Benchmark Almanac

AIME 2024

gpt-oss-120b 96.6% leads since August 2025
Fading

Models solve the 30 problems of the 2024 AIME I and II. Answers are integers from 0 to 999, scored by exact match.

The problems and solutions were published in February 2024, so later training data can contain them.

Released
February 2024
Kind
Competition problems with answers
Level
Competition
Scored
Checked automatically
Answers
Short answer
Tasks
All public
Strongest model tested
o3-pro #81 on the capability index
Last in a launch post
January 2026, dropped after it saturated
Last model added
February 2026
88
Models scored in lab cards
70
Launch posts list it, from 29 labs
57
System cards report it, from 27 labs

gpt-oss-120b leads with 96.6% among models released by February 2026

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

The newest model with a score here came out in February 2026, and nobody has reported a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:

88 models. Scroll sideways for the rest.

  1. 96.6 gpt-oss-120b
  2. 96.0 gpt-oss-20b
  3. 95.8 Grok-3 mini
  4. 93.4 o4-mini
  5. 93.3 Grok 3
  6. 93.3 LongCat-Flash-Thinking
  7. 93.1 DeepSeek-V3.1
  8. 93.0 o3-pro
  9. 92.0 Gemini 2.5 Pro
  10. 91.8 Magistral Medium 1.2
  11. 91.7 seed-oss-36b-instruct
  12. 91.7 Solar Open 100B
  13. 91.6 o3
  14. 91.4 DeepSeek-R1
  15. 91.0 GLM-4.5
  16. 90.9 STEP3-VL-10B
  17. 90.8 INTELLECT-3
  18. 90.0 Magistral Medium 1.0
  19. 90.0 Seed1.6-Thinking
  20. 89.8 Ministral 3 14B
  21. 89.4 GLM-4.5-Air
  22. 89.0 Qwen3-Coder-Next
  23. 88.1 Falcon H1R 7B
  24. 88.0 Gemini 2.5 Flash
  25. 87.5 Llama-3.3-Nemotron-Super-49B-v1.5
  26. 87.3 o3-mini
  27. 87.3 Hunyuan-A13B-Instruct
  28. 86.7 Seed-Thinking-v1.5
  29. 86.1 Magistral Small 1.2
  30. 86.0 MiniMax-M1-80k
  31. 85.7 Qwen3-235B-A22B
  32. 84.7 InternVL3.5-241B-A28B
  33. 83.4 Baichuan-M2-32B
  34. 81.9 nvidia-nemotron-nano-9b-v2
  35. 81.9 Hermes 4 405B
  36. 81.4 Qwen3-32B
  37. 81.3 Phi-4-Reasoning-plus
  38. 80.8 GLM-Z1-32B-0414
  39. 80.8 Llama-3.1-Nemotron-Ultra-253B-v1
  40. 80.6 Olmo 3.1 32B Think
  41. 80.4 Qwen3-30B-A3B
  42. 80.0 Claude 3.7 Sonnet
  43. 79.8 DeepSeek-R1
  44. 79.3 Qwen3-14B
  45. 79.2 o1
  46. 78.8 INTELLECT-2
  47. 78.2 Hunyuan-T1
  48. 77.5 Kimi k1.5
  49. 76.8 Olmo 3 32B Think
  50. 76.5 Solar Pro 2
  51. 76.0 Qwen3-8B
  52. 76.0 Code World Model (CWM)
  53. 75.3 Phi-4-reasoning
  54. 73.8 Qwen3-4B
  55. 73.3 Gemini 2.0 Flash Thinking
  56. 72.9 LongCat-Flash-Omni
  57. 72.6 DeepSeek-R1-Distill-Qwen-32B
  58. 72.1 EXAONE Deep 32B
  59. 72.0 Magistral Medium 1.1
  60. 71.9 Hermes 4.3 36B
  61. 70.7 Magistral Small 1.0
  62. 70.5 Magistral Small 1.1
  63. 70.4 LongCat-Flash-Chat
  64. 70.0 DeepSeek-R1-Distill-Llama-70B
  65. 70.0 Reka Flash 3
  66. 69.7 DeepSeek-R1-Distill-Qwen-14B
  67. 69.6 Kimi K2
  68. 68.2 MiMo-7B-RL
  69. 67.5 Llama-3.3-Nemotron-Super-49B-v1
  70. 59.4 DeepSeek-V3
  71. 57.5 Phi-4-mini-reasoning
  72. 56.7 o1-preview
  73. 54.8 ERNIE-4.5-300B-A47B
  74. 52.3 Phi-4-mini-flash-reasoning
  75. 49.6 GPT-4.1 mini
  76. 48.3 Qwen3-1.7B
  77. 43.3 Hunyuan-TurboS
  78. 36.7 GPT-4.5
  79. 30.0 Mercury
  80. 29.4 GPT-4.1 nano
  81. 28.9 DeepSeek-R1-Distill-Qwen-1.5B
  82. 27.6 Claude 3.5 Sonnet (October 2024)
  83. 23.8 Falcon-H1-34B
  84. 23.3 Cohere Command A
  85. 20.0 InternLM3-8B-Instruct
  86. 10.0 Phi-4 Mini
  87. 8.12 Granite 3.3 8B Instruct
  88. 5.30 Claude 3.5 Haiku
  1. 1 gpt-oss-120b 96.6%
  2. 2 gpt-oss-20b 96%
  3. 3 Grok-3 mini 95.8%
  4. 4 o4-mini 93.4%
  5. 5 Grok 3 93.3%
  6. 6 LongCat-Flash-Thinking 93.3%
  7. 7 DeepSeek-V3.1 93.1%
  8. 8 o3-pro 93%
  9. 9 Gemini 2.5 Pro Mar 2025 92%
  10. 10 Magistral Medium 1.2 91.8%
  11. 11 seed-oss-36b-instruct 91.7%
  12. 12 Solar Open 100B 91.7%
  13. 13 o3 91.6%
  14. 14 DeepSeek-R1 May 2025 91.4%
  15. 15 GLM-4.5 91%
  16. 16 STEP3-VL-10B 90.9%
  17. 17 INTELLECT-3 90.8%
  18. 18 Magistral Medium 1.0 90%
  19. 19 Seed1.6-Thinking 90%
  20. 20 Ministral 3 14B 89.8%
  21. 21 GLM-4.5-Air 89.4%
  22. 22 Qwen3-Coder-Next 89%
  23. 23 Falcon H1R 7B 88.1%
  24. 24 Gemini 2.5 Flash Apr 2025 88%
  25. 25 Llama-3.3-Nemotron-Super-49B-v1.5 87.5%
  26. 26 o3-mini 87.3%
  27. 27 Hunyuan-A13B-Instruct 87.3%
  28. 28 Seed-Thinking-v1.5 86.7%
  29. 29 Magistral Small 1.2 86.1%
  30. 30 MiniMax-M1-80k 86%
  31. 31 Qwen3-235B-A22B 85.7%
  32. 32 InternVL3.5-241B-A28B 84.7%
  33. 33 Baichuan-M2-32B 83.4%
  34. 34 nvidia-nemotron-nano-9b-v2 81.9%
  35. 35 Hermes 4 405B 81.9%
  36. 36 Qwen3-32B 81.4%
  37. 37 Phi-4-Reasoning-plus 81.3%
  38. 38 GLM-Z1-32B-0414 80.8%
  39. 39 Llama-3.1-Nemotron-Ultra-253B-v1 80.8%
  40. 40 Olmo 3.1 32B Think 80.6%
  41. 41 Qwen3-30B-A3B 80.4%
  42. 42 Claude 3.7 Sonnet 80%
  43. 43 DeepSeek-R1 79.8%
  44. 44 Qwen3-14B 79.3%
  45. 45 o1 79.2%
  46. 46 INTELLECT-2 78.8%
  47. 47 Hunyuan-T1 78.2%
  48. 48 Kimi k1.5 77.5%
  49. 49 Olmo 3 32B Think 76.8%
  50. 50 Solar Pro 2 76.5%
  51. 51 Qwen3-8B 76%
  52. 52 Code World Model (CWM) 76%
  53. 53 Phi-4-reasoning 75.3%
  54. 54 Qwen3-4B 73.8%
  55. 55 Gemini 2.0 Flash Thinking Jan 2025 73.3%
  56. 56 LongCat-Flash-Omni 72.9%
  57. 57 DeepSeek-R1-Distill-Qwen-32B 72.6%
  58. 58 EXAONE Deep 32B 72.1%
  59. 59 Magistral Medium 1.1 72%
  60. 60 Hermes 4.3 36B 71.9%
  61. 61 Magistral Small 1.0 70.7%
  62. 62 Magistral Small 1.1 70.5%
  63. 63 LongCat-Flash-Chat 70.4%
  64. 64 DeepSeek-R1-Distill-Llama-70B 70%
  65. 65 Reka Flash 3 70%
  66. 66 DeepSeek-R1-Distill-Qwen-14B 69.7%
  67. 67 Kimi K2 Jul 2025 69.6%
  68. 68 MiMo-7B-RL 68.2%
  69. 69 Llama-3.3-Nemotron-Super-49B-v1 67.5%
  70. 70 DeepSeek-V3 59.4%
  71. 71 Phi-4-mini-reasoning 57.5%
  72. 72 o1-preview 56.7%
  73. 73 ERNIE-4.5-300B-A47B 54.8%
  74. 74 Phi-4-mini-flash-reasoning 52.3%
  75. 75 GPT-4.1 mini 49.6%
  76. 76 Qwen3-1.7B 48.3%
  77. 77 Hunyuan-TurboS 43.3%
  78. 78 GPT-4.5 36.7%
  79. 79 Mercury 30%
  80. 80 GPT-4.1 nano 29.4%
  81. 81 DeepSeek-R1-Distill-Qwen-1.5B 28.9%
  82. 82 Claude 3.5 Sonnet (October 2024) 27.6%
  83. 83 Falcon-H1-34B 23.8%
  84. 84 Cohere Command A 23.3%
  85. 85 InternLM3-8B-Instruct 20%
  86. 86 Phi-4 Mini 10%
  87. 87 Granite 3.3 8B Instruct 8.12%
  88. 88 Claude 3.5 Haiku 5.30%

Source: Labs’ model cards

#ModelScoreSettingDateSource
1 gpt-oss-120b 96.6% Aug 2025 Lab model card
2 gpt-oss-20b 96% Aug 2025 Lab model card
3 Grok-3 mini 95.8% Feb 2025 Lab model card
4 o4-mini 93.4% Apr 2025 Lab model card
5 Grok 3 93.3% Feb 2025 Lab model card
6 LongCat-Flash-Thinking 93.3% Sep 2025 Lab model card
7 DeepSeek-V3.1 93.1% Aug 2025 Lab model card
8 o3-pro 93% Jun 2025 Lab model card
9 Gemini 2.5 Pro Mar 2025 92% Mar 2025 Lab model card
10 Magistral Medium 1.2 91.8% Sep 2025 Lab model card
11 seed-oss-36b-instruct 91.7% Aug 2025 Lab model card
12 Solar Open 100B 91.7% Dec 2025 Lab model card
13 o3 91.6% Apr 2025 Lab model card
14 DeepSeek-R1 May 2025 91.4% May 2025 Lab model card
15 GLM-4.5 91% Jul 2025 Lab model card
16 STEP3-VL-10B 90.9% Jan 2026 Lab model card
17 INTELLECT-3 90.8% Nov 2025 Lab model card
18 Magistral Medium 1.0 90% Jun 2025 Lab model card
19 Seed1.6-Thinking 90% Jun 2025 Lab model card
20 Ministral 3 14B 89.8% Dec 2025 Lab model card
21 GLM-4.5-Air 89.4% Aug 2025 Lab model card
22 Qwen3-Coder-Next 89% Feb 2026 Lab model card
23 Falcon H1R 7B 88.1% Jan 2026 Lab model card
24 Gemini 2.5 Flash Apr 2025 88% Apr 2025 Lab model card
25 Llama-3.3-Nemotron-Super-49B-v1.5 87.5% Jul 2025 Lab model card
26 o3-mini 87.3% Jan 2025 Lab model card
27 Hunyuan-A13B-Instruct 87.3% Jun 2025 Lab model card
28 Seed-Thinking-v1.5 86.7% Apr 2025 Lab model card
29 Magistral Small 1.2 86.1% Sep 2025 Lab model card
30 MiniMax-M1-80k 86% Jun 2025 Lab model card
31 Qwen3-235B-A22B 85.7% Apr 2025 Lab model card
32 InternVL3.5-241B-A28B 84.7% Aug 2025 Lab model card
33 Baichuan-M2-32B 83.4% Aug 2025 Lab model card
34 nvidia-nemotron-nano-9b-v2 81.9% Aug 2025 Lab model card
35 Hermes 4 405B 81.9% Aug 2025 Lab model card
36 Qwen3-32B 81.4% May 2025 Lab model card
37 Phi-4-Reasoning-plus 81.3% Apr 2025 Lab model card
38 GLM-Z1-32B-0414 80.8% Apr 2025 Lab model card
39 Llama-3.1-Nemotron-Ultra-253B-v1 80.8% May 2025 Lab model card
40 Olmo 3.1 32B Think 80.6% Dec 2025 Lab model card
41 Qwen3-30B-A3B 80.4% May 2025 Lab model card
42 Claude 3.7 Sonnet 80% Feb 2025 Lab model card
43 DeepSeek-R1 79.8% Jan 2025 Lab model card
44 Qwen3-14B 79.3% May 2025 Lab model card
45 o1 79.2% Dec 2024 Lab model card
46 INTELLECT-2 78.8% May 2025 Lab model card
47 Hunyuan-T1 78.2% Mar 2025 Lab model card
48 Kimi k1.5 77.5% Jan 2025 Lab model card
49 Olmo 3 32B Think 76.8% Nov 2025 Lab model card
50 Solar Pro 2 76.5% Jul 2025 Lab model card
51 Qwen3-8B 76% May 2025 Lab model card
52 Code World Model (CWM) 76% Sep 2025 Lab model card
53 Phi-4-reasoning 75.3% Apr 2025 Lab model card
54 Qwen3-4B 73.8% May 2025 Lab model card
55 Gemini 2.0 Flash Thinking Jan 2025 73.3% Jan 2025 Lab model card
56 LongCat-Flash-Omni 72.9% Oct 2025 Lab model card
57 DeepSeek-R1-Distill-Qwen-32B 72.6% Jan 2025 Lab model card
58 EXAONE Deep 32B 72.1% Mar 2025 Lab model card
59 Magistral Medium 1.1 72% Jul 2025 Lab model card
60 Hermes 4.3 36B 71.9% Dec 2025 Lab model card
61 Magistral Small 1.0 70.7% Jun 2025 Lab model card
62 Magistral Small 1.1 70.5% Jul 2025 Lab model card
63 LongCat-Flash-Chat 70.4% Aug 2025 Lab model card
64 DeepSeek-R1-Distill-Llama-70B 70% Jan 2025 Lab model card
65 Reka Flash 3 70% Mar 2025 Lab model card
66 DeepSeek-R1-Distill-Qwen-14B 69.7% Jan 2025 Lab model card
67 Kimi K2 Jul 2025 69.6% Jul 2025 Lab model card
68 MiMo-7B-RL 68.2% Apr 2025 Lab model card
69 Llama-3.3-Nemotron-Super-49B-v1 67.5% May 2025 Lab model card
70 DeepSeek-V3 59.4% Mar 2025 Lab model card
71 Phi-4-mini-reasoning 57.5% Apr 2025 Lab model card
72 o1-preview 56.7% Sep 2024 Lab model card
73 ERNIE-4.5-300B-A47B 54.8% Jun 2025 Lab model card
74 Phi-4-mini-flash-reasoning 52.3% Jul 2025 Lab model card
75 GPT-4.1 mini 49.6% Apr 2025 Lab model card
76 Qwen3-1.7B 48.3% May 2025 Lab model card
77 Hunyuan-TurboS 43.3% Feb 2025 Lab model card
78 GPT-4.5 36.7% Feb 2025 Lab model card
79 Mercury 30% Jun 2025 Lab model card
80 GPT-4.1 nano 29.4% Apr 2025 Lab model card
81 DeepSeek-R1-Distill-Qwen-1.5B 28.9% Jan 2025 Lab model card
82 Claude 3.5 Sonnet (October 2024) 27.6% Oct 2024 Lab model card
83 Falcon-H1-34B 23.8% May 2025 Lab model card
84 Cohere Command A 23.3% Apr 2025 Lab model card
85 InternLM3-8B-Instruct 20% Jan 2025 Lab model card
86 Phi-4 Mini 10% Mar 2025 Lab model card
87 Granite 3.3 8B Instruct 8.12% Apr 2025 Lab model card
88 Claude 3.5 Haiku 5.30% Oct 2024 Lab model card

6 models have held number one in labs’ own numbers since its release in February 2024

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

OpenAI DeepSeek xAI
Lab claims Passed 85% in Jan 2025, by o3-mini
gpt-oss-120b 96.6%

Source: Labs’ model cards

OpenAI’s own number for o3-mini passed 85% in January 2025

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

Reported by the lab in its model card Best so far
0% 20% 40% 60% 80% 100% 2025 2026 Near the ceiling (85%) gpt-oss-120b Grok-3 mini o3-mini DeepSeek-R1 o1-preview 0% 20% 40% 60% 80% 100% 2025 2026 Near the ceiling (85%) gpt-oss-120b o3-mini

Source: Labs’ model cards

Labs headline it less often now, last in January 2026

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.

OpenAI
Anthropic
DeepSeek
Shanghai AI Lab
Moonshot AI
Google DeepMind
xAI
Tencent
Qwen
Reka
LG AI Research
ByteDance Seed
Z.ai
IBM
Xiaomi Corp
Microsoft
Prime Intellect
Technology Innovation Institute
Mistral AI
MiniMax
Inception Labs
Baidu
Upstage
NVIDIA
Baichuan
Nous Research
Meituan
Meta
Ai2
DateLaunch postScoreAs the post writes it
Jan 5, 2026 Falcon H1R 7B 88.1 AIME-24
Dec 31, 2025 Solar Open 100B 91.7 AIME 2024
Dec 12, 2025 Olmo 3.1 32B Think 80.6 AIME 2024
Dec 3, 2025 Hermes 4.3 36B 71.9 AIME 24
Dec 2, 2025 Ministral 3 14B 89.8 AIME24 0.898 (reasoning)
Nov 26, 2025 INTELLECT-3 90.8 AIME24
Nov 20, 2025 Olmo 3 32B Think 76.8 AIME 2024
Oct 31, 2025 LongCat-Flash-Omni 72.9 AIME24(avg@10)
Sep 24, 2025 Code World Model (CWM) 76 AIME24
Sep 21, 2025 LongCat-Flash-Thinking 93.3 AIME24(Mean@32)
Sep 17, 2025 Magistral Small 1.2 86.1 AIME24 pass@1
Sep 17, 2025 Magistral Medium 1.2 91.8 AIME24 pass@1
Aug 29, 2025 LongCat-Flash-Chat 70.4 AIME24(avg@10)
Aug 26, 2025 Hermes 4 405B 81.9 AIME'24 (reasoning)
Aug 25, 2025 InternVL3.5-241B-A28B 84.7 AIME24
Aug 21, 2025 DeepSeek-V3.1 93.1 AIME 2024 (Pass@1)
Aug 20, 2025 seed-oss-36b-instruct 91.7 AIME24
Aug 10, 2025 Baichuan-M2-32B 83.4 AIME24
Aug 5, 2025 gpt-oss-20b 96 AIME 2024 (tools)
Aug 5, 2025 gpt-oss-120b 96.6 AIME 2024 (tools)
Jul 28, 2025 GLM-4.5 91 AIME24
Jul 25, 2025 Llama-3.3-Nemotron-Super-49B-v1.5 87.5 AIME 2024 (pass@1, avg of 16)
Jul 24, 2025 Magistral Small 1.1 70.5 AIME24 pass@1
Jul 24, 2025 Magistral Medium 1.1 72 AIME24 pass@1
Jul 11, 2025 Kimi K2 69.6 AIME 2024, Avg@64
Jul 10, 2025 Solar Pro 2 76.5 AIME'24 pass@1
Jul 9, 2025 Phi-4-mini-flash-reasoning 52.3 AIME24
Jun 30, 2025 ERNIE-4.5-300B-A47B 54.8 AIME'24
Jun 27, 2025 Hunyuan-A13B-Instruct 87.3 AIME 2024
Jun 26, 2025 Mercury 30 AIME 2024 (% accuracy)
Jun 25, 2025 Seed1.6-Thinking 90 AIME2024
Jun 16, 2025 MiniMax-M1-80k 86 AIME 2024
Jun 10, 2025 Magistral Small 1.0 70.7 AIME24 pass@1
Jun 10, 2025 o3-pro 93 Competition Math (AIME 2024), pass@1
Jun 10, 2025 Magistral Medium 1.0 90 AIME-24 (maj@64; maj@4 = 81.3, pass@1 = 73.6)
May 28, 2025 DeepSeek-R1 91.4 AIME 2024 (Pass@1)
May 20, 2025 Falcon-H1-34B 23.8 AIME-24
May 11, 2025 INTELLECT-2 78.8 AIME24
Apr 30, 2025 Phi-4-reasoning 75.3 AIME 24
Apr 30, 2025 Phi-4-Reasoning-plus 81.3 AIME 24
Apr 29, 2025 MiMo-7B-RL 68.2 AIME 2024 (Pass@1)
Apr 29, 2025 Qwen3-235B-A22B 85.7 AIME’24
Apr 17, 2025 Gemini 2.5 Flash 88 AIME 2024 single attempt
Apr 16, 2025 o4-mini 93.4 AIME 2024 (no tools)
Apr 16, 2025 Granite 3.3 8B Instruct 8.12 AIME24
Apr 16, 2025 o3 91.6 AIME 2024 Competition Math, o3 (no tools)
Apr 14, 2025 GPT-4.1 nano 29.4 AIME '24
Apr 14, 2025 GPT-4.1 mini 49.6 AIME '24
Apr 14, 2025 GLM-Z1-32B-0414 80.8 AIME24
Apr 10, 2025 Seed-Thinking-v1.5 86.7 AIME 2024
Mar 25, 2025 Gemini 2.5 Pro 92 AIME 2024, single attempt (pass@1)
Mar 24, 2025 DeepSeek-V3 59.4 AIME
Mar 21, 2025 Hunyuan-T1 78.2 AIME 2024
Mar 18, 2025 EXAONE Deep 32B 72.1 AIME 2024 pass@1 72.1 (cons@64 90.0)
Mar 10, 2025 Reka Flash 3 70 AIME'24 (cons@64)
Mar 6, 2025 QwQ-32B AIME24
Feb 27, 2025 Hunyuan-TurboS 43.3 AIME2024
Feb 27, 2025 GPT-4.5 36.7 AIME '24 (math)
Feb 24, 2025 Claude 3.7 Sonnet 80 High school math competition AIME 2024 (64K extended thinking, parallel test-time compute)
Feb 19, 2025 Grok-3 mini 95.8 AIME'24 (cons@64; pass@1 = 89.5) [Grok 3 mini Think]
Feb 19, 2025 Grok 3 93.3 AIME'24 (cons@64; pass@1 = 83.9)
Jan 31, 2025 o3-mini 87.3 Competition Math (AIME 2024)
Jan 21, 2025 Gemini 2.0 Flash Thinking 73.3 AIME2024 (Math)
Jan 20, 2025 Kimi k1.5 77.5 AIME 2024 (Pass@1), long-CoT
Jan 20, 2025 DeepSeek-R1 79.8 AIME 2024 (Pass@1)
Jan 13, 2025 InternLM3-8B-Instruct 20 AIME2024(0-shot), Thinking Mode
Dec 26, 2024 DeepSeek-V3 39.2 AIME 2024 (Pass@1)
Dec 17, 2024 o1 79.2 AIME 2024 (pass @1)
Oct 22, 2024 Claude 3.5 Sonnet (October 2024) 27.6 AIME 2024 (Maj@64 0-shot CoT)
Sep 12, 2024 o1-preview 56.7 AIME (2024) cons@64

57 system cards report it, from 27 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
Feb 28, 2026 Qwen3-Coder-Next technical report 89 AIME24 (Table 9) Capabilities
Jan 14, 2026 STEP3-VL-10B technical report 90.9 AIME2024, SeRe (Tables 2 and 3). PaCoRe 93.33 Capabilities
Jan 13, 2026 Ministral 3 14B technical report 89.8 AIME 2024, reported as pass@16 (Table 5) Capabilities
Jan 11, 2026 Solar Open 100B technical report 91.7 AIME 2024 (Table 6) Capabilities
Jan 5, 2026 Falcon H1R 7B technical report 88.1 AIME24 pass@1 (Table 4). DeepConf@512 96.7 (Table 7) Capabilities
Dec 18, 2025 INTELLECT-3 technical report 90.8 AIME24, Avg@32 (Table 2, Appendix A.1) Capabilities
Dec 15, 2025 Olmo 3 32B Think technical report 76.8 AIME 2024, Avg@32, Final Think 3.0 column (Table 14) Capabilities
Dec 15, 2025 Olmo 3.1 32B Think technical report 80.6 AIME 2024, Avg@32 (Tables 1 and 14) Capabilities
Oct 31, 2025 LongCat-Flash-Omni technical report 72.9 AIME24 (avg@10) (Table 13) Capabilities
Sep 30, 2025 Code World Model (CWM) technical report 76 AIME24, pass@1 averaged over 20 samples (Table 12) Capabilities
Sep 23, 2025 LongCat-Flash-Thinking technical report 93.3 AIME-24(Mean@32) (Table 2) Capabilities
Sep 2, 2025 Baichuan-M2-32B technical report 83.4 AIME24, max_tokens 64k (Table 1) Capabilities
Sep 1, 2025 LongCat-Flash-Chat technical report 70.4 AIME24 (avg@10) (Table 3) Capabilities
Aug 25, 2025 InternVL3.5-241B-A28B technical report 84.7 AIME24 (Table 2). OpenCompass run gives 84.1 (Table 14) Capabilities
Aug 25, 2025 Hermes 4 405B technical report 81.9 AIME'24, reasoning mode (Table 3). Non-reasoning 11.4 Capabilities
Aug 20, 2025 nvidia-nemotron-nano-9b-v2 technical report 81.9 AIME24, NVIDIA-Nemotron-Nano-9B-v2 (Figure 1) Capabilities
Aug 8, 2025 GLM-4.5 technical report 91 AIME 24, Avg@32 (Table 4) Capabilities
Aug 8, 2025 GLM-4.5-Air technical report 89.4 AIME 24, Avg@32 (Table 4) Capabilities
Aug 5, 2025 gpt-oss-20b model card 96 AIME 2024 (with tools), high reasoning (no tools 92.1) (Table 3, Figure 1) Capabilities
Aug 5, 2025 gpt-oss-120b model card 96.6 AIME 2024 (with tools), high reasoning (no tools 95.8) (Table 3, Figure 1) Capabilities
Jul 30, 2025 Falcon-H1-34B technical report 23.8 AIME-24, average accuracy over 16 repetitions (Table 24) Capabilities
Jul 21, 2025 Kimi K2 technical report 69.6 AIME 2024 (Avg@64) (Table 3) Capabilities
Jul 9, 2025 Phi-4-mini-flash-reasoning technical report 52.3 AIME24, pass@1 averaged over 64 samples, 32K generation (Table 4) Capabilities
Jun 29, 2025 ERNIE-4.5-300B-A47B technical report 54.8 AIME'24 (Table 5) Capabilities
Jun 26, 2025 Hunyuan-A13B-Instruct technical report 87.3 AIME2024, slow-thinking (Table 3). Fast-thinking 30.6 (Table 4) Capabilities
Jun 16, 2025 MiniMax-M1-80k technical report 86 AIME 2024, avg of 32 samples (Table 2) Capabilities
Jun 12, 2025 Magistral Small 1.0 technical report 70.7 AIME'24 pass@1, SFT + RL (Magistral Small) column (Table 3). maj@64 83.3 Capabilities
Jun 12, 2025 Magistral Medium 1.0 technical report 73.6 AIME'24, pass@1 averaged over 64 runs (Table 2). maj@64 90.0 Capabilities
May 14, 2025 Qwen3-8B technical report 76 AIME’24, thinking mode (Table 17). Non-thinking 29.1 (Table 18) Capabilities
May 14, 2025 Qwen3-4B technical report 73.8 AIME’24, thinking mode (Table 17). Non-thinking 25.0 (Table 18) Capabilities
May 14, 2025 Qwen3-32B technical report 81.4 AIME’24, thinking mode (Table 13). Non-thinking 31.0 (Table 14) Capabilities
May 14, 2025 Qwen3-30B-A3B technical report 80.4 AIME’24, thinking mode (Table 15). Non-thinking 32.8 (Table 16) Capabilities
May 14, 2025 Qwen3-235B-A22B technical report 85.7 AIME’24, thinking mode (Table 11). Non-thinking 40.1 (Table 12) Capabilities
May 14, 2025 Qwen3-14B technical report 79.3 AIME’24, thinking mode (Table 15). Non-thinking 31.7 (Table 16) Capabilities
May 14, 2025 Qwen3-1.7B technical report 48.3 AIME’24, thinking mode (Table 19). Non-thinking 13.4 (Table 20) Capabilities
May 12, 2025 MiMo-7B-RL technical report 68.2 AIME 2024 (Pass@1), average of 32 runs (Table 4, Table 5, Table 6) Capabilities
May 12, 2025 INTELLECT-2 technical report 78.8 AIME24, evalchemy defaults, target length 10,000 tokens (Table 1) Capabilities
May 2, 2025 Llama-3.3-Nemotron-Super-49B-v1 technical report 67.5 AIME24, reasoning on, reasoning off 16.7 (Table 4) Capabilities
May 2, 2025 Llama-3.1-Nemotron-Ultra-253B-v1 technical report 80.8 AIME24, reasoning on, reasoning off 20.0 (Table 5) Capabilities
Apr 30, 2025 Phi-4-reasoning technical report 74.6 AIME 24, average pass@1, std 5.1 (Table 1) Capabilities
Apr 30, 2025 Phi-4-Reasoning-plus technical report 81.3 AIME 24, average pass@1 over 5 runs (Table 1) Capabilities
Apr 30, 2025 Phi-4-mini-reasoning technical report 57.5 AIME (AIME24 per Section 5.1), pass@1 averaged over 3 runs (Table 3) Capabilities
Apr 29, 2025 Gemini 2.5 Flash model card 88 AIME 2024, single attempt (pass@1) (Table, p.4) Capabilities
Apr 28, 2025 Gemini 2.5 Pro model card 92 AIME 2024, single attempt pass@1 (Table, p.4, column Gemini 2.5 Pro Experimental 03-25) Capabilities
Apr 10, 2025 Seed-Thinking-v1.5 technical report 86.7 AIME 2024, mean of 32 samples (Table 2) Capabilities
Apr 1, 2025 Cohere Command A technical report 23.3 AIME (2024) (Table 15) Capabilities
Mar 16, 2025 EXAONE Deep 32B technical report 72.1 AIME 2024, pass@1 with k=64, cons@64 90.0 (Table 2) Capabilities
Mar 3, 2025 Phi-4 Mini technical report 10 AIME 2024, Phi-4-Mini row of the CoT reasoning comparison (Table 9) Capabilities
Jan 20, 2025 Kimi k1.5 technical report 77.5 AIME 2024 (Pass@1), long-CoT (Table 2). Short-CoT 60.8 (Table 3) Capabilities
Jan 20, 2025 DeepSeek-R1 technical report 79.8 AIME 2024 (Pass@1), DeepSeek-R1 (Table 8, same as final column of Table 3) Capabilities
Jan 20, 2025 DeepSeek-R1-Distill-Qwen-32B technical report 72.6 AIME 2024 pass@1, cons@64 83.3, DeepSeek-R1-Distill-Qwen-32B (Table 15) Capabilities
Jan 20, 2025 DeepSeek-R1-Distill-Qwen-14B technical report 69.7 AIME 2024 pass@1, cons@64 80.0, DeepSeek-R1-Distill-Qwen-14B (Table 15) Capabilities
Jan 20, 2025 DeepSeek-R1-Distill-Qwen-1.5B technical report 28.9 AIME 2024 pass@1, cons@64 52.7, DeepSeek-R1-Distill-Qwen-1.5B (Table 15) Capabilities
Jan 20, 2025 DeepSeek-R1-Distill-Llama-70B technical report 70 AIME 2024 pass@1, cons@64 86.7, DeepSeek-R1-Distill-Llama-70B (Table 15) Capabilities
Dec 26, 2024 DeepSeek-V3 technical report 39.2 AIME 2024 (Pass@1), DeepSeek-V3 (Table 6) Capabilities
Oct 22, 2024 Claude 3.5 Sonnet (October 2024) model card 16 AIME 2024, 0-shot CoT. Maj@64 0-shot CoT 27.6% (Table 7) Capabilities
Oct 22, 2024 Claude 3.5 Haiku model card 5.3 AIME 2024, 0-shot CoT. Maj@64 0-shot CoT 10.1% (Table 8) Capabilities

Versions

We switch the top row to each new version when it comes out. Open it for one row per version. An old version stays in play while people still test it, so whoever first takes it past 85% gets credit for closing it out.

OpenAI DeepSeek xAI
AIME 2026 Passed 85% in Feb 2026, by GPT-5.2
GPT-5.5 100%
AIME 2024 Passed 85% in Jan 2025, by o3-mini
gpt-oss-120b 96.6%
AIME 2025 Passed 85% in Feb 2025, by Grok 3
Grok 4 Heavy 100%
AIME 2026 Passed 85% in Feb 2026, by GPT-5.2
GPT-5.5 100%

Sources: Official leaderboards and labs’ model cards

Replaces AIME 2023 Replaced by AIME 2025

More in Math

All 113 in Math
  • IMO-AnswerBench In use 400 olympiad problems with short verifiable answers, robustified against memorization. Scored by answer match. GLM-5.2 91%
  • 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%
  • 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%
  • 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%
  • MathArena Apex Shortlist In use Models solve 47 hard final-answer problems that MathArena selected from 2025 competitions, where the best models scored about 50% at selection. Scored by accuracy over repeated attempts. GPT-5.5 98.4%
  • FrontierMath Tiers 1-3 v2 In use Models solve 295 unpublished math problems from undergraduate to advanced graduate level and submit answers that code checks automatically. Scored by share correct. Claude Fable 5.2 95.1%