qwen3.5-4B none 55.8%
  121. 121 DeepSeek-R1-Distill-Qwen-32B 55.6%
  122. 122 Grok 3 55.6%
  123. 123 DeepSeek-R1 53.3%
  124. 124 qwen3-4b-instruct-2507 52.2%
  125. 125 DeepSeek-R1-Distill-Llama-70B 51.4%
  126. 126 DeepSeek-R1-Distill-Qwen-14B 50.6%
  127. 127 o1-mini high 46.9%
  128. 128 GPT-4.1 mini 44.7%
  129. 129 deepseek-r1-0528-qwen3-8b 43.9%
  130. 130 GPT-4.1 38.3%
  131. 131 GPT-4.5 37.8%
  132. 132 DeepSeek-V3 Mar 2025 37.8%
  133. 133 Mistral Medium 3 32.2%
  134. 134 o1-preview 31.1%
  135. 135 Gemini 2.0 Flash Feb 2025 31.1%
  136. 136 Mistral Small 3.2 30.3%
  137. 137 Magistral Small 1.0 30%
  138. 138 GPT-4.1 nano 28.9%
  139. 139 Magistral Small 1.2 28.1%
  140. 140 glm-4.7-flash_none none 25%
  141. 141 Gemini 1.5 Pro Sep 2024 23.1%
  142. 142 Gemma 3 27B 22.5%
  143. 143 DeepSeek-R1-Distill-Qwen-1.5B 21.4%
  144. 144 Llama 4 Maverick FP8 20.6%
  145. 145 Qwen Plus Jan 2025 17.8%
  146. 146 Gemma 3 12B 16.7%
  147. 147 Gemini 1.5 Flash Sep 2024 16.3%
  148. 148 Qwen2.5-Max 16.1%
  149. 149 DeepSeek-V3 15.8%
  150. 150 Phi-4 13.8%
  151. 151 Grok-2 Dec 2024 11.5%
  152. 152 Llama 3.1-405B 9.72%
  153. 153 Mistral Large 2 Jul 2024 8.47%
  154. 154 Claude 3.5 Sonnet (October 2024) 8.47%
  155. 155 Qwen2.5-72B 8.06%
  156. 156 Qwen3-1.7B none 8.06%
  157. 157 Mistral Large 2 Nov 2024 7.78%
  158. 158 Llama 4 Scout 7.78%
  159. 159 Gemma 3 4B 7.50%
  160. 160 Qwen2.5-32B 7.36%
  161. 161 GPT-4o mini 6.94%
  162. 162 Gemini 1.5 Pro May 2024 6.81%
  163. 163 GPT-4 Turbo Apr 2024 6.67%
  164. 164 Mistral Small 3 6.67%
  165. 165 Claude 3.5 Sonnet Jun 2024 6.53%
  166. 166 GPT-4o Aug 2024 6.39%
  167. 167 GPT-4o May 2024 6.25%
  168. 168 GPT-4o Nov 2024 6.25%
  169. 169 Qwen-Turbo 6.11%
  170. 170 Mistral Small 3.1 5.83%
  171. 171 Llama 3.3 70B 5.14%
  172. 172 Claude 3 Opus 4.72%
  173. 173 Gemini 1.5 Flash 8B 4.58%
  174. 174 Tulu 3 (Tülu 3) 70B 4.44%
  175. 175 Llama 3-70B 4.31%
  176. 176 Claude 3.5 Haiku Oct 2024 4.31%
  177. 177 Gemini 1.5 Flash May 2024 3.89%
  178. 178 Llama 3.1-70B 3.61%
  179. 179 granite-4.0-micro 2.78%
  180. 180 Llama 3.2 90B 2.64%
  181. 181 Claude 2 2.50%
  182. 182 Claude 3 Sonnet 2.50%
  183. 183 Hermes 2 Theta Llama-3 70B 2.50%
  184. 184 Qwen2.5-7B 2.50%
  185. 185 GPT-3.5 Turbo Jan 2024 2.22%
  186. 186 Claude 2.1 1.94%
  187. 187 Mistral Large 1.94%
  188. 188 Llama 3-8B 1.94%
  189. 189 Claude 3 Haiku 1.81%
  190. 190 Llama 3.1-8B 1.67%
  191. 191 Gemma 2 27B 1.39%
  192. 192 GPT-4 Jun 2023 1.11%
  193. 193 Gemini 1.0 Pro 1.11%
  194. 194 Gemma 3 1B 1.11%
  195. 195 DeepSeek LLM 67B 0.83%
  196. 196 granite-4.0-1b 0.83%
  197. 197 GPT-4 Mar 2023 0.56%
  198. 198 Gemma 2 9B 0.56%
  199. 199 Llama 3.2 1B 0.56%
  200. 200 Mistral 7B v0.3 0.28%
  201. 201 granite-4.0-350m 0.28%
  202. 202 Llama 2-70B 0%
#ModelScoreSettingDateSource
1 GPT-5.5 100% xhigh Apr 2026 Epoch AI
2 GPT-5.5 Pro 100% xhigh Apr 2026 Epoch AI
3 Claude Fable 5 100% high Jun 2026 Epoch AI
4 GPT-5.6 Sol 100% max Jul 2026 Epoch AI
5 Claude Fable 5.1 100% max Sep 2026 Epoch AI
6 Qwen3.8 Max (0902) 100% xhigh Sep 2026 Epoch AI
7 GPT-6 Astra 100% max Sep 2026 Epoch AI
8 Claude Opus 5.5 100% max Sep 2026 Epoch AI
9 GPT-6 Sol 100% max Sep 2026 Epoch AI
10 Claude Sonnet 5.5 100% max Sep 2026 Epoch AI
11 GPT-6.1 Sol 100% max Sep 2026 Epoch AI
12 Gemini 4 Argon 100% high Sep 2026 Epoch AI
13 GPT-6.1 Terra 100% max Oct 2026 Epoch AI
14 GPT-5.6 Terra 99.7% max Jul 2026 Epoch AI
15 Qwen 3.8 Max 99.4% xhigh Aug 2026 Epoch AI
16 Muse Wonder 99.4% max Oct 2026 Epoch AI
17 DeepSeek V4.1 Flash 1017 99.4% max Oct 2026 Epoch AI
18 Grok 4.6 99.2% xhigh Aug 2026 Epoch AI
19 Muse Spark 1.3 99.2% xhigh Sep 2026 Epoch AI
20 Claude Opus 5 98.9% max Jul 2026 Epoch AI
21 Gemini 3.8 Flash 98.9% high Sep 2026 Epoch AI
22 GPT-6 Luna 98.9% max Sep 2026 Epoch AI
23 Claude Haiku 5.5 98.9% xhigh Oct 2026 Epoch AI
24 DeepSeek V4 Pro 0813 98.6% max Aug 2026 Epoch AI
25 Claude Opus 4.8 98.3% max May 2026 Epoch AI
26 GPT-5.6 Luna 98.3% max Jul 2026 Epoch AI
27 DeepSeek V4.1 Flash 98.3% max Sep 2026 Epoch AI
28 Mistral Large 4 98.3% high Oct 2026 Epoch AI
29 Grok 4.7 98.1% xhigh Sep 2026 Epoch AI
30 Muse Spark Open 98.1% xhigh Oct 2026 Epoch AI
31 Claude Opus 4.7 97.8% xhigh Apr 2026 Epoch AI
32 GPT-5.4 97.8% high Mar 2026 Epoch AI
33 Grok 4.5 97.8% high Jul 2026 Epoch AI
34 Kimi K3 97.2% max Jul 2026 Epoch AI
35 Gemini 3.7 Flash 97.2% high Aug 2026 Epoch AI
36 DeepSeek-V4-Pro 96.7% max Apr 2026 Epoch AI
37 GPT-5.2 96.1% high Dec 2025 Epoch AI
38 Kimi K2.6 96.1% Apr 2026 Epoch AI
39 Gemini 3.1 Pro 95.6% Feb 2026 Epoch AI
40 Gemini 3 Flash 95.6% high Dec 2025 Epoch AI
41 Gemini 3.5 Flash 95.6% high May 2026 Epoch AI
42 Qwen3.7-Max 95.6% May 2026 Epoch AI
43 Kimi K2.7 Code 95.6% Jun 2026 Epoch AI
44 Claude Sonnet 5 94.7% xhigh Jun 2026 Epoch AI
45 Claude Opus 4.6 94.4% 64k thinking Feb 2026 Epoch AI
46 DeepSeek V4 Flash 0731 94.4% max Jul 2026 Epoch AI
47 Gemini 3.6 Flash 94.2% high Jul 2026 Epoch AI
48 GLM-5.3-Flash 93.9% max Aug 2026 Epoch AI
49 Qwen 3.6 Plus 93.3% 2026-04-02 Mar 2026 Epoch AI
50 GLM-5.1 93.3% Apr 2026 Epoch AI
51 Grok 4.3 Beta 93.3% high Apr 2026 Epoch AI
52 Qwen3.7-Plus 93.3% Jun 2026 Epoch AI
53 Grok 4.20 92.2% Feb 2026 Epoch AI
54 Kimi K2.5 92.2% Fireworks Jan 2026 Epoch AI
55 GPT-5 91.4% high Aug 2025 Epoch AI
56 Gemini 3 Pro 91.4% Nov 2025 Epoch AI
57 Qwen 3.6 Max (Preview) 91.1% Apr 2026 Epoch AI
58 Qwen3.6 27B 91.1% Apr 2026 Epoch AI
59 GLM-5.3 91.1% max Aug 2026 Epoch AI
60 Inkling-Small 90% xhigh Jul 2026 Epoch AI
61 Muse Spark 88.9% Apr 2026 Epoch AI
62 gpt-oss-120b 88.9% high Aug 2025 Epoch AI
63 Qwen3.5 397B-A17B 88.9% Feb 2026 Epoch AI
64 GPT-5.4 Mini 88.9% xhigh Mar 2026 Epoch AI
65 Inkling 88.9% xhigh Jul 2026 Epoch AI
66 GPT-5.1 88.6% high Nov 2025 Epoch AI
67 DeepSeek-V3.2 87.8% Thinking Dec 2025 Epoch AI
68 GPT-5.4 Nano 87.8% high Mar 2026 Epoch AI
69 Qwen3-235B-A22B-Thinking Jul 2025 86.7% Jul 2025 Epoch AI
70 GPT-5 mini 86.7% high Aug 2025 Epoch AI
71 Qwen 3.5 Plus (hosted 397B-A17B) 86.7% Feb 2026 Epoch AI
72 Qwen 3.6 35B-A3B 86.7% Apr 2026 Epoch AI
73 Nemotron 3 Ultra 86.7% Jun 2026 Epoch AI
74 Qwen3.7 Flash 86.7% Jul 2026 Epoch AI
75 GLM-5.2 86.4% max Jun 2026 Epoch AI
76 Claude Opus 4.5 86.1% 32k thinking Nov 2025 Epoch AI
77 Claude Sonnet 4.6 85.8% 32k thinking Feb 2026 Epoch AI
78 Gemini 2.5 Pro Jun 2025 84.7% Jun 2025 Epoch AI
79 o3 84.4% medium Apr 2025 Epoch AI
80 Qwen 3.5 Flash (hosted 35B-A3B) 84.4% Feb 2026 Epoch AI
81 Qwen 3.6 Flash 84.4% 2026-04-16 Apr 2026 Epoch AI
82 Grok 4 84% Jul 2025 Epoch AI
83 GLM-4.7 83.3% Dec 2025 Epoch AI
84 Kimi K2 Thinking 83.1% Nov 2025 Epoch AI
85 Gemma 4 26B A4B 82.2% minimal Apr 2026 Epoch AI
86 o4-mini 81.7% high Apr 2025 Epoch AI
87 GPT-5 nano 81.1% high Aug 2025 Epoch AI
88 GLM-5 80% Feb 2026 Epoch AI
89 Gemini 3.1 Flash-Lite 80% high Mar 2026 Epoch AI
90 Grok-3 mini 77.8% high Apr 2025 Epoch AI
91 Claude Sonnet 4.5 77.8% 59k thinking Sep 2025 Epoch AI
92 o3-mini 76.9% high Jan 2025 Epoch AI
93 o1 73.3% high Dec 2024 Epoch AI
94 Qwen3-Max 73.3% Sep 2025 Epoch AI
95 Gemma 4 31B IT 73.3% minimal Apr 2026 Epoch AI
96 Gemini 2.5 Flash Apr 2025 73.1% Apr 2025 Epoch AI
97 Claude Sonnet 4 71.1% 32K May 2025 Epoch AI
98 MiniMax-M3 71.1% Jun 2026 Epoch AI
99 Gemini 3.5 Flash-Lite 71.1% high Jul 2026 Epoch AI
100 Gemini 2.5 Flash May 2025 70.8% May 2025 Epoch AI
101 Qwen3-30B-A3B-Thinking Jul 2025 70.3% Jul 2025 Epoch AI
102 Qwen3.5-35B-A3B 70% none Feb 2026 Epoch AI
103 Claude Opus 4.1 68.9% 27K Aug 2025 Epoch AI
104 GPT-5.5 Instant 68.1% May 2026 Epoch AI
105 seed-oss-36b-instruct 67.5% Aug 2025 Epoch AI
106 Qwen3-32B 66.9% Apr 2025 Epoch AI
107 Claude Haiku 4.5 66.7% 32K Oct 2025 Epoch AI
108 Qwen3-14B 66.4% Apr 2025 Epoch AI
109 DeepSeek-R1 May 2025 66.4% May 2025 Epoch AI
110 gpt-oss-20b 65.3% medium Aug 2025 Epoch AI
111 Claude Opus 4 64.4% 27K May 2025 Epoch AI
112 Qwen3-30B-A3B 62.8% Apr 2025 Epoch AI
113 Qwen3-30B-A3B-Instruct Jul 2025 62.2% Jul 2025 Epoch AI
114 Qwen3.5-9B 61.7% none Feb 2026 Epoch AI
115 QwQ-32B 59.2% Mar 2025 Epoch AI
116 glm-4.7-flash 58.3% Jan 2026 Epoch AI
117 Gemini 2.0 Flash Thinking Jan 2025 57.8% Jan 2025 Epoch AI
118 Claude 3.7 Sonnet 57.8% 64k thinking Feb 2025 Epoch AI
119 Qwen3-8B 56.1% Apr 2025 Epoch AI
120 Qwen3.5-4B 55.8% none Feb 2026 Epoch AI
121 DeepSeek-R1-Distill-Qwen-32B 55.6% Jan 2025 Epoch AI
122 Grok 3 55.6% Apr 2025 Epoch AI
123 DeepSeek-R1 53.3% Jan 2025 Epoch AI
124 qwen3-4b-instruct-2507 52.2% Aug 2025 Epoch AI
125 DeepSeek-R1-Distill-Llama-70B 51.4% Jan 2025 Epoch AI
126 DeepSeek-R1-Distill-Qwen-14B 50.6% Jan 2025 Epoch AI
127 o1-mini 46.9% high Sep 2024 Epoch AI
128 GPT-4.1 mini 44.7% Apr 2025 Epoch AI
129 deepseek-r1-0528-qwen3-8b 43.9% May 2025 Epoch AI
130 GPT-4.1 38.3% Apr 2025 Epoch AI
131 GPT-4.5 37.8% Feb 2025 Epoch AI
132 DeepSeek-V3 Mar 2025 37.8% Mar 2025 Epoch AI
133 Mistral Medium 3 32.2% May 2025 Epoch AI
134 o1-preview 31.1% Sep 2024 Epoch AI
135 Gemini 2.0 Flash Feb 2025 31.1% Feb 2025 Epoch AI
136 Mistral Small 3.2 30.3% Jun 2025 Epoch AI
137 Magistral Small 1.0 30% Jun 2025 Epoch AI
138 GPT-4.1 nano 28.9% Apr 2025 Epoch AI
139 Magistral Small 1.2 28.1% Sep 2025 Epoch AI
140 glm-4.7-flash_none 25% none Epoch AI
141 Gemini 1.5 Pro Sep 2024 23.1% Sep 2024 Epoch AI
142 Gemma 3 27B 22.5% Mar 2025 Epoch AI
143 DeepSeek-R1-Distill-Qwen-1.5B 21.4% Jan 2025 Epoch AI
144 Llama 4 Maverick 20.6% FP8 Apr 2025 Epoch AI
145 Qwen Plus Jan 2025 17.8% Jan 2025 Epoch AI
146 Gemma 3 12B 16.7% Mar 2025 Epoch AI
147 Gemini 1.5 Flash Sep 2024 16.3% Sep 2024 Epoch AI
148 Qwen2.5-Max 16.1% Jan 2025 Epoch AI
149 DeepSeek-V3 15.8% Dec 2024 Epoch AI
150 Phi-4 13.8% Dec 2024 Epoch AI
151 Grok-2 Dec 2024 11.5% Dec 2024 Epoch AI
152 Llama 3.1-405B 9.72% Jul 2024 Epoch AI
153 Mistral Large 2 Jul 2024 8.47% Jul 2024 Epoch AI
154 Claude 3.5 Sonnet (October 2024) 8.47% Oct 2024 Epoch AI
155 Qwen2.5-72B 8.06% Sep 2024 Epoch AI
156 Qwen3-1.7B 8.06% none Apr 2025 Epoch AI
157 Mistral Large 2 Nov 2024 7.78% Nov 2024 Epoch AI
158 Llama 4 Scout 7.78% Apr 2025 Epoch AI
159 Gemma 3 4B 7.50% Mar 2025 Epoch AI
160 Qwen2.5-32B 7.36% Sep 2024 Epoch AI
161 GPT-4o mini 6.94% Jul 2024 Epoch AI
162 Gemini 1.5 Pro May 2024 6.81% May 2024 Epoch AI
163 GPT-4 Turbo Apr 2024 6.67% Apr 2024 Epoch AI
164 Mistral Small 3 6.67% Jan 2025 Epoch AI
165 Claude 3.5 Sonnet 6.53% Jun 2024 Jun 2024 Epoch AI
166 GPT-4o Aug 2024 6.39% Aug 2024 Epoch AI
167 GPT-4o May 2024 6.25% May 2024 Epoch AI
168 GPT-4o Nov 2024 6.25% Nov 2024 Epoch AI
169 Qwen-Turbo 6.11% Nov 2024 Epoch AI
170 Mistral Small 3.1 5.83% Mar 2025 Epoch AI
171 Llama 3.3 70B 5.14% Dec 2024 Epoch AI
172 Claude 3 Opus 4.72% Feb 2024 Epoch AI
173 Gemini 1.5 Flash 8B 4.58% Oct 2024 Epoch AI
174 Tulu 3 (Tülu 3) 70B 4.44% Nov 2024 Epoch AI
175 Llama 3-70B 4.31% Apr 2024 Epoch AI
176 Claude 3.5 Haiku 4.31% Oct 2024 Oct 2024 Epoch AI
177 Gemini 1.5 Flash May 2024 3.89% May 2024 Epoch AI
178 Llama 3.1-70B 3.61% Jul 2024 Epoch AI
179 granite-4.0-micro 2.78% Oct 2025 Epoch AI
180 Llama 3.2 90B 2.64% Sep 2024 Epoch AI
181 Claude 2 2.50% Jul 2023 Epoch AI
182 Claude 3 Sonnet 2.50% Feb 2024 Epoch AI
183 Hermes 2 Theta Llama-3 70B 2.50% Jun 2024 Epoch AI
184 Qwen2.5-7B 2.50% Sep 2024 Epoch AI
185 GPT-3.5 Turbo Jan 2024 2.22% Jan 2024 Epoch AI
186 Claude 2.1 1.94% Nov 2023 Epoch AI
187 Mistral Large 1.94% Feb 2024 Epoch AI
188 Llama 3-8B 1.94% Apr 2024 Epoch AI
189 Claude 3 Haiku 1.81% Mar 2024 Epoch AI
190 Llama 3.1-8B 1.67% Jul 2024 Epoch AI
191 Gemma 2 27B 1.39% Jun 2024 Epoch AI
192 GPT-4 Jun 2023 1.11% Jun 2023 Epoch AI
193 Gemini 1.0 Pro 1.11% Dec 2023 Epoch AI
194 Gemma 3 1B 1.11% Mar 2025 Epoch AI
195 DeepSeek LLM 67B 0.83% Nov 2023 Epoch AI
196 granite-4.0-1b 0.83% Oct 2025 Epoch AI
197 GPT-4 Mar 2023 0.56% Mar 2023 Epoch AI
198 Gemma 2 9B 0.56% Jun 2024 Epoch AI
199 Llama 3.2 1B 0.56% Sep 2024 Epoch AI
200 Mistral 7B v0.3 0.28% May 2024 Epoch AI
201 granite-4.0-350m 0.28% Oct 2025 Epoch AI
202 Llama 2-70B 0% Jul 2023 Epoch AI

13 models have held number one since its release in Dec 2024

Lab claims count from the day the card came out, independent runs from the model’s release.

OpenAI xAI Google DeepMind Qwen Anthropic
Epoch AI runs Passed 85% in Jul 2025, by Qwen3-235B-A22B-Thinking
GPT-5.5 100%

The best score passed 85% in Jul 2025

All the scores we have, one dot each, so a model tested at several settings appears more than once.

Run or collected by Epoch AI Best so far
0% 20% 40% 60% 80% 100% 2023 2024 2025 2026 2027 Near the ceiling (85%) Random guessing GPT-5.5 GPT-5 Qwen3-235B-A22B-Thinking Grok-3 mini o1 o1-mini Llama 3.1-405B 0% 20% 40% 60% 80% 100% 2023 2024 2025 2026 2027 Near the ceiling (85%) Random guessing GPT-5.5 GPT-5

No lab model card reports it yet

We read the headline results of 479 launch posts from 51 labs, and none of them list this benchmark.

More in Math

All 105 in Math
  • IMO-AnswerBench In use 400 olympiad problems with short verifiable answers, robustified against memorization. Scored by answer match. GLM-5.2 91%
  • AIME 2026 In use Models solve the 30 integer-answer problems from the 2026 AIME I and II math competitions. Scored by exact answer match. GPT-5.5 100%
  • HMMT 2026 In use Models solve the 33 final-answer problems from the February 2026 Harvard-MIT Mathematics Tournament. Scored by exact answer match. GPT-5.5 98.5%
  • MathArena (Apex, IMO, USAMO) In use Evaluates models on newly released math competitions after release. Final-answer or human/LLM-judged proof scores. Claude Opus 4.8 81.3%
  • PolyMath In use Models solve 9,000 parallel math problems in 18 languages across four difficulty levels, from school math to frontier math. Final answers are checked. Qwen3.7-Max 86.5%
  • USAMO 2026 In use Models write full proofs for the six problems of the 2026 USA Mathematical Olympiad. Judges grade each proof from 0 to 7 against rubrics. GPT-5.5 98.2%