Benchmark Almanac

GSM8K

Llama 3.1-405B 96.8% leads since July 2024
Claude Opus 4.5 98.1% leads since November 2025
Claude Opus 4.5 98.1% leads since November 2025
Fading 1 known issue

AGI-Eval’s leaderboard hasn’t scored a model released after Kimi K2.5 (January 2026). Labs report their own numbers for 9 newer models, such as DiffusionGemma 26B A4B at 96.3%.

8.5K grade-school math word problems. Final numeric answer scored by exact match.

Saturated.

Made by
OpenAI
Released
October 2021
Kind
Word problems
Level
School
Scored
Checked automatically
Answers
Short answer
Tasks
All public
Measures
Capability
Subject
Mathematics
Language
English
In and out
Text → Text
Interaction
Single turn
Run by
Anyone
Strongest model tested
DeepSeek V4.1 Flash #34 on the capability index
Last in a launch post
September 2026, dropped after it saturated
Last model added
October 2026
Scores refreshed
November 20th, 2026

In the authors’ words

State-of-the-art language models can match human performance on many tasks, but they still struggle to robustly perform multi-step mathematical reasoning. To diagnose the failures of current models and support research, we introduce GSM8K, a dataset of 8.5K high quality linguistically diverse grade school math word problems. We find that even the largest transformer models fail to achieve high test performance, despite the conceptual simplicity of this problem distribution. To increase performance, we propose training verifiers to judge the correctness of model completions. At test time, we generate many candidate solutions and select the one ranked highest by the verifier. We demonstrate that verification significantly improves performance on GSM8K, and we provide strong empirical evidence that verification scales more effectively with increased data than a finetuning baseline.

Abstract of Training Verifiers to Solve Math Word Problems (arXiv:2110.14168, CC0)

Known issues

A published audit found a problem in GSM8K. We summarize each finding in our words and link its source. The scores on this page don't include any fixes. See all audits

  1. Contamination Still open

    Scale AI reports that many models score lower on GSM1k, a new set written to mirror GSM8K, than on GSM8K itself. It reads the gap as evidence that some models partially memorized GSM8K, while frontier models show minimal signs of overfitting.

    Accuracy drops by up to 8% on GSM1k. A model's chance of generating GSM8K examples tracks its GSM8K-to-GSM1k gap (Spearman's r² = 0.36).

    Our analysis confirms the widespread suspicion in the field that many models are contaminated by benchmark data, with the worst models performing 8% worse on GSM1k compared to GSM8k.

    A Careful Examination of Large Language Model Performance on Grade School Arithmetic by Scale AI, May 1st, 2024

92
Models scored in lab cards
57
Launch posts list it, from 19 labs
72
System cards report it, from 17 labs

Llama 3.1-405B leads with 96.8%

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

Claude Opus 4.5 leads with 98.1% across all independent runs

Best score per model across AGI-Eval’s 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.

Claude Opus 4.5 leads with 98.1%, 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.

92 models. Scroll sideways for the rest.

  1. 96.8 Llama 3.1-405B
  2. 96.6 ERNIE-4.5-300B-A47B
  3. 96.4 Cogito v1 Preview 70B
  4. 96.4 Claude 3.5 Sonnet
  5. 96.3 DiffusionGemma 26B A4B
  6. 96.2 Cogito v2 Preview 671B MoE
  7. 95.9 Qwen2.5-32B
  8. 95.9 Gemma 3 27B
  9. 95.8 Qwen2.5-72B
  10. 95.5 Tulu 3 405B
  11. 95.3 Qwen2.5-VL-72B
  12. 95.1 Llama 3.1-70B
  13. 95.0 Claude 3 Opus
  14. 94.8 Qwen2.5-14B
  15. 94.8 MiniMax-Text-01
  16. 94.8 Qwen2.5-14B-Instruct-1M
  17. 94.4 Gemini 1.0 Ultra
  18. 94.4 Gemma 3 12B
  19. 94.2 Granite 4.1 30B
  20. 94.0 Sarvam-M
  21. 93.8 Qwen-Turbo
  22. 93.3 Code World Model (CWM)
  23. 93.2 Qwen2-72B
  24. 93.0 Llama 3-70B
  25. 93.0 Mistral Large 2
  26. 93.0 DeepSeek V4.1 Flash
  27. 93.0 DeepSeek-V4.1-Flash Base
  28. 92.6 DeepSeek-V4-Pro
  29. 92.3 Nemotron 3 Nano 30B-A3B Base
  30. 92.3 Claude 3 Sonnet
  31. 92.2 DeepSeek-V2 (MoE-236B, May 2024)
  32. 92.0 GPT-4
  33. 91.7 Nemotron 3.5 Lightning 30B-A3B Base
  34. 91.7 Nemotron 3.5 Super 120B-A12B Base
  35. 91.7 Gemini 1.5 Pro
  36. 91.6 Qwen2.5-7B
  37. 91.6 InternVL3.5-241B-A28B
  38. 91.2 Mistral Large
  39. 91.0 PaLM 2-L
  40. 91.0 phi-3-medium 14B
  41. 90.8 Gemini 1.5 Pro
  42. 90.0 Grok-1.5
  43. 89.6 phi-3-small 7.4B
  44. 89.3 DeepSeek-V3
  45. 89.2 Gemma 3 4B
  46. 88.9 Claude 3 Haiku
  47. 88.7 Phi-3.5-MoE
  48. 88.7 Qwen2.5-Omni-7B
  49. 88.6 Phi-4 Mini
  50. 88.1 Nemotron 3 Ultra 550B-A55B Base
  51. 88.0 Claude 2
  52. 87.6 GLM-4
  53. 87.6 OLMo 2 32B Instruct
  54. 87.3 Granite 4.0 H Small
  55. 86.2 Phi-3.5-mini
  56. 85.6 LFM2.5-1.2B-Thinking
  57. 84.5 Llama 3.1-8B
  58. 84.4 LFM2-8B-A1B
  59. 84.1 DeepSeek LLM 67B
  60. 83.6 Falcon-H1-34B
  61. 82.5 phi-3-mini 3.8B
  62. 81.7 Granite 3.2 8B Instruct
  63. 80.9 Granite 3.3 8B Instruct
  64. 80.7 Mistral Small 3
  65. 79.6 Llama 3-8B
  66. 79.5 Qwen1.5-72B
  67. 79.4 GLM-4.5
  68. 77.6 Apertus 70B
  69. 77.4 Moonlight-16B-A3B
  70. 76.3 granite-4.0-1b
  71. 74.0 Gemma 2 27B
  72. 72.3 ChatGLM3-6B
  73. 68.8 GLM-5
  74. 68.6 Gemma 2 9B
  75. 68.3 OLMo 2 1B Instruct
  76. 67.7 Falcon-Arabic-7B
  77. 62.9 Grok-1
  78. 62.8 Gemma 3 1B
  79. 61.1 Phi-2
  80. 60.1 Qwen-14B
  81. 58.4 Mixtral 8x7B
  82. 58.4 BitNet b1.58 2B4T
  83. 58.3 LFM2-1.2B
  84. 56.8 Llama 2-70B
  85. 54.1 Qwen-7B
  86. 52.2 Mistral 7B v0.1
  87. 46.4 Gemma 7B
  88. 42.2 Llama 2-34B
  89. 28.7 Llama 2-13B
  90. 27.8 Qwen-1_8B
  91. 17.7 Gemma 2B
  92. 14.6 Llama 2-7B
  1. 1 Llama 3.1-405B 96.8%
  2. 2 ERNIE-4.5-300B-A47B 96.6%
  3. 3 Cogito v1 Preview 70B 96.4%
  4. 4 Claude 3.5 Sonnet 96.4%
  5. 5 DiffusionGemma 26B A4B 96.3%
  6. 6 Cogito v2 Preview 671B MoE 96.2%
  7. 7 Qwen2.5-32B 95.9%
  8. 8 Gemma 3 27B 95.9%
  9. 9 Qwen2.5-72B 95.8%
  10. 10 Tulu 3 405B 95.5%
  11. 11 Qwen2.5-VL-72B 95.3%
  12. 12 Llama 3.1-70B 95.1%
  13. 13 Claude 3 Opus 95%
  14. 14 Qwen2.5-14B 94.8%
  15. 15 MiniMax-Text-01 94.8%
  16. 16 Qwen2.5-14B-Instruct-1M 94.8%
  17. 17 Gemini 1.0 Ultra 94.4%
  18. 18 Gemma 3 12B 94.4%
  19. 19 Granite 4.1 30B 94.2%
  20. 20 Sarvam-M 94%
  21. 21 Qwen-Turbo 93.8%
  22. 22 Code World Model (CWM) 93.3%
  23. 23 Qwen2-72B 93.2%
  24. 24 Llama 3-70B 93%
  25. 25 Mistral Large 2 Jul 2024 93%
  26. 26 DeepSeek V4.1 Flash 93%
  27. 27 DeepSeek-V4.1-Flash Base 93%
  28. 28 DeepSeek-V4-Pro 92.6%
  29. 29 Nemotron 3 Nano 30B-A3B Base 92.3%
  30. 30 Claude 3 Sonnet 92.3%
  31. 31 DeepSeek-V2 (MoE-236B, May 2024) 92.2%
  32. 32 GPT-4 Mar 2023 92%
  33. 33 Nemotron 3.5 Lightning 30B-A3B Base 91.7%
  34. 34 Nemotron 3.5 Super 120B-A12B Base 91.7%
  35. 35 Gemini 1.5 Pro Feb 2024 91.7%
  36. 36 Qwen2.5-7B 91.6%
  37. 37 InternVL3.5-241B-A28B 91.6%
  38. 38 Mistral Large 91.2%
  39. 39 PaLM 2-L 91%
  40. 40 phi-3-medium 14B 91%
  41. 41 Gemini 1.5 Pro May 2024 90.8%
  42. 42 Grok-1.5 90%
  43. 43 phi-3-small 7.4B 89.6%
  44. 44 DeepSeek-V3 89.3%
  45. 45 Gemma 3 4B 89.2%
  46. 46 Claude 3 Haiku 88.9%
  47. 47 Phi-3.5-MoE 88.7%
  48. 48 Qwen2.5-Omni-7B 88.7%
  49. 49 Phi-4 Mini 88.6%
  50. 50 Nemotron 3 Ultra 550B-A55B Base 88.1%
  51. 51 Claude 2 88%
  52. 52 GLM-4 87.6%
  53. 53 OLMo 2 32B Instruct 87.6%
  54. 54 Granite 4.0 H Small 87.3%
  55. 55 Phi-3.5-mini 86.2%
  56. 56 LFM2.5-1.2B-Thinking 85.6%
  57. 57 Llama 3.1-8B 84.5%
  58. 58 LFM2-8B-A1B 84.4%
  59. 59 DeepSeek LLM 67B 84.1%
  60. 60 Falcon-H1-34B 83.6%
  61. 61 phi-3-mini 3.8B 82.5%
  62. 62 Granite 3.2 8B Instruct 81.7%
  63. 63 Granite 3.3 8B Instruct 80.9%
  64. 64 Mistral Small 3 80.7%
  65. 65 Llama 3-8B 79.6%
  66. 66 Qwen1.5-72B 79.5%
  67. 67 GLM-4.5 79.4%
  68. 68 Apertus 70B 77.6%
  69. 69 Moonlight-16B-A3B 77.4%
  70. 70 granite-4.0-1b 76.3%
  71. 71 Gemma 2 27B 74%
  72. 72 ChatGLM3-6B 72.3%
  73. 73 GLM-5 68.8%
  74. 74 Gemma 2 9B 68.6%
  75. 75 OLMo 2 1B Instruct 68.3%
  76. 76 Falcon-Arabic-7B 67.7%
  77. 77 Grok-1 62.9%
  78. 78 Gemma 3 1B 62.8%
  79. 79 Phi-2 61.1%
  80. 80 Qwen-14B 60.1%
  81. 81 Mixtral 8x7B 58.4%
  82. 82 BitNet b1.58 2B4T 58.4%
  83. 83 LFM2-1.2B 58.3%
  84. 84 Llama 2-70B 56.8%
  85. 85 Qwen-7B 54.1%
  86. 86 Mistral 7B v0.1 52.2%
  87. 87 Gemma 7B 46.4%
  88. 88 Llama 2-34B 42.2%
  89. 89 Llama 2-13B 28.7%
  90. 90 Qwen-1_8B 27.8%
  91. 91 Gemma 2B 17.7%
  92. 92 Llama 2-7B 14.6%

Source: Labs’ model cards

  1. 1 Claude Opus 4.5 98.1%
  2. 2 Claude Sonnet 4 97.7%
  3. 3 Gemini 3 Flash 97.7%
  4. 4 Gemini 3 Pro 97.5%
  5. 5 Kimi K2.5 Chat 97.5%
  6. 6 Claude Sonnet 4.5 Thinking 97.4%
  7. 7 GPT-5.1 97.4%
  8. 8 Doubao-Seed-1.6 Auto 97.3%
  9. 9 Qwen3-Next-80B-A3B Thinking 97.3%
  10. 10 Kimi K2 Thinking Thinking 97.3%
  11. 11 QwQ-32B 97.2%
  12. 12 o3 97.2%
  13. 13 o4-mini 97.2%
  14. 14 GPT-5 Thinking (High) 97.2%
  15. 15 GPT-5.2 97.2%
  16. 16 Claude 3.7 Sonnet 97.1%
  17. 17 DeepSeek-V3 Mar 2025 97.1%
  18. 18 Step 3 97.1%
  19. 19 DeepSeek-V3.2-Speciale Thinking 97.1%
  20. 20 o3-mini high 97%
  21. 21 Qwen3-Max-Preview 97%
  22. 22 GLM-4.6 97%
  23. 23 Ring-1T 97%
  24. 24 Kimi K2 Jul 2025 97%
  25. 25 Qwen3-235B-A22B-Thinking Jul 2025, Thinking 97%
  26. 26 Qwen3-Next-80B-A3B-Instruct 97%
  27. 27 GPT-4.5 96.9%
  28. 28 Claude Opus 4 96.9%
  29. 29 Gemini 2.5 Pro Jun 2025 96.9%
  30. 30 DeepSeek-V3.1 Thinking 96.9%
  31. 31 DeepSeek-V3 96.8%
  32. 32 ERNIE-4.5-300B-A47B 96.8%
  33. 33 gpt-oss-120b high 96.8%
  34. 34 Claude 3.5 Sonnet (October 2024) 96.7%
  35. 35 DeepSeek-V3.2-Exp Thinking 96.7%
  36. 36 Llama 4 Maverick 96.5%
  37. 37 DeepSeek-R1 May 2025 96.5%
  38. 38 Llama 3.1-405B 96.4%
  39. 39 Hunyuan-T1 96.4%
  40. 40 Qwen3-235B-A22B-Instruct Jul 2025 96.4%
  41. 41 GLM-4.5 96.4%
  42. 42 DeepSeek-V3.1-Terminus Thinking 96.4%
  43. 43 GPT-5.1 Instant 96.4%
  44. 44 DeepSeek-V3.2 Thinking 96.4%
  45. 45 Gemini 2.5 Flash Sep 2025 96.3%
  46. 46 Llama 4 Scout 96.1%
  47. 47 GPT-4.1 96.1%
  48. 48 Qwen3-235B-A22B 96.1%
  49. 49 GPT-4o Nov 2024 96.1%
  50. 50 Gemma 3 27B 96.1%
  51. 51 Qwen2.5-72B 95.9%
  52. 52 MiniMax-M2 95.8%
  53. 53 Qwen3-32B 95.8%
  54. 54 Mistral Large 2 Nov 2024 95.7%
  55. 55 GPT-4o May 2024 95.6%
  56. 56 Grok 4.1 Thinking 95.6%
  57. 57 Grok 3 95.5%
  58. 58 gpt-oss-20b high 95.5%
  59. 59 MiniMax-M1-80k 95.4%
  60. 60 Qwen3-14B Thinking 95.3%
  61. 61 Qwen3-30B-A3B-Thinking Jul 2025, Thinking 95.3%
  62. 62 Llama 3.1-70B 95.2%
  63. 63 Qwen2.5-32B 95.2%
  64. 64 Qwen2.5-14B 95%
  65. 65 Qwen3-30B-A3B 94.8%
  66. 66 Grok 4 94.5%
  67. 67 Gemma 3 12B 94.5%
  68. 68 GPT-4o mini 93.6%
  69. 69 Qwen3-8B 93%
  70. 70 Qwen2.5-7B 91.1%
  71. 71 Gemma 3 4B 89.6%
  72. 72 Gemma 2 9B 87.3%
  73. 73 Llama 3.1-8B 85.3%
  74. 74 Qwen2.5-3B 85.1%
  75. 75 GLM-4-9B 82.9%
  76. 76 Qwen2.5-1.5B 72.1%
  77. 77 Gemma 3 1B 58.9%
  78. 78 Qwen2.5-0.5B 44.3%

Source: AGI-Eval’s leaderboard

208 models. Scroll sideways for the rest.

  1. 98.1 Claude Opus 4.5
  2. 97.7 Claude Sonnet 4
  3. 97.7 Gemini 3 Flash
  4. 97.5 Gemini 3 Pro
  5. 97.5 Kimi K2.5
  6. 97.4 Claude Sonnet 4.5
  7. 97.4 GPT-5.1
  8. 97.3 Doubao-Seed-1.6
  9. 97.3 Qwen3-Next-80B-A3B
  10. 97.3 Kimi K2 Thinking
  11. 97.2 QwQ-32B
  12. 97.2 o3
  13. 97.2 o4-mini
  14. 97.2 GPT-5
  15. 97.2 GPT-5.2
  16. 97.1 Claude 3.7 Sonnet
  17. 97.1 DeepSeek-V3
  18. 97.1 Step 3
  19. 97.1 DeepSeek-V3.2-Speciale
  20. 97.0 o3-mini
  21. 97.0 Qwen3-Max-Preview
  22. 97.0 GLM-4.6
  23. 97.0 Ring-1T
  24. 97.0 Kimi K2
  25. 97.0 Qwen3-235B-A22B-Thinking
  26. 97.0 Qwen3-Next-80B-A3B-Instruct
  27. 96.9 GPT-4.5
  28. 96.9 Claude Opus 4
  29. 96.9 Gemini 2.5 Pro
  30. 96.9 DeepSeek-V3.1
  31. 96.8 DeepSeek-V3
  32. 96.8 ERNIE-4.5-300B-A47B
  33. 96.8 gpt-oss-120b
  34. 96.8 Llama 3.1-405B
  35. 96.7 Claude 3.5 Sonnet (October 2024)
  36. 96.7 DeepSeek-V3.2-Exp
  37. 96.5 Llama 4 Maverick
  38. 96.5 DeepSeek-R1
  39. 96.4 Hunyuan-T1
  40. 96.4 Cogito v1 Preview 70B
  41. 96.4 Qwen3-235B-A22B-Instruct
  42. 96.4 GLM-4.5
  43. 96.4 Claude 3.5 Sonnet
  44. 96.4 DeepSeek-V3.1-Terminus
  45. 96.4 GPT-5.1 Instant
  46. 96.4 DeepSeek-V3.2
  47. 96.3 DiffusionGemma 26B A4B
  48. 96.3 Gemini 2.5 Flash
  49. 96.2 Cogito v2 Preview 671B MoE
  50. 96.1 Llama 4 Scout
  51. 96.1 GPT-4.1
  52. 96.1 Qwen3-235B-A22B
  53. 96.1 GPT-4o
  54. 96.1 Gemma 3 27B
  55. 95.9 Qwen2.5-72B
  56. 95.9 Qwen2.5-32B
  57. 95.8 MiniMax-M2
  58. 95.8 Qwen3-32B
  59. 95.7 Mistral Large 2
  60. 95.6 GPT-4o
  61. 95.6 Grok 4.1
  62. 95.5 Grok 3
  63. 95.5 gpt-oss-20b
  64. 95.5 Tulu 3 405B
  65. 95.4 MiniMax-M1-80k
  66. 95.3 Qwen2.5-VL-72B
  67. 95.3 Qwen3-14B
  68. 95.3 Qwen3-30B-A3B-Thinking
  69. 95.2 Llama 3.1-70B
  70. 95.0 Claude 3 Opus
  71. 95.0 Qwen2.5-14B
  72. 94.8 MiniMax-Text-01
  73. 94.8 Qwen2.5-14B-Instruct-1M
  74. 94.8 Qwen3-30B-A3B
  75. 94.5 Grok 4
  76. 94.5 DeepSeek-Coder-V2 236B
  77. 94.5 Gemma 3 12B
  78. 94.4 Gemini 1.0 Ultra
  79. 94.2 Qwen2.5-Coder-14B-Instruct
  80. 94.2 Granite 4.1 30B
  81. 94.0 Sarvam-M
  82. 93.8 Qwen-Turbo
  83. 93.6 GPT-4o mini
  84. 93.3 Code World Model (CWM)
  85. 93.2 Qwen2-72B
  86. 93.0 Qwen3-8B
  87. 93.0 Llama 3-70B
  88. 93.0 Mistral Large 2
  89. 93.0 Qwen2.5-Coder-32B-Instruct
  90. 93.0 DeepSeek V4.1 Flash
  91. 93.0 DeepSeek-V4.1-Flash Base
  92. 92.6 DeepSeek-V4-Pro
  93. 92.3 Nemotron 3 Nano 30B-A3B Base
  94. 92.3 Claude 3 Sonnet
  95. 92.2 DeepSeek-V2 (MoE-236B, May 2024)
  96. 92.0 GPT-4
  97. 91.7 Nemotron 3.5 Lightning 30B-A3B Base
  98. 91.7 Nemotron 3.5 Super 120B-A12B Base
  99. 91.7 Gemini 1.5 Pro
  100. 91.6 Qwen2.5-7B
  101. 91.6 InternVL3.5-241B-A28B
  102. 91.2 Mistral Large
  103. 91.1 Qwen2.5-Coder-32B
  104. 91.0 PaLM 2-L
  105. 91.0 phi-3-medium 14B
  106. 90.8 Gemini 1.5 Pro
  107. 90.0 Grok-1.5
  108. 90.0 GPT-4
  109. 89.6 Gemma 3 4B
  110. 89.6 phi-3-small 7.4B
  111. 88.9 Claude 3 Haiku
  112. 88.7 Phi-3.5-MoE
  113. 88.7 Qwen2.5-Coder-14B
  114. 88.7 Qwen2.5-Omni-7B
  115. 88.6 Phi-4 Mini
  116. 88.1 Nemotron 3 Ultra 550B-A55B Base
  117. 88.0 Claude 2
  118. 87.6 GLM-4
  119. 87.6 DeepSeek-Coder-V2-Lite-Instruct
  120. 87.6 OLMo 2 32B Instruct
  121. 87.3 Gemma 2 9B
  122. 87.3 Granite 4.0 H Small
  123. 86.7 Claude Instant
  124. 86.7 Qwen2.5-Coder (7B)
  125. 86.2 Phi-3.5-mini
  126. 85.6 LFM2.5-1.2B-Thinking
  127. 85.3 Llama 3.1-8B
  128. 85.1 Qwen2.5-3B
  129. 84.4 LFM2-8B-A1B
  130. 84.2 Mistral NeMo
  131. 84.1 DeepSeek LLM 67B
  132. 83.6 Falcon-H1-34B
  133. 82.9 GLM-4-9B
  134. 82.5 phi-3-mini 3.8B
  135. 82.4 Gemini 1.5 Flash
  136. 81.7 Granite 3.2 8B Instruct
  137. 80.9 Granite 3.3 8B Instruct
  138. 80.7 Mistral Small 3
  139. 80.7 Qwen2.5-Coder-3B-Instruct
  140. 79.6 Llama 3-8B
  141. 79.5 Qwen1.5-72B
  142. 78.2 davinci-003
  143. 77.6 Apertus 70B
  144. 77.4 Moonlight-16B-A3B
  145. 76.3 granite-4.0-1b
  146. 76.0 Yi-34B
  147. 75.7 Qwen2.5-Coder-3B
  148. 74.4 Mixtral 8x7B
  149. 74.0 Gemma 2 27B
  150. 72.3 ChatGLM3-6B
  151. 72.1 Qwen2.5-1.5B
  152. 69.6 Llama 2-70B
  153. 69.6 Stable Beluga 2
  154. 68.8 GLM-5
  155. 68.3 OLMo 2 1B Instruct
  156. 67.7 Falcon-Arabic-7B
  157. 67.1 DeepSeek-Coder-V2-Lite-Base
  158. 65.8 Qwen2.5-Coder (1.5B)
  159. 62.9 internlm-20b
  160. 62.9 Grok-1
  161. 62.8 Gemma 3 1B
  162. 61.3 Qwen-14B
  163. 61.1 Phi-2
  164. 58.4 BitNet b1.58 2B4T
  165. 58.3 LFM2-1.2B
  166. 57.8 GPT-3.5 Turbo
  167. 57.7 StarCoder 2 15B
  168. 56.5 PaLM (540B)
  169. 54.4 LLaMA-65B
  170. 54.4 Falcon-180B
  171. 54.4 Mistral 7B v0.1
  172. 54.1 Qwen-7B
  173. 53.8 Falcon 2 11B
  174. 52.8 Baichuan2-13B
  175. 46.4 Gemma 7B
  176. 46.0 Nemotron-4 15B
  177. 45.7 Baichuan2-13B-Chat
  178. 44.9 Yi 6B
  179. 44.3 Qwen2.5-0.5B
  180. 44.1 LLaMA-33B
  181. 42.2 Llama 2-34B
  182. 38.6 INTELLECT-1
  183. 37.7 CodeQwen1.5-7B
  184. 36.9 Llama 2-13B
  185. 35.4 DeepSeek Coder 33B
  186. 35.4 Mistral 7B v0.2
  187. 34.5 Qwen2.5-Coder-0.5B
  188. 33.0 PaLM 62B
  189. 32.7 StarCoder 2 7B
  190. 32.4 chatglm2-6b
  191. 31.2 internlm-7b
  192. 28.1 vicuna-13b-v1.1
  193. 27.8 Qwen-1_8B
  194. 26.8 Baichuan 1-13B
  195. 24.6 Baichuan 2-7B
  196. 21.6 StarCoder 2 3B
  197. 21.5 Falcon-40B
  198. 21.3 DeepSeek Coder 6.7B
  199. 20.6 LLaMA-13B
  200. 17.7 Gemma 2B
  201. 16.7 Llama 2-7B
  202. 15.7 internlm-chat-20b
  203. 15.2 MPT-30B
  204. 11.0 LLaMA-7B
  205. 9.20 Baichuan1-7B
  206. 9.10 MPT-7B
  207. 6.80 Falcon-7B
  208. 4.40 DeepSeek Coder 1.3B
  1. 1 Claude Opus 4.5 98.1%
  2. 2 Claude Sonnet 4 97.7%
  3. 3 Gemini 3 Flash 97.7%
  4. 4 Gemini 3 Pro 97.5%
  5. 5 Kimi K2.5 Chat 97.5%
  6. 6 Claude Sonnet 4.5 Thinking 97.4%
  7. 7 GPT-5.1 97.4%
  8. 8 Doubao-Seed-1.6 Auto 97.3%
  9. 9 Qwen3-Next-80B-A3B Thinking 97.3%
  10. 10 Kimi K2 Thinking Thinking 97.3%
  11. 11 QwQ-32B 97.2%
  12. 12 o3 97.2%
  13. 13 o4-mini 97.2%
  14. 14 GPT-5 Thinking (High) 97.2%
  15. 15 GPT-5.2 97.2%
  16. 16 Claude 3.7 Sonnet 97.1%
  17. 17 DeepSeek-V3 Mar 2025 97.1%
  18. 18 Step 3 97.1%
  19. 19 DeepSeek-V3.2-Speciale Thinking 97.1%
  20. 20 o3-mini high 97%
  21. 21 Qwen3-Max-Preview 97%
  22. 22 GLM-4.6 97%
  23. 23 Ring-1T 97%
  24. 24 Kimi K2 Jul 2025 97%
  25. 25 Qwen3-235B-A22B-Thinking Jul 2025, Thinking 97%
  26. 26 Qwen3-Next-80B-A3B-Instruct 97%
  27. 27 GPT-4.5 96.9%
  28. 28 Claude Opus 4 96.9%
  29. 29 Gemini 2.5 Pro Jun 2025 96.9%
  30. 30 DeepSeek-V3.1 Thinking 96.9%
  31. 31 DeepSeek-V3 96.8%
  32. 32 ERNIE-4.5-300B-A47B 96.8%
  33. 33 gpt-oss-120b high 96.8%
  34. 34 Llama 3.1-405B 96.8%
  35. 35 Claude 3.5 Sonnet (October 2024) 96.7%
  36. 36 DeepSeek-V3.2-Exp Thinking 96.7%
  37. 37 Llama 4 Maverick 96.5%
  38. 38 DeepSeek-R1 May 2025 96.5%
  39. 39 Hunyuan-T1 96.4%
  40. 40 Cogito v1 Preview 70B 96.4%
  41. 41 Qwen3-235B-A22B-Instruct Jul 2025 96.4%
  42. 42 GLM-4.5 96.4%
  43. 43 Claude 3.5 Sonnet 96.4%
  44. 44 DeepSeek-V3.1-Terminus Thinking 96.4%
  45. 45 GPT-5.1 Instant 96.4%
  46. 46 DeepSeek-V3.2 Thinking 96.4%
  47. 47 DiffusionGemma 26B A4B 96.3%
  48. 48 Gemini 2.5 Flash Sep 2025 96.3%
  49. 49 Cogito v2 Preview 671B MoE 96.2%
  50. 50 Llama 4 Scout 96.1%
  51. 51 GPT-4.1 96.1%
  52. 52 Qwen3-235B-A22B 96.1%
  53. 53 GPT-4o Nov 2024 96.1%
  54. 54 Gemma 3 27B 96.1%
  55. 55 Qwen2.5-72B 95.9%
  56. 56 Qwen2.5-32B 95.9%
  57. 57 MiniMax-M2 95.8%
  58. 58 Qwen3-32B 95.8%
  59. 59 Mistral Large 2 Nov 2024 95.7%
  60. 60 GPT-4o May 2024 95.6%
  61. 61 Grok 4.1 Thinking 95.6%
  62. 62 Grok 3 95.5%
  63. 63 gpt-oss-20b high 95.5%
  64. 64 Tulu 3 405B 95.5%
  65. 65 MiniMax-M1-80k 95.4%
  66. 66 Qwen2.5-VL-72B 95.3%
  67. 67 Qwen3-14B Thinking 95.3%
  68. 68 Qwen3-30B-A3B-Thinking Jul 2025, Thinking 95.3%
  69. 69 Llama 3.1-70B 95.2%
  70. 70 Claude 3 Opus 95%
  71. 71 Qwen2.5-14B 95%
  72. 72 MiniMax-Text-01 94.8%
  73. 73 Qwen2.5-14B-Instruct-1M 94.8%
  74. 74 Qwen3-30B-A3B 94.8%
  75. 75 Grok 4 94.5%
  76. 76 DeepSeek-Coder-V2 236B 94.5%
  77. 77 Gemma 3 12B 94.5%
  78. 78 Gemini 1.0 Ultra 94.4%
  79. 79 Qwen2.5-Coder-14B-Instruct 94.2%
  80. 80 Granite 4.1 30B 94.2%
  81. 81 Sarvam-M 94%
  82. 82 Qwen-Turbo 93.8%
  83. 83 GPT-4o mini 93.6%
  84. 84 Code World Model (CWM) 93.3%
  85. 85 Qwen2-72B 93.2%
  86. 86 Qwen3-8B 93%
  87. 87 Llama 3-70B 93%
  88. 88 Mistral Large 2 Jul 2024 93%
  89. 89 Qwen2.5-Coder-32B-Instruct 93%
  90. 90 DeepSeek V4.1 Flash 93%
  91. 91 DeepSeek-V4.1-Flash Base 93%
  92. 92 DeepSeek-V4-Pro 92.6%
  93. 93 Nemotron 3 Nano 30B-A3B Base 92.3%
  94. 94 Claude 3 Sonnet 92.3%
  95. 95 DeepSeek-V2 (MoE-236B, May 2024) 92.2%
  96. 96 GPT-4 Mar 2023 92%
  97. 97 Nemotron 3.5 Lightning 30B-A3B Base 91.7%
  98. 98 Nemotron 3.5 Super 120B-A12B Base 91.7%
  99. 99 Gemini 1.5 Pro Feb 2024 91.7%
  100. 100 Qwen2.5-7B 91.6%
  101. 101 InternVL3.5-241B-A28B 91.6%
  102. 102 Mistral Large 91.2%
  103. 103 Qwen2.5-Coder-32B 91.1%
  104. 104 PaLM 2-L 91%
  105. 105 phi-3-medium 14B 91%
  106. 106 Gemini 1.5 Pro May 2024 90.8%
  107. 107 Grok-1.5 90%
  108. 108 GPT-4 Jun 2023 90%
  109. 109 Gemma 3 4B 89.6%
  110. 110 phi-3-small 7.4B 89.6%
  111. 111 Claude 3 Haiku 88.9%
  112. 112 Phi-3.5-MoE 88.7%
  113. 113 Qwen2.5-Coder-14B 88.7%
  114. 114 Qwen2.5-Omni-7B 88.7%
  115. 115 Phi-4 Mini 88.6%
  116. 116 Nemotron 3 Ultra 550B-A55B Base 88.1%
  117. 117 Claude 2 88%
  118. 118 GLM-4 87.6%
  119. 119 DeepSeek-Coder-V2-Lite-Instruct 87.6%
  120. 120 OLMo 2 32B Instruct 87.6%
  121. 121 Gemma 2 9B 87.3%
  122. 122 Granite 4.0 H Small 87.3%
  123. 123 Claude Instant 86.7%
  124. 124 Qwen2.5-Coder (7B) 86.7%
  125. 125 Phi-3.5-mini 86.2%
  126. 126 LFM2.5-1.2B-Thinking 85.6%
  127. 127 Llama 3.1-8B 85.3%
  128. 128 Qwen2.5-3B 85.1%
  129. 129 LFM2-8B-A1B 84.4%
  130. 130 Mistral NeMo 84.2%
  131. 131 DeepSeek LLM 67B 84.1%
  132. 132 Falcon-H1-34B 83.6%
  133. 133 GLM-4-9B 82.9%
  134. 134 phi-3-mini 3.8B 82.5%
  135. 135 Gemini 1.5 Flash May 2024 82.4%
  136. 136 Granite 3.2 8B Instruct 81.7%
  137. 137 Granite 3.3 8B Instruct 80.9%
  138. 138 Mistral Small 3 80.7%
  139. 139 Qwen2.5-Coder-3B-Instruct 80.7%
  140. 140 Llama 3-8B 79.6%
  141. 141 Qwen1.5-72B 79.5%
  142. 142 davinci-003 78.2%
  143. 143 Apertus 70B 77.6%
  144. 144 Moonlight-16B-A3B 77.4%
  145. 145 granite-4.0-1b 76.3%
  146. 146 Yi-34B 76%
  147. 147 Qwen2.5-Coder-3B 75.7%
  148. 148 Mixtral 8x7B 74.4%
  149. 149 Gemma 2 27B 74%
  150. 150 ChatGLM3-6B 72.3%
  151. 151 Qwen2.5-1.5B 72.1%
  152. 152 Llama 2-70B 69.6%
  153. 153 Stable Beluga 2 69.6%
  154. 154 GLM-5 68.8%
  155. 155 OLMo 2 1B Instruct 68.3%
  156. 156 Falcon-Arabic-7B 67.7%
  157. 157 DeepSeek-Coder-V2-Lite-Base 67.1%
  158. 158 Qwen2.5-Coder (1.5B) 65.8%
  159. 159 internlm-20b 62.9%
  160. 160 Grok-1 62.9%
  161. 161 Gemma 3 1B 62.8%
  162. 162 Qwen-14B 61.3%
  163. 163 Phi-2 61.1%
  164. 164 BitNet b1.58 2B4T 58.4%
  165. 165 LFM2-1.2B 58.3%
  166. 166 GPT-3.5 Turbo Jun 2023 57.8%
  167. 167 StarCoder 2 15B 57.7%
  168. 168 PaLM (540B) 56.5%
  169. 169 LLaMA-65B 54.4%
  170. 170 Falcon-180B 54.4%
  171. 171 Mistral 7B v0.1 54.4%
  172. 172 Qwen-7B 54.1%
  173. 173 Falcon 2 11B 53.8%
  174. 174 Baichuan2-13B 52.8%
  175. 175 Gemma 7B 46.4%
  176. 176 Nemotron-4 15B 46%
  177. 177 Baichuan2-13B-Chat 45.7%
  178. 178 Yi 6B 44.9%
  179. 179 Qwen2.5-0.5B 44.3%
  180. 180 LLaMA-33B 44.1%
  181. 181 Llama 2-34B 42.2%
  182. 182 INTELLECT-1 38.6%
  183. 183 CodeQwen1.5-7B 37.7%
  184. 184 Llama 2-13B 36.9%
  185. 185 DeepSeek Coder 33B 35.4%
  186. 186 Mistral 7B v0.2 35.4%
  187. 187 Qwen2.5-Coder-0.5B 34.5%
  188. 188 PaLM 62B 33%
  189. 189 StarCoder 2 7B 32.7%
  190. 190 chatglm2-6b 32.4%
  191. 191 internlm-7b 31.2%
  192. 192 vicuna-13b-v1.1 28.1%
  193. 193 Qwen-1_8B 27.8%
  194. 194 Baichuan 1-13B 26.8%
  195. 195 Baichuan 2-7B 24.6%
  196. 196 StarCoder 2 3B 21.6%
  197. 197 Falcon-40B 21.5%
  198. 198 DeepSeek Coder 6.7B 21.3%
  199. 199 LLaMA-13B 20.6%
  200. 200 Gemma 2B 17.7%
  201. 201 Llama 2-7B 16.7%
  202. 202 internlm-chat-20b 15.7%
  203. 203 MPT-30B 15.2%
  204. 204 LLaMA-7B 11%
  205. 205 Baichuan1-7B 9.20%
  206. 206 MPT-7B 9.10%
  207. 207 Falcon-7B 6.80%
  208. 208 DeepSeek Coder 1.3B 4.40%

Sources: AGI-Eval’s leaderboard, labs’ model cards and another board, via Epoch AI (CC BY 4.0)

#ModelScoreSettingDateSource
1 Llama 3.1-405B 96.8% Jul 2024 Lab model card
2 ERNIE-4.5-300B-A47B 96.6% Jun 2025 Lab model card
3 Cogito v1 Preview 70B 96.4% Apr 2025 Lab model card
4 Claude 3.5 Sonnet 96.4% Jun 2024 Lab model card
5 DiffusionGemma 26B A4B 96.3% Jul 2026 Lab model card
6 Cogito v2 Preview 671B MoE 96.2% Jul 2025 Lab model card
7 Qwen2.5-32B 95.9% Dec 2024 Lab model card
8 Gemma 3 27B 95.9% Mar 2025 Lab model card
9 Qwen2.5-72B 95.8% Sep 2024 Lab model card
10 Tulu 3 405B 95.5% Jan 2025 Lab model card
11 Qwen2.5-VL-72B 95.3% Feb 2025 Lab model card
12 Llama 3.1-70B 95.1% Jul 2024 Lab model card
13 Claude 3 Opus 95% Mar 2024 Lab model card
14 Qwen2.5-14B 94.8% Dec 2024 Lab model card
15 MiniMax-Text-01 94.8% Jan 2025 Lab model card
16 Qwen2.5-14B-Instruct-1M 94.8% Jan 2025 Lab model card
17 Gemini 1.0 Ultra 94.4% Dec 2023 Lab model card
18 Gemma 3 12B 94.4% Mar 2025 Lab model card
19 Granite 4.1 30B 94.2% Apr 2026 Lab model card
20 Sarvam-M 94% May 2025 Lab model card
21 Qwen-Turbo 93.8% Dec 2024 Lab model card
22 Code World Model (CWM) 93.3% Sep 2025 Lab model card
23 Qwen2-72B 93.2% Jul 2024 Lab model card
24 Llama 3-70B 93% Apr 2024 Lab model card
25 Mistral Large 2 Jul 2024 93% Jul 2024 Lab model card
26 DeepSeek V4.1 Flash 93% Sep 2026 Lab model card
27 DeepSeek-V4.1-Flash Base 93% Sep 2026 Lab model card
28 DeepSeek-V4-Pro 92.6% Apr 2026 Lab model card
29 Nemotron 3 Nano 30B-A3B Base 92.3% Dec 2025 Lab model card
30 Claude 3 Sonnet 92.3% Mar 2024 Lab model card
31 DeepSeek-V2 (MoE-236B, May 2024) 92.2% May 2024 Lab model card
32 GPT-4 Mar 2023 92% Mar 2023 Lab model card
33 Nemotron 3.5 Lightning 30B-A3B Base 91.7% Oct 2026 Lab model card
34 Nemotron 3.5 Super 120B-A12B Base 91.7% Oct 2026 Lab model card
35 Gemini 1.5 Pro Feb 2024 91.7% Feb 2024 Lab model card
36 Qwen2.5-7B 91.6% Dec 2024 Lab model card
37 InternVL3.5-241B-A28B 91.6% Aug 2025 Lab model card
38 Mistral Large 91.2% Feb 2024 Lab model card
39 PaLM 2-L 91% May 2023 Lab model card
40 phi-3-medium 14B 91% Aug 2024 Lab model card
41 Gemini 1.5 Pro May 2024 90.8% May 2024 Lab model card
42 Grok-1.5 90% Mar 2024 Lab model card
43 phi-3-small 7.4B 89.6% Aug 2024 Lab model card
44 DeepSeek-V3 89.3% Dec 2024 Lab model card
45 Gemma 3 4B 89.2% Mar 2025 Lab model card
46 Claude 3 Haiku 88.9% Mar 2024 Lab model card
47 Phi-3.5-MoE 88.7% Aug 2024 Lab model card
48 Qwen2.5-Omni-7B 88.7% Mar 2025 Lab model card
49 Phi-4 Mini 88.6% Feb 2025 Lab model card
50 Nemotron 3 Ultra 550B-A55B Base 88.1% Jun 2026 Lab model card
51 Claude 2 88% Jul 2023 Lab model card
52 GLM-4 87.6% Jan 2024 Lab model card
53 OLMo 2 32B Instruct 87.6% Mar 2025 Lab model card
54 Granite 4.0 H Small 87.3% Oct 2025 Lab model card
55 Phi-3.5-mini 86.2% Aug 2024 Lab model card
56 LFM2.5-1.2B-Thinking 85.6% Jan 2026 Lab model card
57 Llama 3.1-8B 84.5% Jul 2024 Lab model card
58 LFM2-8B-A1B 84.4% Oct 2025 Lab model card
59 DeepSeek LLM 67B 84.1% Nov 2023 Lab model card
60 Falcon-H1-34B 83.6% May 2025 Lab model card
61 phi-3-mini 3.8B 82.5% Aug 2024 Lab model card
62 Granite 3.2 8B Instruct 81.7% Feb 2025 Lab model card
63 Granite 3.3 8B Instruct 80.9% Apr 2025 Lab model card
64 Mistral Small 3 80.7% Jan 2025 Lab model card
65 Llama 3-8B 79.6% Apr 2024 Lab model card
66 Qwen1.5-72B 79.5% Feb 2024 Lab model card
67 GLM-4.5 79.4% Aug 2025 Lab model card
68 Apertus 70B 77.6% Sep 2025 Lab model card
69 Moonlight-16B-A3B 77.4% Feb 2025 Lab model card
70 granite-4.0-1b 76.3% Oct 2025 Lab model card
71 Gemma 2 27B 74% Jun 2024 Lab model card
72 ChatGLM3-6B 72.3% Oct 2023 Lab model card
73 GLM-5 68.8% Feb 2026 Lab model card
74 Gemma 2 9B 68.6% Jul 2024 Lab model card
75 OLMo 2 1B Instruct 68.3% Apr 2025 Lab model card
76 Falcon-Arabic-7B 67.7% Nov 2025 Lab model card
77 Grok-1 62.9% Nov 2023 Lab model card
78 Gemma 3 1B 62.8% Mar 2025 Lab model card
79 Phi-2 61.1% Dec 2023 Lab model card
80 Qwen-14B 60.1% Sep 2023 Lab model card
81 Mixtral 8x7B 58.4% Dec 2023 Lab model card
82 BitNet b1.58 2B4T 58.4% Apr 2025 Lab model card
83 LFM2-1.2B 58.3% Jul 2025 Lab model card
84 Llama 2-70B 56.8% Jul 2023 Lab model card
85 Qwen-7B 54.1% Sep 2023 Lab model card
86 Mistral 7B v0.1 52.2% Oct 2023 Lab model card
87 Gemma 7B 46.4% Feb 2024 Lab model card
88 Llama 2-34B 42.2% Jul 2023 Lab model card
89 Llama 2-13B 28.7% Jul 2023 Lab model card
90 Qwen-1_8B 27.8% Sep 2023 Lab model card
91 Gemma 2B 17.7% Mar 2024 Lab model card
92 Llama 2-7B 14.6% Jul 2023 Lab model card
#ModelScoreSettingDateSource
1 Claude Opus 4.5 98.1% Nov 2025 Official leaderboard
2 Claude Sonnet 4 97.7% May 2025 Official leaderboard
3 Gemini 3 Flash 97.7% Dec 2025 Official leaderboard
4 Gemini 3 Pro 97.5% Nov 2025 Official leaderboard
5 Kimi K2.5 97.5% Chat Jan 2026 Official leaderboard
6 Claude Sonnet 4.5 97.4% Thinking Sep 2025 Official leaderboard
7 GPT-5.1 97.4% Nov 2025 Official leaderboard
8 Doubao-Seed-1.6 97.3% Auto Jun 2025 Official leaderboard
9 Qwen3-Next-80B-A3B 97.3% Thinking Sep 2025 Official leaderboard
10 Kimi K2 Thinking 97.3% Thinking Nov 2025 Official leaderboard
11 QwQ-32B 97.2% Mar 2025 Official leaderboard
12 o3 97.2% Apr 2025 Official leaderboard
13 o4-mini 97.2% Apr 2025 Official leaderboard
14 GPT-5 97.2% Thinking (High) Aug 2025 Official leaderboard
15 GPT-5.2 97.2% Dec 2025 Official leaderboard
16 Claude 3.7 Sonnet 97.1% Feb 2025 Official leaderboard
17 DeepSeek-V3 Mar 2025 97.1% Mar 2025 Official leaderboard
18 Step 3 97.1% Jul 2025 Official leaderboard
19 DeepSeek-V3.2-Speciale 97.1% Thinking Dec 2025 Official leaderboard
20 o3-mini 97% high Jan 2025 Official leaderboard
21 Qwen3-Max-Preview 97% Sep 2025 Official leaderboard
22 GLM-4.6 97% Sep 2025 Official leaderboard
23 Ring-1T 97% Oct 2025 Official leaderboard
24 Kimi K2 Jul 2025 97% Jul 2025 Official leaderboard
25 Qwen3-235B-A22B-Thinking Jul 2025 97% Thinking Jul 2025 Official leaderboard
26 Qwen3-Next-80B-A3B-Instruct 97% Sep 2025 Official leaderboard
27 GPT-4.5 96.9% Feb 2025 Official leaderboard
28 Claude Opus 4 96.9% May 2025 Official leaderboard
29 Gemini 2.5 Pro Jun 2025 96.9% Jun 2025 Official leaderboard
30 DeepSeek-V3.1 96.9% Thinking Aug 2025 Official leaderboard
31 DeepSeek-V3 96.8% Dec 2024 Official leaderboard
32 ERNIE-4.5-300B-A47B 96.8% Jun 2025 Official leaderboard
33 gpt-oss-120b 96.8% high Aug 2025 Official leaderboard
34 Claude 3.5 Sonnet (October 2024) 96.7% Oct 2024 Official leaderboard
35 DeepSeek-V3.2-Exp 96.7% Thinking Sep 2025 Official leaderboard
36 Llama 4 Maverick 96.5% Apr 2025 Official leaderboard
37 DeepSeek-R1 May 2025 96.5% May 2025 Official leaderboard
38 Llama 3.1-405B 96.4% Jul 2024 Official leaderboard
39 Hunyuan-T1 96.4% Mar 2025 Official leaderboard
40 Qwen3-235B-A22B-Instruct Jul 2025 96.4% Jul 2025 Official leaderboard
41 GLM-4.5 96.4% Aug 2025 Official leaderboard
42 DeepSeek-V3.1-Terminus 96.4% Thinking Sep 2025 Official leaderboard
43 GPT-5.1 Instant 96.4% Nov 2025 Official leaderboard
44 DeepSeek-V3.2 96.4% Thinking Dec 2025 Official leaderboard
45 Gemini 2.5 Flash Sep 2025 96.3% Sep 2025 Official leaderboard
46 Llama 4 Scout 96.1% Apr 2025 Official leaderboard
47 GPT-4.1 96.1% Apr 2025 Official leaderboard
48 Qwen3-235B-A22B 96.1% Apr 2025 Official leaderboard
49 GPT-4o Nov 2024 96.1% Nov 2024 Official leaderboard
50 Gemma 3 27B 96.1% Mar 2025 Official leaderboard
51 Qwen2.5-72B 95.9% Sep 2024 Official leaderboard
52 MiniMax-M2 95.8% Oct 2025 Official leaderboard
53 Qwen3-32B 95.8% Apr 2025 Official leaderboard
54 Mistral Large 2 Nov 2024 95.7% Nov 2024 Official leaderboard
55 GPT-4o May 2024 95.6% May 2024 Official leaderboard
56 Grok 4.1 95.6% Thinking Nov 2025 Official leaderboard
57 Grok 3 95.5% Apr 2025 Official leaderboard
58 gpt-oss-20b 95.5% high Aug 2025 Official leaderboard
59 MiniMax-M1-80k 95.4% Jun 2025 Official leaderboard
60 Qwen3-14B 95.3% Thinking Apr 2025 Official leaderboard
61 Qwen3-30B-A3B-Thinking Jul 2025 95.3% Thinking Jul 2025 Official leaderboard
62 Llama 3.1-70B 95.2% Jul 2024 Official leaderboard
63 Qwen2.5-32B 95.2% Sep 2024 Official leaderboard
64 Qwen2.5-14B 95% Sep 2024 Official leaderboard
65 Qwen3-30B-A3B 94.8% Apr 2025 Official leaderboard
66 Grok 4 94.5% Jul 2025 Official leaderboard
67 Gemma 3 12B 94.5% Mar 2025 Official leaderboard
68 GPT-4o mini 93.6% Jul 2024 Official leaderboard
69 Qwen3-8B 93% Apr 2025 Official leaderboard
70 Qwen2.5-7B 91.1% Sep 2024 Official leaderboard
71 Gemma 3 4B 89.6% Mar 2025 Official leaderboard
72 Gemma 2 9B 87.3% Jun 2024 Official leaderboard
73 Llama 3.1-8B 85.3% Jul 2024 Official leaderboard
74 Qwen2.5-3B 85.1% Sep 2024 Official leaderboard
75 GLM-4-9B 82.9% Jun 2024 Official leaderboard
76 Qwen2.5-1.5B 72.1% Sep 2024 Official leaderboard
77 Gemma 3 1B 58.9% Mar 2025 Official leaderboard
78 Qwen2.5-0.5B 44.3% Sep 2024 Official leaderboard
#ModelScoreSettingDateSource
1 Claude Opus 4.5 98.1% Nov 2025 Official leaderboard
2 Claude Sonnet 4 97.7% May 2025 Official leaderboard
3 Gemini 3 Flash 97.7% Dec 2025 Official leaderboard
4 Gemini 3 Pro 97.5% Nov 2025 Official leaderboard
5 Kimi K2.5 97.5% Chat Jan 2026 Official leaderboard
6 Claude Sonnet 4.5 97.4% Thinking Sep 2025 Official leaderboard
7 GPT-5.1 97.4% Nov 2025 Official leaderboard
8 Doubao-Seed-1.6 97.3% Auto Jun 2025 Official leaderboard
9 Qwen3-Next-80B-A3B 97.3% Thinking Sep 2025 Official leaderboard
10 Kimi K2 Thinking 97.3% Thinking Nov 2025 Official leaderboard
11 QwQ-32B 97.2% Mar 2025 Official leaderboard
12 o3 97.2% Apr 2025 Official leaderboard
13 o4-mini 97.2% Apr 2025 Official leaderboard
14 GPT-5 97.2% Thinking (High) Aug 2025 Official leaderboard
15 GPT-5.2 97.2% Dec 2025 Official leaderboard
16 Claude 3.7 Sonnet 97.1% Feb 2025 Official leaderboard
17 DeepSeek-V3 Mar 2025 97.1% Mar 2025 Official leaderboard
18 Step 3 97.1% Jul 2025 Official leaderboard
19 DeepSeek-V3.2-Speciale 97.1% Thinking Dec 2025 Official leaderboard
20 o3-mini 97% high Jan 2025 Official leaderboard
21 Qwen3-Max-Preview 97% Sep 2025 Official leaderboard
22 GLM-4.6 97% Sep 2025 Official leaderboard
23 Ring-1T 97% Oct 2025 Official leaderboard
24 Kimi K2 Jul 2025 97% Jul 2025 Official leaderboard
25 Qwen3-235B-A22B-Thinking Jul 2025 97% Thinking Jul 2025 Official leaderboard
26 Qwen3-Next-80B-A3B-Instruct 97% Sep 2025 Official leaderboard
27 GPT-4.5 96.9% Feb 2025 Official leaderboard
28 Claude Opus 4 96.9% May 2025 Official leaderboard
29 Gemini 2.5 Pro Jun 2025 96.9% Jun 2025 Official leaderboard
30 DeepSeek-V3.1 96.9% Thinking Aug 2025 Official leaderboard
31 DeepSeek-V3 96.8% Dec 2024 Official leaderboard
32 ERNIE-4.5-300B-A47B 96.8% Jun 2025 Official leaderboard
33 gpt-oss-120b 96.8% high Aug 2025 Official leaderboard
34 Llama 3.1-405B 96.8% Jul 2024 Lab model card
35 Claude 3.5 Sonnet (October 2024) 96.7% Oct 2024 Official leaderboard
36 DeepSeek-V3.2-Exp 96.7% Thinking Sep 2025 Official leaderboard
37 Llama 4 Maverick 96.5% Apr 2025 Official leaderboard
38 DeepSeek-R1 May 2025 96.5% May 2025 Official leaderboard
39 Hunyuan-T1 96.4% Mar 2025 Official leaderboard
40 Cogito v1 Preview 70B 96.4% Apr 2025 Lab model card
41 Qwen3-235B-A22B-Instruct Jul 2025 96.4% Jul 2025 Official leaderboard
42 GLM-4.5 96.4% Aug 2025 Official leaderboard
43 Claude 3.5 Sonnet 96.4% Jun 2024 Lab model card
44 DeepSeek-V3.1-Terminus 96.4% Thinking Sep 2025 Official leaderboard
45 GPT-5.1 Instant 96.4% Nov 2025 Official leaderboard
46 DeepSeek-V3.2 96.4% Thinking Dec 2025 Official leaderboard
47 DiffusionGemma 26B A4B 96.3% Jul 2026 Lab model card
48 Gemini 2.5 Flash Sep 2025 96.3% Sep 2025 Official leaderboard
49 Cogito v2 Preview 671B MoE 96.2% Jul 2025 Lab model card
50 Llama 4 Scout 96.1% Apr 2025 Official leaderboard
51 GPT-4.1 96.1% Apr 2025 Official leaderboard
52 Qwen3-235B-A22B 96.1% Apr 2025 Official leaderboard
53 GPT-4o Nov 2024 96.1% Nov 2024 Official leaderboard
54 Gemma 3 27B 96.1% Mar 2025 Official leaderboard
55 Qwen2.5-72B 95.9% Sep 2024 Official leaderboard
56 Qwen2.5-32B 95.9% Dec 2024 Lab model card
57 MiniMax-M2 95.8% Oct 2025 Official leaderboard
58 Qwen3-32B 95.8% Apr 2025 Official leaderboard
59 Mistral Large 2 Nov 2024 95.7% Nov 2024 Official leaderboard
60 GPT-4o May 2024 95.6% May 2024 Official leaderboard
61 Grok 4.1 95.6% Thinking Nov 2025 Official leaderboard
62 Grok 3 95.5% Apr 2025 Official leaderboard
63 gpt-oss-20b 95.5% high Aug 2025 Official leaderboard
64 Tulu 3 405B 95.5% Jan 2025 Lab model card
65 MiniMax-M1-80k 95.4% Jun 2025 Official leaderboard
66 Qwen2.5-VL-72B 95.3% Feb 2025 Lab model card
67 Qwen3-14B 95.3% Thinking Apr 2025 Official leaderboard
68 Qwen3-30B-A3B-Thinking Jul 2025 95.3% Thinking Jul 2025 Official leaderboard
69 Llama 3.1-70B 95.2% Jul 2024 Official leaderboard
70 Claude 3 Opus 95% Mar 2024 Lab model card
71 Qwen2.5-14B 95% Sep 2024 Official leaderboard
72 MiniMax-Text-01 94.8% Jan 2025 Lab model card
73 Qwen2.5-14B-Instruct-1M 94.8% Jan 2025 Lab model card
74 Qwen3-30B-A3B 94.8% Apr 2025 Official leaderboard
75 Grok 4 94.5% Jul 2025 Official leaderboard
76 DeepSeek-Coder-V2 236B 94.5% Jun 2024 Claim in Qwen2.5-Coder Technical Report, via Epoch AI
77 Gemma 3 12B 94.5% Mar 2025 Official leaderboard
78 Gemini 1.0 Ultra 94.4% Dec 2023 Lab model card
79 Qwen2.5-Coder-14B-Instruct 94.2% Nov 2024 Claim in Qwen2.5-Coder Technical Report, via Epoch AI
80 Granite 4.1 30B 94.2% Apr 2026 Lab model card
81 Sarvam-M 94% May 2025 Lab model card
82 Qwen-Turbo 93.8% Dec 2024 Lab model card
83 GPT-4o mini 93.6% Jul 2024 Official leaderboard
84 Code World Model (CWM) 93.3% Sep 2025 Lab model card
85 Qwen2-72B 93.2% Jul 2024 Lab model card
86 Qwen3-8B 93% Apr 2025 Official leaderboard
87 Llama 3-70B 93% Apr 2024 Lab model card
88 Mistral Large 2 Jul 2024 93% Jul 2024 Lab model card
89 Qwen2.5-Coder-32B-Instruct 93% Nov 2024 Claim in Qwen2.5-Coder Technical Report, via Epoch AI
90 DeepSeek V4.1 Flash 93% Sep 2026 Lab model card
91 DeepSeek-V4.1-Flash Base 93% Sep 2026 Lab model card
92 DeepSeek-V4-Pro 92.6% Apr 2026 Lab model card
93 Nemotron 3 Nano 30B-A3B Base 92.3% Dec 2025 Lab model card
94 Claude 3 Sonnet 92.3% Mar 2024 Lab model card
95 DeepSeek-V2 (MoE-236B, May 2024) 92.2% May 2024 Lab model card
96 GPT-4 Mar 2023 92% Mar 2023 Lab model card
97 Nemotron 3.5 Lightning 30B-A3B Base 91.7% Oct 2026 Lab model card
98 Nemotron 3.5 Super 120B-A12B Base 91.7% Oct 2026 Lab model card
99 Gemini 1.5 Pro Feb 2024 91.7% Feb 2024 Lab model card
100 Qwen2.5-7B 91.6% Dec 2024 Lab model card
101 InternVL3.5-241B-A28B 91.6% Aug 2025 Lab model card
102 Mistral Large 91.2% Feb 2024 Lab model card
103 Qwen2.5-Coder-32B 91.1% Sep 2024 Claim in Qwen2.5-Coder Technical Report, via Epoch AI
104 PaLM 2-L 91% May 2023 Lab model card
105 phi-3-medium 14B 91% Aug 2024 Lab model card
106 Gemini 1.5 Pro May 2024 90.8% May 2024 Lab model card
107 Grok-1.5 90% Mar 2024 Lab model card
108 GPT-4 Jun 2023 90% Jun 2023 Claim in Baichuan 2: Open Large-scale Language Models, via Epoch AI
109 Gemma 3 4B 89.6% Mar 2025 Official leaderboard
110 phi-3-small 7.4B 89.6% Aug 2024 Lab model card
111 Claude 3 Haiku 88.9% Mar 2024 Lab model card
112 Phi-3.5-MoE 88.7% Aug 2024 Lab model card
113 Qwen2.5-Coder-14B 88.7% Sep 2024 Claim in Qwen2.5-Coder Technical Report, via Epoch AI
114 Qwen2.5-Omni-7B 88.7% Mar 2025 Lab model card
115 Phi-4 Mini 88.6% Feb 2025 Lab model card
116 Nemotron 3 Ultra 550B-A55B Base 88.1% Jun 2026 Lab model card
117 Claude 2 88% Jul 2023 Lab model card
118 GLM-4 87.6% Jan 2024 Lab model card
119 DeepSeek-Coder-V2-Lite-Instruct 87.6% Jun 2024 Claim in Qwen2.5-Coder Technical Report, via Epoch AI
120 OLMo 2 32B Instruct 87.6% Mar 2025 Lab model card
121 Gemma 2 9B 87.3% Jun 2024 Official leaderboard
122 Granite 4.0 H Small 87.3% Oct 2025 Lab model card
123 Claude Instant 86.7% Aug 2023 Claim in Releasing Claude Instant 1.2, via Epoch AI
124 Qwen2.5-Coder (7B) 86.7% Sep 2024 Claim in Qwen2.5-Coder Technical Report, via Epoch AI
125 Phi-3.5-mini 86.2% Aug 2024 Lab model card
126 LFM2.5-1.2B-Thinking 85.6% Jan 2026 Lab model card
127 Llama 3.1-8B 85.3% Jul 2024 Official leaderboard
128 Qwen2.5-3B 85.1% Sep 2024 Official leaderboard
129 LFM2-8B-A1B 84.4% Oct 2025 Lab model card
130 Mistral NeMo 84.2% Jul 2024 Claim in Phi-3 Technical Report: A Highly Capable Language Model L…, via Epoch AI
131 DeepSeek LLM 67B 84.1% Nov 2023 Lab model card
132 Falcon-H1-34B 83.6% May 2025 Lab model card
133 GLM-4-9B 82.9% Jun 2024 Official leaderboard
134 phi-3-mini 3.8B 82.5% Aug 2024 Lab model card
135 Gemini 1.5 Flash May 2024 82.4% May 2024 Claim in Phi-3 Technical Report: A Highly Capable Language Model L…, via Epoch AI
136 Granite 3.2 8B Instruct 81.7% Feb 2025 Lab model card
137 Granite 3.3 8B Instruct 80.9% Apr 2025 Lab model card
138 Mistral Small 3 80.7% Jan 2025 Lab model card
139 Qwen2.5-Coder-3B-Instruct 80.7% Nov 2024 Claim in Qwen2.5-Coder Technical Report, via Epoch AI
140 Llama 3-8B 79.6% Apr 2024 Lab model card
141 Qwen1.5-72B 79.5% Feb 2024 Lab model card
142 davinci-003 78.2% Nov 2022 Claim in Qwen Technical Report, via Epoch AI
143 Apertus 70B 77.6% Sep 2025 Lab model card
144 Moonlight-16B-A3B 77.4% Feb 2025 Lab model card
145 granite-4.0-1b 76.3% Oct 2025 Lab model card
146 Yi-34B 76% Nov 2023 Claim in Yi: Open Foundation Models by 01.AI, via Epoch AI
147 Qwen2.5-Coder-3B 75.7% Sep 2024 Claim in Qwen2.5-Coder Technical Report, via Epoch AI
148 Mixtral 8x7B 74.4% Dec 2023 Claim in Mixtral of Experts, via Epoch AI
149 Gemma 2 27B 74% Jun 2024 Lab model card
150 ChatGLM3-6B 72.3% Oct 2023 Lab model card
151 Qwen2.5-1.5B 72.1% Sep 2024 Official leaderboard
152 Llama 2-70B 69.6% Jul 2023 Claim in Mixtral of Experts, via Epoch AI
153 Stable Beluga 2 69.6% Jul 2023 Claim in Qwen Technical Report, via Epoch AI
154 GLM-5 68.8% Feb 2026 Lab model card
155 OLMo 2 1B Instruct 68.3% Apr 2025 Lab model card
156 Falcon-Arabic-7B 67.7% Nov 2025 Lab model card
157 DeepSeek-Coder-V2-Lite-Base 67.1% Jun 2024 Claim in Qwen2.5-Coder Technical Report, via Epoch AI
158 Qwen2.5-Coder (1.5B) 65.8% Sep 2024 Claim in Qwen2.5-Coder Technical Report, via Epoch AI
159 internlm-20b 62.9% Sep 2023 Claim in Yi: Open Foundation Models by 01.AI, via Epoch AI
160 Grok-1 62.9% Nov 2023 Lab model card
161 Gemma 3 1B 62.8% Mar 2025 Lab model card
162 Qwen-14B 61.3% Sep 2023 Claim in Yi: Open Foundation Models by 01.AI, via Epoch AI
163 Phi-2 61.1% Dec 2023 Lab model card
164 BitNet b1.58 2B4T 58.4% Apr 2025 Lab model card
165 LFM2-1.2B 58.3% Jul 2025 Lab model card
166 GPT-3.5 Turbo Jun 2023 57.8% Jun 2023 Claim in Baichuan 2: Open Large-scale Language Models, via Epoch AI
167 StarCoder 2 15B 57.7% Feb 2024 Claim in Qwen2.5-Coder Technical Report, via Epoch AI
168 PaLM (540B) 56.5% Apr 2022 Claim in LLaMA: Open and Efficient Foundation Language Models, via Epoch AI
169 LLaMA-65B 54.4% Feb 2023 Claim in Qwen Technical Report, via Epoch AI
170 Falcon-180B 54.4% Sep 2023 Claim in Yi: Open Foundation Models by 01.AI, via Epoch AI
171 Mistral 7B v0.1 54.4% Sep 2023 Claim in Phi-3 Technical Report: A Highly Capable Language Model L…, via Epoch AI
172 Qwen-7B 54.1% Sep 2023 Lab model card
173 Falcon 2 11B 53.8% May 2024 Claim in Falcon2-11B Technical Report, via Epoch AI
174 Baichuan2-13B 52.8% Sep 2023 Claim in Nemotron-4 15B Technical Report, via Epoch AI
175 Gemma 7B 46.4% Feb 2024 Lab model card
176 Nemotron-4 15B 46% Feb 2024 Claim in Nemotron-4 15B Technical Report, via Epoch AI
177 Baichuan2-13B-Chat 45.7% Sep 2023 Claim in Yi: Open Foundation Models by 01.AI, via Epoch AI
178 Yi 6B 44.9% Nov 2023 Claim in Yi: Open Foundation Models by 01.AI, via Epoch AI
179 Qwen2.5-0.5B 44.3% Sep 2024 Official leaderboard
180 LLaMA-33B 44.1% Feb 2023 Claim in Mixtral of Experts, via Epoch AI
181 Llama 2-34B 42.2% Jul 2023 Lab model card
182 INTELLECT-1 38.6% Nov 2024 Claim in INTELLECT-1 Technical Report, via Epoch AI
183 CodeQwen1.5-7B 37.7% Apr 2024 Claim in Qwen2.5-Coder Technical Report, via Epoch AI
184 Llama 2-13B 36.9% Jul 2023 Claim in Yi: Open Foundation Models by 01.AI, via Epoch AI
185 DeepSeek Coder 33B 35.4% Nov 2023 Claim in Qwen2.5-Coder Technical Report, via Epoch AI
186 Mistral 7B v0.2 35.4% Dec 2023 Claim in Gemma: Open Models Based on Gemini Research and Technology, via Epoch AI
187 Qwen2.5-Coder-0.5B 34.5% Sep 2024 Claim in Qwen2.5-Coder Technical Report, via Epoch AI
188 PaLM 62B 33% Apr 2022 Claim in LLaMA: Open and Efficient Foundation Language Models, via Epoch AI
189 StarCoder 2 7B 32.7% Feb 2024 Claim in Qwen2.5-Coder Technical Report, via Epoch AI
190 chatglm2-6b 32.4% Jun 2023 Claim in Qwen Technical Report, via Epoch AI
191 internlm-7b 31.2% Jul 2023 Claim in Qwen Technical Report, via Epoch AI
192 vicuna-13b-v1.1 28.1% Apr 2023 Claim in Baichuan 2: Open Large-scale Language Models, via Epoch AI
193 Qwen-1_8B 27.8% Sep 2023 Lab model card
194 Baichuan 1-13B 26.8% Jul 2023 Claim in Baichuan 2: Open Large-scale Language Models, via Epoch AI
195 Baichuan 2-7B 24.6% Sep 2023 Claim in Qwen Technical Report, via Epoch AI
196 StarCoder 2 3B 21.6% Feb 2024 Claim in Qwen2.5-Coder Technical Report, via Epoch AI
197 Falcon-40B 21.5% Mar 2023 Claim in Falcon2-11B Technical Report, via Epoch AI
198 DeepSeek Coder 6.7B 21.3% Nov 2023 Claim in Qwen2.5-Coder Technical Report, via Epoch AI
199 LLaMA-13B 20.6% Feb 2023 Claim in Baichuan 2: Open Large-scale Language Models, via Epoch AI
200 Gemma 2B 17.7% Mar 2024 Lab model card
201 Llama 2-7B 16.7% Jul 2023 Claim in Yi: Open Foundation Models by 01.AI, via Epoch AI
202 internlm-chat-20b 15.7% Sep 2023 Claim in Yi: Open Foundation Models by 01.AI, via Epoch AI
203 MPT-30B 15.2% Jun 2023 Claim in Llama 2: Open Foundation and Fine-Tuned Chat Models, via Epoch AI
204 LLaMA-7B 11% Feb 2023 Claim in Llama 2: Open Foundation and Fine-Tuned Chat Models, via Epoch AI
205 Baichuan1-7B 9.20% Jun 2023 Claim in Baichuan 2: Open Large-scale Language Models, via Epoch AI
206 MPT-7B 9.10% May 2023 Claim in Qwen Technical Report, via Epoch AI
207 Falcon-7B 6.80% Apr 2023 Claim in Llama 2: Open Foundation and Fine-Tuned Chat Models, via Epoch AI
208 DeepSeek Coder 1.3B 4.40% Nov 2023 Claim in Qwen2.5-Coder Technical Report, via Epoch AI

AGI-Eval’s leaderboard has 92 entries, 78 of them models we track. Epoch AI collected claims for 70 models from labs’ reports and papers. Switch the scores above to rank them together.

Scores at each effort level

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

Lowest effort to highest, light to dark
Claude Opus 4.5
no-reasoning
98.1%
Claude Sonnet 4
Thinking
97.7%
Kimi K2.5
Thinking Chat
97.5%
Claude Sonnet 4.5
Thinking
97.4%
Doubao-Seed-1.6
Thinking On Auto
97.3%
GPT-5
Thinking (H…
97.2%
Claude 3.7 Sonnet
Thinking
97.1%
o3-mini
medium
97%
Claude Opus 4
Thinking
96.9%
DeepSeek-V3.1
Thinking
96.9%
DeepSeek-V3.2-Exp
Thinking
96.7%
DeepSeek-V3.1-Terminus
Thinking
96.4%

Source: AGI-Eval’s leaderboard

ModelEffortHarnessScoreCost per taskOutput tokens
Claude Opus 4.5 98.1%
Claude Sonnet 4 97.7%
Claude Opus 4.5 no-reasoning 97.7%
Gemini 3 Flash 97.7%
Gemini 3 Pro 97.5%
Kimi K2.5 Chat 97.5%
Claude Sonnet 4.5 Thinking 97.4%
GPT-5.1 97.4%
Claude Sonnet 4.5 97.3%
Doubao-Seed-1.6 Auto 97.3%
Qwen3-Next-80B-A3B Thinking 97.3%
Kimi K2 Thinking Thinking 97.3%
QwQ-32B 97.2%
o3 97.2%
o4-mini 97.2%
GPT-5 Thinking (High) 97.2%
GPT-5.2 97.2%
Claude 3.7 Sonnet 97.1%
DeepSeek-V3 Mar 2025 97.1%
Step 3 97.1%
DeepSeek-V3.2-Speciale Thinking 97.1%
Kimi K2.5 Thinking 97.1%
o3-mini high 97%
Claude 3.7 Sonnet Thinking 97%
Qwen3-Max-Preview 97%
GLM-4.6 97%
Ring-1T 97%
o3-mini medium 97%
Claude Sonnet 4 Thinking 97%
Kimi K2 Jul 2025 97%
Qwen3-235B-A22B-Thinking Jul 2025 Thinking 97%
Qwen3-Next-80B-A3B-Instruct 97%
GPT-4.5 96.9%
Claude Opus 4 96.9%
Gemini 2.5 Pro Jun 2025 96.9%
DeepSeek-V3.1 Thinking 96.9%
DeepSeek-V3 96.8%
Claude Opus 4 Thinking 96.8%
Doubao-Seed-1.6 On 96.8%
ERNIE-4.5-300B-A47B 96.8%
Qwen3-235B-A22B-Thinking Jul 2025 Thinking 96.8%
gpt-oss-120b high 96.8%
Claude 3.5 Sonnet (October 2024) 96.7%
Doubao-Seed-1.6 Off 96.7%
DeepSeek-V3.2-Exp Thinking 96.7%
Doubao-Seed-1.6 Thinking 96.6%
Llama 4 Maverick 96.5%
DeepSeek-R1 May 2025 96.5%
Llama 3.1-405B 96.4%
Hunyuan-T1 96.4%
Qwen3-235B-A22B-Instruct Jul 2025 96.4%
GLM-4.5 96.4%
DeepSeek-V3.1-Terminus Thinking 96.4%
GPT-5.1 Instant 96.4%
DeepSeek-V3.2 Thinking 96.4%
DeepSeek-V3.1 96.3%
Gemini 2.5 Flash Sep 2025 96.3%
DeepSeek-V3.2 non-thinking, Chat 96.2%
Llama 4 Scout 96.1%
GPT-4.1 96.1%
Qwen3-235B-A22B 96.1%
GPT-5 96.1%
GPT-4o Nov 2024 96.1%
Gemma 3 27B 96.1%
DeepSeek-V3.1-Terminus 96.1%
Gemini 2.5 Flash Sep 2025 96%
Qwen2.5-72B 95.9%
DeepSeek-R1 May 2025 95.9%
DeepSeek-V3.2-Exp 95.9%
MiniMax-M2 95.8%
Qwen3-32B 95.8%
Mistral Large 2 Nov 2024 95.7%
GPT-4o May 2024 95.6%
Grok 4.1 Thinking 95.6%
Grok 3 95.5%
Qwen3-32B Thinking 95.5%
gpt-oss-20b high 95.5%
MiniMax-M1-80k 95.4%
Qwen3-14B Thinking 95.3%
Qwen3-30B-A3B-Thinking Jul 2025 Thinking 95.3%
Llama 3.1-70B 95.2%
Qwen2.5-32B 95.2%
Qwen2.5-14B 95%
Qwen3-14B 94.9%
Qwen3-30B-A3B 94.8%
Grok 4 94.5%
Gemma 3 12B 94.5%
GPT-4o mini 93.6%
Qwen3-8B 93%
Qwen2.5-7B 91.1%
Gemma 3 4B 89.6%
Gemma 2 9B 87.3%
Llama 3.1-8B 85.3%
Qwen2.5-3B 85.1%
GLM-4-9B 82.9%
Qwen2.5-1.5B 72.1%
Gemma 3 1B 58.9%
Qwen2.5-0.5B 44.3%

5 models have held number one in labs’ own numbers since 2023 9 models have held number one across all independent runs since 2023 13 models have held number one with claims included since 2023

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

OpenAI Meta Anthropic DeepSeek Qwen Google DeepMind
AGI-Eval leaderboard Passed 85% in May 2024, by GPT-4o
Lab claims Passed 85% in Mar 2023, by GPT-4

Sources: AGI-Eval’s leaderboard and labs’ model cards

OpenAI’s own number for GPT-4 passed 85% in March 2023

That was 17 months after its release. All the scores we have, one dot each, so a model tested at several settings appears more than once.

Plot with other benchmarks
On AGI-Eval’s leaderboard Reported by the lab in its model card A claim Epoch AI collected from a report or paper Best so far
0% 20% 40% 60% 80% 100% 2022 2023 2024 2025 2026 Near the ceiling (85%) Claude Opus 4.5 Claude 3.7 Sonnet GPT-4o GPT-4 davinci-003 PaLM (540B) 0% 20% 40% 60% 80% 100% 2022 2023 2024 2025 2026 Near the ceiling (85%) Claude Opus 4.5 GPT-4

Sources: AGI-Eval’s leaderboard, labs’ model cards and claims collected by Epoch AI (CC BY 4.0)

Labs headline it less often now, last in September 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
Google DeepMind
Anthropic
Qwen
Mistral AI
Z.ai
xAI
DeepSeek
Microsoft
Meta
MiniMax
Ai2
Moonshot AI
IBM
Baidu
Deep Cogito
Technology Innovation Institute
Sarvam AI
Liquid AI
DateLaunch postScoreAs the post writes it
Sep 10, 2026 DeepSeek V4.1 Flash 93 GSM8K (EM)
Apr 29, 2026 Granite 4.1 30B 94.2 GSM8K (8-shot)
Apr 24, 2026 DeepSeek-V4-Pro 92.6 GSM8K (EM)
Jan 20, 2026 LFM2.5-1.2B-Thinking 85.6 GSM8K
Oct 28, 2025 granite-4.0-1b 76.3 GSM8K (8-shot)
Oct 7, 2025 LFM2-8B-A1B 84.4 GSM8K
Oct 2, 2025 Granite 4.0 H Small 87.3 GSM8K (8-shot)
Jul 31, 2025 Cogito v2 Preview 671B MoE 96.2 GSM8K (thinking)
Jul 10, 2025 LFM2-1.2B 58.3 GSM8K
Jun 30, 2025 ERNIE-4.5-300B-A47B 96.6 GSM8K
May 23, 2025 Sarvam-M 94 GSM-8K (0.94)
May 20, 2025 Falcon-H1-34B 83.6 GSM8k
Apr 29, 2025 OLMo 2 1B Instruct 68.3 GSM8K
Apr 16, 2025 Granite 3.3 8B Instruct 80.9 GSM8K
Apr 15, 2025 BitNet b1.58 2B4T 58.4 GSM8K
Apr 8, 2025 Cogito v1 Preview 70B 96.4 GSM8K (thinking)
Mar 27, 2025 Qwen2.5-Omni-7B 88.7 GSM8K
Mar 16, 2025 ERNIE 4.5 GSM8K
Mar 13, 2025 OLMo 2 32B Instruct 87.6 GSM8k
Mar 12, 2025 Gemma 3 27B 95.9 GSM8K 0-shot (IT); PT 8-shot = 82.6
Feb 26, 2025 Phi-4 Mini 88.6 GSM8K (8-shot, CoT)
Feb 26, 2025 Granite 3.2 8B Instruct 81.7 GSM8K
Feb 22, 2025 Moonlight-16B-A3B 77.4 GSM8K
Jan 30, 2025 Tulu 3 405B 95.5 GSM8K (8 shot, CoT)
Jan 30, 2025 Mistral Small 3 80.7 GSM8K (5-shot, maj@1) [base]
Jan 28, 2025 Qwen2.5-Max GSM8K
Jan 15, 2025 MiniMax-Text-01 94.8 GSM8k*
Dec 26, 2024 DeepSeek-V3 89.3 GSM8K (EM)
Sep 19, 2024 Qwen2.5-72B 95.8 GSM8K
Aug 20, 2024 Phi-3.5-MoE 88.7 GSM8K (8-shot, CoT)
Jul 24, 2024 Mistral Large 2 93 GSM8K (8-shot)
Jul 23, 2024 Llama 3.1-405B 96.8 GSM8K (8-shot, CoT)
Jun 27, 2024 Gemma 2 27B 74 GSM8K (5-shot, maj@1)
Jun 20, 2024 Claude 3.5 Sonnet 96.4 GSM8K (0-shot CoT)
Jun 7, 2024 Qwen2-72B 91.1 GSM8K
May 14, 2024 Gemini 1.5 Pro 90.8 GSM8K, 11-shot
May 7, 2024 DeepSeek-V2 (MoE-236B, May 2024) 92.2 GSM8K
Apr 22, 2024 phi-3-medium 14B 90.3 GSM-8K (0-Shot; CoT)
Apr 18, 2024 Llama 3-70B 93 GSM-8K (8-shot, CoT) [instruct]
Mar 28, 2024 Grok-1.5 90 GSM8K (8-shot, maj@1)
Mar 4, 2024 Claude 3 Opus 95 GSM8K (0-shot CoT)
Feb 26, 2024 Mistral Large 91.2 GSM8K maj@8 (8-shot) [maj@1 (5-shot) = 81.0]
Feb 21, 2024 Gemma 7B 46.4 GSM8K (maj@1)
Feb 15, 2024 Gemini 1.5 Pro 91.7 GSM8K, 11-shot
Feb 5, 2024 Qwen1.5-72B 79.5 GSM8K
Jan 16, 2024 GLM-4 87.6 GSM8K (5-shot)
Dec 12, 2023 Phi-2 61.1 Math (GSM8k, 8-shot)
Dec 11, 2023 Mixtral 8x7B 58.4 GSM-8K (5-shot) [detailed table: 74.4]
Dec 6, 2023 Gemini 1.0 Ultra 94.4 GSM8K, Maj1@32
Nov 29, 2023 DeepSeek LLM 67B 84.1 GSM8K
Nov 3, 2023 Grok-1 62.9 GSM8k (8-shot)
Oct 27, 2023 ChatGLM3-6B 72.3 GSM8K
Sep 27, 2023 Mistral 7B v0.1 52.1 GSM8K (8-shot, maj@8)
Sep 25, 2023 Qwen-14B 60.1 GSM8K (0-shot)
Jul 11, 2023 Claude 2 88 GSM8k (0-shot CoT)
May 10, 2023 PaLM 2-L 91 GSM8K, CoT + self-consistency (greedy CoT = 80.7)
Mar 14, 2023 GPT-4 92 GSM-8K (5-shot chain-of-thought)

72 system cards report it, from 17 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
Oct 15, 2026 Nemotron 3.5 Super 120B-A12B Base technical report 91.7 GSM8K, 8-shot CoT exact match, Table 6 Capabilities
Oct 15, 2026 Nemotron 3.5 Lightning 30B-A3B Base technical report 91.7 GSM8K, 8-shot CoT exact match, Table 6 Capabilities
Sep 10, 2026 DeepSeek-V4.1-Flash Base model card 93 GSM8K, EM, 8-shot Capabilities
Jul 31, 2026 DiffusionGemma 26B A4B technical report 96.3 GSM8K, TD, 95.8 no-think (Table 3) Capabilities
Jun 4, 2026 Nemotron 3 Ultra 550B-A55B Base model card 88.1 GSM8K, 8-shot CoT EM Capabilities
Feb 17, 2026 GLM-5 technical report 68.8 GLM-5-Base, GSM8K (EM) (Table 11) Capabilities
Dec 23, 2025 Nemotron 3 Nano 30B-A3B Base technical report 92.3 GSM8K, 8-shot accuracy, base model Table 2 Capabilities
Nov 28, 2025 LFM2-8B-A1B technical report 84.4 GSM8K, LFM2-8B-A1B (Table 7) Capabilities
Nov 28, 2025 LFM2-1.2B technical report 58.3 GSM8K, LFM2-1.2B (Table 6) Capabilities
Nov 8, 2025 Falcon-Arabic-7B technical report 67.7 GSM8K 5-shot, English (Table 8). Arabic-GSM8K exact match 54.89 (Table 7) Capabilities
Oct 8, 2025 OLMo 2 1B Instruct technical report 68.3 GSM8K (Table 7, Table 23) Capabilities
Sep 30, 2025 Code World Model (CWM) technical report 93.3 GSM8k, without reasoning (Table 13) Capabilities
Sep 17, 2025 Apertus 70B technical report 77.6 GSM8K, 8-shot CoT (Table 18) Capabilities
Aug 25, 2025 InternVL3.5-241B-A28B technical report 91.6 GSM8K, OpenCompass (Table 14) Capabilities
Aug 8, 2025 GLM-4.5 technical report 79.4 GLM-4.5-Base, GSM8K (EM) (Table 2) Capabilities
Jul 30, 2025 Falcon-H1-34B technical report 83.6 GSM8k, strict match 5-shot (Table 24) Capabilities
Jul 17, 2025 Voxtral Small technical report GSM8K 8-shot, text-only, chart without printed numbers (Figure 6). Speech-synthesized GSM8k* 89.7 (Table 8) Capabilities
Jun 29, 2025 ERNIE-4.5-300B-A47B technical report 96.6 GSM8K (Table 5) Capabilities
Apr 16, 2025 BitNet b1.58 2B4T technical report 58.4 GSM8K (4-shot; EM) (Table 1, Table 2) Capabilities
Mar 26, 2025 Qwen2.5-Omni-7B technical report 88.7 GSM8K (Table 1) Capabilities
Mar 25, 2025 Gemma 3 4B technical report 89.2 GSM8K, IT, 0-shot CoT (Table 18) Capabilities
Mar 25, 2025 Gemma 3 27B technical report 95.9 GSM8K, IT, 0-shot CoT (Table 18) Capabilities
Mar 25, 2025 Gemma 3 1B technical report 62.8 GSM8K, IT, 0-shot CoT (Table 18) Capabilities
Mar 25, 2025 Gemma 3 12B technical report 94.4 GSM8K, IT, 0-shot CoT (Table 18) Capabilities
Mar 3, 2025 Phi-4 Mini technical report 88.6 GSM-8K (8-Shot, CoT) (Table 7) Capabilities
Feb 19, 2025 Qwen2.5-VL-72B technical report 95.3 GSM8K (Table 4) Capabilities
Jan 26, 2025 Qwen2.5-14B-Instruct-1M technical report 94.8 GSM8K (Table 6) Capabilities
Jan 14, 2025 MiniMax-Text-01 technical report 94.8 GSM8k, 0-shot CoT (Table 8) Capabilities
Dec 31, 2024 OLMo 2 32B Instruct technical report 87.6 GSM8K, 8-shot CoT (Tables 7 and 16) Capabilities
Dec 19, 2024 Qwen2.5-7B technical report 91.6 GSM8K, Qwen2.5-7B-Instruct (Table 8) Capabilities
Dec 19, 2024 Qwen2.5-72B technical report 95.8 GSM8K, Qwen2.5-72B-Instruct (Table 6) Capabilities
Dec 19, 2024 Qwen2.5-32B technical report 95.9 GSM8K, Qwen2.5-32B-Instruct (Table 7) Capabilities
Dec 19, 2024 Qwen2.5-14B technical report 94.8 GSM8K, Qwen2.5-14B-Instruct (Table 7) Capabilities
Dec 19, 2024 Qwen-Turbo technical report 93.8 GSM8K, Qwen2.5-Turbo (Table 7) Capabilities
Nov 23, 2024 Llama 3.1-8B technical report 84.5 GSM8K (8-shot, CoT), post-trained (Table 2). Pretrained many-shot GSM8K (16-shot) = 60.0 (Table 14) Capabilities
Nov 23, 2024 Llama 3.1-70B technical report 95.1 GSM8K (8-shot, CoT), post-trained (Table 2). Pretrained many-shot GSM8K (16-shot) = 83.0 (Table 14) Capabilities
Nov 23, 2024 Llama 3.1-405B technical report 96.8 GSM8K (8-shot, CoT), post-trained (Table 2). Pretrained many-shot GSM8K (16-shot) = 90.0 (Table 14) Capabilities
Nov 22, 2024 Tulu 3 405B technical report 95.5 GSM8K (8 shot, CoT), RLVR (Table 4) Capabilities
Aug 30, 2024 phi-3-small 7.4B technical report 89.6 GSM-8K (8-Shot, CoT) (Section 3 table) Capabilities
Aug 30, 2024 phi-3-mini 3.8B technical report 82.5 GSM-8K (8-Shot, CoT) (Section 3 table) Capabilities
Aug 30, 2024 phi-3-medium 14B technical report 91 GSM-8K (8-Shot, CoT) (Section 3 table) Capabilities
Aug 30, 2024 Phi-3.5-MoE technical report 88.7 GSM8K (8-shot, CoT) (Table 3) Capabilities
Aug 30, 2024 Phi-3.5-mini technical report 86.2 GSM8K (8-shot, CoT) (Table 3) Capabilities
Jul 31, 2024 Gemma 2 9B technical report 68.6 GSM8K, PT, 5-shot (Table 13) Capabilities
Jul 31, 2024 Gemma 2 27B technical report 74 GSM8K, PT, 5-shot (Table 13) Capabilities
Jul 23, 2024 Llama 3.1-8B model card 84.5 GSM-8K (CoT), 8-shot, em_maj1@1, instruction tuned (Instruction tuned models table) Capabilities
Jul 23, 2024 Llama 3.1-70B model card 95.1 GSM-8K (CoT), 8-shot, em_maj1@1, instruction tuned (Instruction tuned models table) Capabilities
Jul 23, 2024 Llama 3.1-405B model card 96.8 GSM-8K (CoT), 8-shot, em_maj1@1, instruction tuned (Instruction tuned models table) Capabilities
Jul 15, 2024 Qwen2-72B technical report 93.2 GSM8K, Qwen2-72B-Instruct (Table 6) Capabilities
Jun 20, 2024 Claude 3.5 Sonnet model card 96.4 GSM8K, 0-shot CoT (Table 1) Capabilities
Jun 18, 2024 GLM-4 technical report 87.6 GLM-4 (0116), GSM8K, chain-of-thought (Table 2) Capabilities
Jun 18, 2024 ChatGLM3-6B technical report 72.3 ChatGLM3-6B-Base, GSM8K (Table 1) Capabilities
May 7, 2024 DeepSeek-V2 (MoE-236B, May 2024) technical report 92.2 GSM8K 8-shot, DeepSeek-V2 Chat (RL) (Table 3) Capabilities
Apr 18, 2024 Llama 3-8B model card 79.6 GSM-8K (8-shot, CoT), instruction tuned (Instruction tuned models table) Capabilities
Apr 18, 2024 Llama 3-70B model card 93 GSM-8K (8-shot, CoT), instruction tuned (Instruction tuned models table) Capabilities
Mar 13, 2024 Gemma 7B technical report 46.4 GSM8K, PT, maj@1 (Table 6). HuggingFace H6 run (Table 7): 50.9 Capabilities
Mar 13, 2024 Gemma 2B technical report 17.7 GSM8K, PT, maj@1 (Table 6) Capabilities
Mar 4, 2024 Claude 3 Sonnet model card 92.3 GSM8K, 0-shot CoT (Table 1) Capabilities
Mar 4, 2024 Claude 3 Opus model card 95 GSM8K, 0-shot CoT (Table 1) Capabilities
Mar 4, 2024 Claude 3 Haiku model card 88.9 GSM8K, 0-shot CoT (Table 1) Capabilities
Jan 8, 2024 Mixtral 8x7B technical report 58.4 GSM-8K, 5-shot (Table 3). 8-shot maj@8 74.4 (Table 2) Capabilities
Jan 5, 2024 DeepSeek LLM 67B technical report 84.1 GSM8K 0-shot, chain of thought, DeepSeek 67B Chat (Table 6). 86.7 with tool-integrated reasoning (Table 16) Capabilities
Oct 10, 2023 Mistral 7B v0.1 technical report 52.2 GSM8K, 8-shot maj@8 (Table 2) Capabilities
Sep 28, 2023 Qwen-7B technical report 54.1 GSM8K 8-shot, higher of the two settings, 0-shot 50.3 (Table 5) Capabilities
Sep 28, 2023 Qwen-14B technical report 60.1 GSM8K 0-shot, higher of the two settings, 8-shot 59.3 (Table 5) Capabilities
Sep 28, 2023 Qwen-1_8B technical report 27.8 GSM8K 0-shot, higher of the two settings, 8-shot 19.5 (Table 5) Capabilities
Jul 19, 2023 Llama 2-7B technical report 14.6 GSM8k, 8-shot, maj1@1, pretrained (Table 25) Capabilities
Jul 19, 2023 Llama 2-70B technical report 56.8 GSM8k, 8-shot, maj1@1, pretrained (Table 25) Capabilities
Jul 19, 2023 Llama 2-34B technical report 42.2 GSM8k, 8-shot, maj1@1, pretrained (Table 25) Capabilities
Jul 19, 2023 Llama 2-13B technical report 28.7 GSM8k, 8-shot, maj1@1, pretrained (Table 25) Capabilities
Jul 11, 2023 Claude 2 model card 88 GSM8k (0-shot CoT) (4.3) Capabilities
Mar 14, 2023 GPT-4 technical report 92 GSM-8K, 5-shot chain-of-thought, part of the training set in pre-training mix (Table 2, base model) Capabilities

The lab's number comes out ahead in 4 of 12 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. 3 of them match, which usually means one side copied the other. Every benchmark.

Model Lab says Board says Gap
Gemma 2 9B 68.6% GSM8K, PT, 5-shot (Table 13) 87.3% Leaderboard −19 pts
GLM-4.5 79.4% GLM-4.5-Base, GSM8K (EM) (Table 2) 96.4% Leaderboard −17 pts
DeepSeek-V3 89.3% GSM8K (EM) 96.8% Leaderboard −7.5 pts
Gemma 3 1B 62.8% GSM8K, IT, 0-shot CoT (Table 18) 58.9% Leaderboard +3.9 pts
Llama 3.1-8B 84.5% GSM-8K (CoT), 8-shot, em_maj1@1, instruction tuned (Instruction tuned models table) 85.3% Leaderboard −0.8 pts
Qwen2.5-32B 95.9% GSM8K, Qwen2.5-32B-Instruct (Table 7) 95.2% Leaderboard +0.7 pts
Qwen2.5-7B 91.6% GSM8K, Qwen2.5-7B-Instruct (Table 8) 91.1% Leaderboard +0.5 pts
Gemma 3 4B 89.2% GSM8K, IT, 0-shot CoT (Table 18) 89.6% Leaderboard −0.4 pts
Llama 3.1-405B 96.8% GSM8K (8-shot, CoT) 96.4% Leaderboard +0.4 pts
ERNIE-4.5-300B-A47B 96.6% GSM8K 96.8% Leaderboard −0.2 pts
Qwen2.5-14B 94.8% GSM8K, Qwen2.5-14B-Instruct (Table 7) 95% Leaderboard −0.2 pts
Gemma 3 27B 95.9% GSM8K 0-shot (IT); PT 8-shot = 82.6 96.1% Leaderboard −0.2 pts
Llama 3.1-70B 95.1% GSM-8K (CoT), 8-shot, em_maj1@1, instruction tuned (Instruction tuned models table) 95.2% Leaderboard Same
Qwen2.5-72B 95.8% GSM8K 95.9% Leaderboard Same
Gemma 3 12B 94.4% GSM8K, IT, 0-shot CoT (Table 18) 94.5% Leaderboard Same

Versions

More in Math

All 140 in Math
  • 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%
  • 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%

Data audit

8 of 10 checks pass, 1 warning, 1 problem. Look first at the Known issues check. 1 open finding: Contamination. Every benchmark

Catalog record 2 pass
  • Pass Task access All tasks are public.
  • Pass Confidence Checked against a primary source.
Scores 3 pass 2 notes
  • Pass Independent runs Scores from the official leaderboard (92 entries), launch posts (55 scores), system cards (71 scores) and claims Epoch AI collected (70 models).
  • Pass Models scored 208 models we track, plus 14 other entries on its leaderboard.
  • Pass Newest score The newest is from October 2026, for Nemotron 3.5 Lightning 30B-A3B Base.
  • Note Frontier models None of the top 10 has a score, which is fine for a retired test. The strongest tested is DeepSeek V4.1 Flash (#34).
  • Note Headroom Saturated. The best is 98.1%, past 85% since March 2023.
Leaderboard import 3 pass
  • Pass Importer We read the board on AGI-Eval: 98 rows for models we track and 14 other entries at the last read.
  • Pass Last read November 20th, 2026.
  • Pass Read worked The last read worked.
Consistency 1 problem 1 warning
  • Warning Lab claims 2 of 15 pairs differ by more than 10 points, the largest for Gemma 2 9B (−19 pts).
  • Problem Known issues 1 open finding: Contamination.

How we check