Vai al contenuto
AI.info

Model Tracker

GPQA Diamond leaderboard

The models in the Model Tracker that Epoch AI has measured on GPQA Diamond, ranked by the highest score of each: the name Epoch AI gives it, the setting it ran and the day. Epoch AI, ‘Capabilities & benchmarking’, epoch.ai/benchmarks, CC BY

In inglese

The models in the Model Tracker that Epoch AI has measured on GPQA Diamond, ranked by the highest score of each: the name Epoch AI gives it, the setting it ran and the day. Epoch AI, ‘Capabilities & benchmarking’, epoch.ai/benchmarks, CC BY 4.0: Epoch AI’s own runs and its Capabilities Index.

  1. 1. Gemini 4 Argon: 96.4% (± 1.2) — gemini-4-argon_high, high, 13 October 2026
  2. 2. GPT-6 Astra: 95.8% (± 1.4) — gpt-6-astra_max, max, 30 August 2026
  3. 3. Claude Sonnet 5.5: 95.6% (± 1.4) — claude-sonnet-5-5_max, max, 29 September 2026
  4. 4. GPT-6.1 Sol: 95.4% (± 1.4) — gpt-6.1-sol_max, max, 29 September 2026
  5. 4. Gemini 3.8 Flash: 95.4% (± 1.4) — gemini-3.8-flash_high, high, 2 September 2026
  6. 6. Gemini 3.7 Flash: 94.8% (± 1.3) — gemini-3.7-flash_high, high, 14 August 2026
  7. 7. GPT-5.4 Pro: 94.6% (± 1.6) — gpt-5.4-pro-2026-03-05_xhigh, xhigh, 20 March 2026
  8. 8. Gemini 3.1 Pro: 94.4% (± 1.6) — gemini-3.1-pro-preview_high, high, 6 August 2026
  9. 9. GPT-6 Sol: 94.3% (± 1.5) — gpt-6-sol_max, max, 22 September 2026
  10. 10. Gemini 3.6 Flash: 94.1% (± 1.4) — gemini-3.6-flash_high, high, 2 August 2026
  11. 11. Grok 4.6: 94.0% (± 1.4) — grok-4.6_high, high, 12 August 2026
  12. 11. GPT-5.5: 94.0% (± 1.5) — gpt-5.5-pre-release_xhigh, xhigh, 24 April 2026
  13. 13. GPT-5.5 Pro: 93.9% (± 1.6) — gpt-5.5-pro-pre-release_xhigh, xhigh, 24 April 2026
  14. 14. Claude Opus 5: 93.9% (± 1.5) — claude-opus-5_max, max, 24 July 2026
  15. 15. GPT-5.6 Sol: 93.5% (± 1.6) — gpt-5.6-sol_max, max, 9 July 2026
  16. 16. Grok 4.5: 93.4% (± 1.4) — grok-4.5_high, high, 8 July 2026
  17. 17. GPT-5.6 Terra: 93.3% (± 1.5) — gpt-5.6-terra_max, max, 9 July 2026
  18. 18. GPT-5.4: 93.3% (± 1.8) — gpt-5.4-2026-03-05_xhigh, xhigh, 6 March 2026
  19. 19. Gemini 3.5 Flash: 92.8% (± 1.6) — gemini-3.5-flash_high, high, 22 May 2026
  20. 20. Grok 4.7: 92.7% (± 1.6) — grok-4.7_xhigh, xhigh, 22 September 2026
  21. 21. Qwen3.8-Max: 92.7% (± 1.7) — qwen3.8-max_xhigh, xhigh, 4 August 2026
  22. 22. Gemini 3 Pro: 92.6% (± 1.7) — gemini-3-pro-preview, 19 November 2025
  23. 23. GPT-5.6 Luna: 91.6% (± 1.7) — gpt-5.6-luna_max, max, 9 July 2026
  24. 24. GPT-5.2: 91.4% (± 1.8) — gpt-5.2-2025-12-11_xhigh, xhigh, 13 December 2025
  25. 25. Claude Opus 4.8: 91.0% (± 1.9) — claude-opus-4-8_max, max, 7 June 2026
  26. 26. DeepSeek V4 Pro: 90.9% (± 2.0) — deepseek-v4-pro_high, high, 6 August 2026
  27. 27. Claude Opus 5.5: 90.6% (± 1.9) — claude-opus-5-5_max, max, 22 September 2026
  28. 28. Claude Opus 4.6: 90.5% (± 1.7) — claude-opus-4-6_32K, 32K, 6 February 2026
  29. 28. Claude Sonnet 5: 90.5% (± 1.8) — claude-sonnet-5_xhigh, xhigh, 1 July 2026
  30. 30. GPT-6 Luna: 90.5% (± 1.9) — gpt-6-luna_max, max, 22 September 2026
  31. 31. Claude Opus 4.7: 90.2% (± 1.8) — claude-opus-4-7_xhigh, xhigh, 17 April 2026
  32. 32. DeepSeek-V4.1-Flash: 89.8% (± 1.7) — deepseek-v4.1-flash_max, max, 9 October 2026
  33. 33. Muse Spark: 89.8% (± 2.2) — muse-spark, 8 April 2026
  34. 34. Claude Haiku 5.5: 89.6% (± 2.0) — claude-haiku-5-5_max, max, 9 October 2026
  35. 35. Gemini 3 Flash: 89.4% (± 2.2) — gemini-3-flash-preview_high, high, 6 August 2026
  36. 36. Grok 4.20: 89.3% (± 1.9) — grok-4.20-0309-reasoning, 13 July 2026
  37. 37. Mistral Large 4: 88.1% (± 1.9) — mistral-large-4-0_high, high, 12 October 2026
  38. 38. GPT-5.1: 87.6% (± 1.9) — gpt-5.1-2025-11-13_high, high, 13 November 2025
  39. 39. Claude Sonnet 4.6: 87.4% (± 2.0) — claude-sonnet-4-6_32K, 32K, 20 February 2026
  40. 40. GPT-5.4 Mini: 86.9% (± 2.4) — gpt-5.4-mini-2026-03-17_xhigh, xhigh, 7 August 2026
  41. 41. GPT-5: 86.2% (± 2.1) — gpt-5-2025-08-07_high, high, 29 October 2025
  42. 42. Claude Opus 4.5: 86.0% (± 2.1) — claude-opus-4-5-20251101_32K, 32K, 24 November 2025
  43. 43. Qwen3.6-27B: 85.9% (± 2.5) — qwen3.6-27b, 7 August 2026
  44. 43. Claude Fable 5: 85.9% (± 2.5) — claude-fable-5_max, max, 6 August 2026
  45. 45. Gemini 2.5 Pro: 85.3% (± 2.1) — gemini-2.5-pro, 16 November 2025
  46. 46. Qwen3.6-35B-A3B: 84.8% (± 2.6) — qwen3.6-35b-a3b_none, none, 7 August 2026
  47. 47. Qwen3.5-35B-A3B: 83.5% (± 2.2) — qwen3.5-35b-a3b, 28 August 2026
  48. 48. Gemini 3.5 Flash-Lite: 83.3% (± 2.7) — gemini-3.5-flash-lite_high, high, 6 August 2026
  49. 49. Claude Sonnet 4.5: 82.3% (± 2.7) — claude-sonnet-4-5-20250929_59K, 59K, 28 October 2025
  50. 50. o3: 81.8% (± 2.1) — o3-2025-04-16_high, high, 16 April 2025
  51. 50. Gemini 3.1 Flash-Lite: 81.8% (± 2.7) — gemini-3.1-flash-lite_high, high, 6 August 2026
  52. 52. Claude Sonnet 3.7: 79.7% (± 2.7) — claude-3-7-sonnet-20250219_64K, 64K, 26 May 2025
  53. 53. o4-mini: 79.6% (± 2.4) — o4-mini-2025-04-16_high, high, 16 April 2025
  54. 54. Claude Sonnet 4: 79.2% (± 2.7) — claude-sonnet-4-20250514_59K, 59K, 26 May 2025
  55. 55. GPT-5.4 nano: 78.5% (± 2.4) — gpt-5.4-nano-2026-03-17_high, high, 14 April 2026
  56. 56. Claude Opus 4.1: 77.3% (± 3.0) — claude-opus-4-1-20250805_16K, 16K, 5 August 2025
  57. 57. o3-mini: 77.0% (± 2.6) — o3-mini-2025-01-31_high, high, 13 February 2025
  58. 58. o1: 76.8% (± 3.0) — o1-2024-12-17_high, high, 13 February 2025
  59. 59. DeepSeek-R1: 76.3% (± 2.4) — DeepSeek-R1-0528, 29 May 2025
  60. 60. Grok 3 mini: 76.3% (± 3.0) — grok-3-mini-beta_low, low, 10 April 2025
  61. 61. gpt-oss-120b: 75.8% (± 2.7) — openai/gpt-oss-120b_high, high, 11 December 2025
  62. 61. Grok 3: 75.8% (± 2.7) — grok-3-beta, 26 May 2025
  63. 63. GPT-5 Mini: 75.0% (± 2.3) — gpt-5-mini-2025-08-07_high, high, 30 October 2025
  64. 64. Claude Haiku 4.5: 71.2% (± 3.2) — claude-haiku-4-5-20251001_32K, 32K, 22 October 2025
  65. 65. Qwen3-235B-A22B: 70.7% (± 2.7) — qwen3-235b-a22b, 3 June 2025
  66. 66. GPT-5 nano: 69.4% (± 2.8) — gpt-5-nano-2025-08-07_high, high, 30 October 2025
  67. 67. GPT-4.5: 68.7% (± 3.3) — gpt-4.5-preview-2025-02-27, 28 February 2025
  68. 68. DeepSeek-V3: 67.6% (± 2.7) — DeepSeek-V3-0324, 1 April 2025
  69. 69. Llama 4 Maverick: 67.0% (± 2.8) — Llama-4-Maverick-17B-128E-Instruct-FP8, 8 April 2025
  70. 70. GPT-4.1: 66.9% (± 2.8) — gpt-4.1-2025-04-14, 14 April 2025
  71. 71. GPT-4.1 mini: 65.8% (± 2.7) — gpt-4.1-mini-2025-04-14, 14 April 2025
  72. 72. Qwen3-32B: 65.7% (± 2.8) — Qwen3-32B, 28 August 2026
  73. 73. Gemini 2.0 Flash: 64.1% (± 2.7) — gemini-2.0-flash-001, 6 February 2025
  74. 74. Qwen3-14B: 63.8% (± 2.9) — qwen3-14b, 28 August 2026
  75. 75. o1-mini: 62.4% (± 2.7) — o1-mini-2024-09-12_high, high, 13 February 2025
  76. 76. Qwen3-30B-A3B: 61.7% (± 3.0) — Qwen3-30B-A3B, 30 August 2026
  77. 77. gpt-oss-20b: 60.8% (± 2.5) — gpt-oss-20b_medium, medium, 27 August 2026
  78. 78. Mistral Medium 3: 59.5% (± 2.8) — mistral-medium-2505, 7 May 2025
  79. 79. Gemini 1.5 Pro: 57.2% (± 2.8) — gemini-1.5-pro-002, 27 January 2025
  80. 80. Qwen3-8B: 56.8% (± 2.9) — qwen3-8b, 27 August 2026
  81. 81. Magistral Small 1.0: 56.1% (± 3.5) — magistral-small-2506, 6 August 2026
  82. 82. Grok-2: 53.8% (± 2.7) — grok-2-1212, 27 January 2025
  83. 83. Qwen3-4B: 52.3% (± 3.0) — qwen3-4b, 28 August 2026
  84. 84. Llama 4 Scout: 51.8% (± 3.2) — Llama-4-Scout-17B-16E-Instruct, 8 April 2025
  85. 85. o1-preview: 50.3% (± 2.8) — o1-preview-2024-09-12, 27 January 2025
  86. 86. GPT-4o: 49.2% (± 2.6) — gpt-4o-2024-08-06, 27 January 2025
  87. 87. Mistral Small 3.2: 49.1% (± 2.8) — mistral-small-3.2-2506, 28 August 2026
  88. 88. GPT-4.1 nano: 48.9% (± 2.5) — gpt-4.1-nano-2025-04-14, 14 April 2025
  89. 89. Magistral Small 1.2: 47.6% (± 2.6) — magistral-small-2509, 30 August 2026
  90. 90. Mistral Small 3.1: 47.5% (± 2.8) — mistral-small-2503, 18 March 2025
  91. 91. Gemini 1.5 Flash: 47.3% (± 2.8) — gemini-1.5-flash-002, 27 January 2025
  92. 92. Claude 3 Opus: 47.2% (± 2.6) — claude-3-opus-20240229, 27 January 2025
  93. 93. GPT-4 Turbo: 46.6% (± 2.7) — gpt-4-turbo-2024-04-09, 27 February 2025
  94. 94. Claude 3 Sonnet: 40.6% (± 2.4) — claude-3-sonnet-20240229, 27 January 2025
  95. 95. Claude 3.5 Haiku: 38.1% (± 2.6) — claude-3-5-haiku-20241022, 12 March 2025
  96. 96. Qwen3-1.7B: 38.0% (± 2.7) — qwen3-1.7b, 28 August 2026
  97. 97. GPT-4o mini: 37.7% (± 2.4) — gpt-4o-mini-2024-07-18, 27 January 2025
  98. 98. Claude 3 Haiku: 36.3% (± 2.4) — claude-3-haiku-20240307, 27 January 2025
  99. 99. GPT-4: 35.7% (± 2.4) — gpt-4-0314, 23 October 2025
  100. 100. Claude 2: 34.7% (± 2.5) — claude-2.0, 27 January 2025
  101. 101. Mixtral 8x22B: 34.1% (± 2.1) — open-mixtral-8x22b, 27 January 2025
  102. 102. Gemini 1.5 Flash-8B: 33.0% (± 2.4) — gemini-1.5-flash-8b-001, 12 March 2025
  103. 102. Claude 2.1: 33.0% (± 2.3) — claude-2.1, 27 January 2025
  104. 104. Mixtral 8x7B: 30.6% (± 1.9) — Mixtral-8x7B-Instruct-v0.1, 27 January 2025
  105. 105. GPT-3.5 Turbo: 28.0% (± 1.9) — gpt-3.5-turbo-1106, 27 January 2025
  106. 106. Ministral 8B: 27.1% (± 2.1) — ministral-8b-2410, 27 January 2025

Epoch AI: the benchmark and its data · CC BY 4.0

Other benchmarks

All of the Model Tracker