Benchmark Almanac

ARC-AGI-2

GPT-6 Astra 95% leads since September 2026
GPT-6 Astra 95% leads since September 2026
In use

Models infer a rule from example grid pairs and produce the output grid for new inputs. Scored by tasks solved within two attempts.

ARC-AGI-3 is its successor, and both have ARC Prize 2026 competitions.

Released
March 2025
Kind
Abstract puzzles and logic
Level
Everyday
Scored
Checked automatically
Answers
Short answer
Tasks
Public, plus a private test set
Strongest model tested
Claude Fable 5.2 #1 on the capability index
Last in a launch post
September 2026
Last model added
November 2026
Scores refreshed
November 12th, 2026

In the authors’ words

The Abstraction and Reasoning Corpus for Artificial General Intelligence (ARC-AGI), introduced in 2019, established a challenging benchmark for evaluating the general fluid intelligence of artificial systems via a set of unique, novel tasks only requiring minimal prior knowledge. While ARC-AGI has spurred significant research activity over the past five years, recent AI progress calls for benchmarks capable of finer-grained evaluation at higher levels of cognitive complexity. We introduce ARC-AGI-2, an upgraded version of the benchmark. ARC-AGI-2 preserves the input-output pair task format of its predecessor, ensuring continuity for researchers. It incorporates a newly curated and expanded set of tasks specifically designed to provide a more granular signal to assess abstract reasoning and problem-solving abilities at higher levels of fluid intelligence. To contextualize the difficulty and characteristics of ARC-AGI-2, we present extensive results from human testing, providing a robust baseline that highlights the benchmark's accessibility to human intelligence, yet difficulty for current AI systems. ARC-AGI-2 aims to serve as a next-generation tool for rigorously measuring progress towards more general and human-like AI capabilities.

Abstract of ARC-AGI-2: A New Challenge for Frontier AI Reasoning Systems (arXiv:2505.11831, CC0)
103
Entries on its own leaderboard, 98 models we track
23
Launch posts list it, from 8 labs
12
System cards report it, from 5 labs

GPT-6 Astra leads with 95%

Best score per entry from the benchmark's own leaderboard, read on November 12th, 2026. Where a model ran with several settings or harnesses, we keep its best. Every run is in the next chart. Names in gray aren't in our model list: fine-tunes, agent systems, products and older models. They don't count toward leaders.

GPT-6 Astra leads with 95%, 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.

103 entries. Scroll sideways for the rest.

  1. 95.0 GPT-6 Astra
  2. 94.2 GPT-6.1 Sol
  3. 94.2 Gemini 4 Carbon
  4. 93.8 Claude Fable 5.2
  5. 93.3 Claude Opus 5.5
  6. 92.5 GPT-5.6 Sol
  7. 91.3 Gemini 4 Argon
  8. 90.4 Claude Opus 5
  9. 90.0 Claude Fable 5.1
  10. 89.6 GPT-6 Sol
  11. 89.2 Claude Fable 5
  12. 89.2 Gemini 3.8 Flash
  13. 85.0 GPT-5.5
  14. 84.6 Gemini 3 Deep Think
  15. 84.6 GPT-5.5 Pro
  16. 84.6 Gemini 3.7 Flash
  17. 83.9 GPT-5.6 Terra
  18. 83.9 Claude Sonnet 5.5
  19. 83.3 GPT-5.4 Pro
  20. 81.7 Inkling 2 Small
  21. 78.1 DeepSeek V4.1 Flash 1017
  22. 77.1 Gemini 3.1 Pro
  23. 76.8 Dots3-Note Preview (Max)
  24. 75.8 Claude Opus 4.7
  25. 74.0 GPT-5.4
  26. 72.9 DeepSeek V4.1 Flash
  27. 72.9 GPT-5.2 (Refinement)
  28. 72.1 Gemini 3.5 Flash
  29. 72.1 Claude Opus 4.8
  30. 69.2 Claude Opus 4.6
  31. 67.1 Grok 4.6
  32. 65.8 GLM-5.3-Flash
  33. 65.1 Grok 4.20
  34. 61.4 DeepSeek V4 Flash 0731
  35. 61.4 Grok 4.7
  36. 61.3 DeepSeek V4 Pro 0813
  37. 61.3 Claude Haiku 5.5
  38. 60.4 Claude Sonnet 4.6
  39. 60.4 Kimi K3
  40. 60.4 Gemini 3.6 Flash
  41. 59.6 GPT-5.6 Luna
  42. 59.3 GPT-6 Luna
  43. 57.5 Muse Spark Open
  44. 54.2 GPT-5.2 Pro
  45. 54.0 Gemini 3 Pro (Refinement)
  46. 52.9 GPT-5.2
  47. 52.6 Grok 4.5
  48. 45.1 Gemini 3 Deep Think (Preview)
  49. 42.4 Qwen 3.8 27B
  50. 40.1 Inkling-Small
  51. 37.6 Claude Opus 4.5
  52. 36.5 Inkling
  53. 33.6 Gemini 3 Flash
  54. 31.1 Gemini 3 Pro
  55. 29.4 Grok 4 (Refinement)
  56. 23.5 Beam 1.0
  57. 22.8 GLM-5.2
  58. 18.9 GPT-5.4 Mini
  59. 18.3 GPT-5 Pro
  60. 17.6 GPT-5.1
  61. 16.0 Grok 4
  62. 13.6 Claude Sonnet 4.5
  63. 11.8 Kimi K2.5
  64. 10.3 Gemini 3.5 Flash-Lite
  65. 9.86 GPT-5
  66. 8.61 Claude Opus 4
  67. 6.53 o3
  68. 6.25 tiny-recursion-model
  69. 6.11 o4-mini
  70. 5.93 Claude Sonnet 4
  71. 5.69 GPT-5.4 Nano
  72. 5.28 Grok 4 Fast
  73. 4.86 Gemini 2.5 Pro
  74. 4.86 o3-pro
  75. 4.86 GLM-5
  76. 4.86 MiniMax-M2.5
  77. 4.44 GPT-5 mini
  78. 4.03 Claude Haiku 4.5
  79. 4.03 DeepSeek-V3.2
  80. 2.99 o3-mini
  81. 2.61 GPT-5 nano
  82. 2.54 Gemini 2.5 Flash
  83. 1.94 Nemotron 3.5 Super VL
  84. 1.30 Gemini 2.0 Flash
  85. 1.30 DeepSeek-R1
  86. 1.27 codex-mini-2025-05-16
  87. 1.25 Qwen3-235B-A22B-Instruct
  88. 1.12 DeepSeek-R1
  89. 0.90 Claude 3.7 Sonnet
  90. 0.83 o1-mini
  91. 0.80 Gemini 1.5 Pro
  92. 0.80 GPT-4.5
  93. 0.42 Grok-3 mini
  94. 0.42 GPT-4.1
  95. 0.0 GPT-4o mini
  96. 0.0 GPT-4o
  97. 0.0 Llama 4 Maverick
  98. 0.0 Llama 4 Scout
  99. 0.0 Grok 3
  100. 0.0 GPT-4.1 mini
  101. 0.0 GPT-4.1 nano
  102. 0.0 Magistral Medium 1.0
  103. 0.0 Magistral Small 1.0
  1. 1 GPT-6 Astra max 95%
  2. 2 GPT-6.1 Sol max 94.2%
  3. 3 Gemini 4 Carbon medium 94.2%
  4. 4 Claude Fable 5.2 xhigh 93.8%
  5. 5 Claude Opus 5.5 high 93.3%
  6. 6 GPT-5.6 Sol max 92.5%
  7. 7 Gemini 4 Argon high 91.3%
  8. 8 Claude Opus 5 max 90.4%
  9. 9 Claude Fable 5.1 max 90%
  10. 10 GPT-6 Sol max 89.6%
  11. 11 Claude Fable 5 max 89.2%
  12. 12 Gemini 3.8 Flash high 89.2%
  13. 13 GPT-5.5 xhigh 85%
  14. 14 Gemini 3 Deep Think 84.6%
  15. 15 GPT-5.5 Pro high 84.6%
  16. 16 Gemini 3.7 Flash high 84.6%
  17. 17 GPT-5.6 Terra max 83.9%
  18. 18 Claude Sonnet 5.5 xhigh 83.9%
  19. 19 GPT-5.4 Pro xhigh 83.3%
  20. 20 Inkling 2 Small xhigh 81.7%
  21. 21 DeepSeek V4.1 Flash 1017 max 78.1%
  22. 22 Gemini 3.1 Pro 77.1%
  23. 23 Dots3-Note Preview (Max) 76.8%
  24. 24 Claude Opus 4.7 max 75.8%
  25. 25 GPT-5.4 xhigh 74%
  26. 26 DeepSeek V4.1 Flash max 72.9%
  27. 27 GPT-5.2 (Refinement) 72.9%
  28. 28 Gemini 3.5 Flash high 72.1%
  29. 29 Claude Opus 4.8 high 72.1%
  30. 30 Claude Opus 4.6 120k, high 69.2%
  31. 31 Grok 4.6 xhigh 67.1%
  32. 32 GLM-5.3-Flash max 65.8%
  33. 33 Grok 4.20 reasoning 65.1%
  34. 34 DeepSeek V4 Flash 0731 max 61.4%
  35. 35 Grok 4.7 xhigh 61.4%
  36. 36 DeepSeek V4 Pro 0813 max 61.3%
  37. 37 Claude Haiku 5.5 xhigh 61.3%
  38. 38 Claude Sonnet 4.6 high 60.4%
  39. 39 Kimi K3 max 60.4%
  40. 40 Gemini 3.6 Flash high 60.4%
  41. 41 GPT-5.6 Luna max 59.6%
  42. 42 GPT-6 Luna max 59.3%
  43. 43 Muse Spark Open xhigh 57.5%
  44. 44 GPT-5.2 Pro high 54.2%
  45. 45 Gemini 3 Pro (Refinement) 54%
  46. 46 GPT-5.2 xhigh 52.9%
  47. 47 Grok 4.5 high 52.6%
  48. 48 Gemini 3 Deep Think (Preview) 45.1%
  49. 49 Qwen 3.8 27B xhigh 42.4%
  50. 50 Inkling-Small xhigh 40.1%
  51. 51 Claude Opus 4.5 thinking, 64k 37.6%
  52. 52 Inkling 36.5%
  53. 53 Gemini 3 Flash high 33.6%
  54. 54 Gemini 3 Pro 31.1%
  55. 55 Grok 4 (Refinement) 29.4%
  56. 56 Beam 1.0 xhigh 23.5%
  57. 57 GLM-5.2 22.8%
  58. 58 GPT-5.4 Mini xhigh 18.9%
  59. 59 GPT-5 Pro 18.3%
  60. 60 GPT-5.1 thinking, high 17.6%
  61. 61 Grok 4 thinking 16%
  62. 62 Claude Sonnet 4.5 thinking 32k 13.6%
  63. 63 Kimi K2.5 11.8%
  64. 64 Gemini 3.5 Flash-Lite high 10.3%
  65. 65 GPT-5 high 9.86%
  66. 66 Claude Opus 4 thinking 16k 8.61%
  67. 67 o3 high 6.53%
  68. 68 tiny-recursion-model 6.25%
  69. 69 o4-mini high 6.11%
  70. 70 Claude Sonnet 4 thinking 16k 5.93%
  71. 71 GPT-5.4 Nano xhigh 5.69%
  72. 72 Grok 4 Fast 5.28%
  73. 73 Gemini 2.5 Pro Jun 2025, thinking 32k 4.86%
  74. 74 o3-pro high 4.86%
  75. 75 GLM-5 4.86%
  76. 76 MiniMax-M2.5 4.86%
  77. 77 GPT-5 mini high 4.44%
  78. 78 Claude Haiku 4.5 thinking 32k 4.03%
  79. 79 DeepSeek-V3.2 4.03%
  80. 80 o3-mini high 2.99%
  81. 81 GPT-5 nano high 2.61%
  82. 82 Gemini 2.5 Flash May 2025, thinking 24k 2.54%
  83. 83 Nemotron 3.5 Super VL medium 1.94%
  84. 84 Gemini 2.0 Flash Dec 2024 1.30%
  85. 85 DeepSeek-R1 1.30%
  86. 86 codex-mini-2025-05-16 1.27%
  87. 87 Qwen3-235B-A22B-Instruct Jul 2025 1.25%
  88. 88 DeepSeek-R1 May 2025 1.12%
  89. 89 Claude 3.7 Sonnet 8k 0.90%
  90. 90 o1-mini 0.83%
  91. 91 Gemini 1.5 Pro Sep 2024 0.80%
  92. 92 GPT-4.5 0.80%
  93. 93 Grok-3 mini low 0.42%
  94. 94 GPT-4.1 0.42%
  95. 95 GPT-4o mini 0%
  96. 96 GPT-4o Nov 2024 0%
  97. 97 Llama 4 Maverick 0%
  98. 98 Llama 4 Scout 0%
  99. 99 Grok 3 0%
  100. 100 GPT-4.1 mini 0%
  101. 101 GPT-4.1 nano 0%
  102. 102 Magistral Medium 1.0 0%
  103. 103 Magistral Small 1.0 0%

Source: Official ARC-AGI-2 leaderboard

106 models. Scroll sideways for the rest.

  1. 95.0 GPT-6 Astra
  2. 94.2 GPT-6.1 Sol
  3. 94.2 Gemini 4 Carbon
  4. 93.8 Claude Fable 5.2
  5. 93.3 Claude Opus 5.5
  6. 92.5 GPT-5.6 Sol
  7. 91.3 Gemini 4 Argon
  8. 90.4 Claude Opus 5
  9. 90.0 Claude Fable 5.1
  10. 89.6 GPT-6 Sol
  11. 89.2 Claude Fable 5
  12. 89.2 Gemini 3.8 Flash
  13. 85.0 GPT-5.5
  14. 84.6 Gemini 3 Deep Think
  15. 84.6 GPT-5.5 Pro
  16. 84.6 Gemini 3.7 Flash
  17. 83.9 GPT-5.6 Terra
  18. 83.9 Claude Sonnet 5.5
  19. 83.3 GPT-5.4 Pro
  20. 81.7 Inkling 2 Small
  21. 78.1 DeepSeek V4.1 Flash 1017
  22. 77.1 Gemini 3.1 Pro
  23. 75.8 Claude Opus 4.7
  24. 74.0 GPT-5.4
  25. 72.9 DeepSeek V4.1 Flash
  26. 72.1 Gemini 3.5 Flash
  27. 72.1 Claude Opus 4.8
  28. 69.2 Claude Opus 4.6
  29. 67.1 Grok 4.6
  30. 66.2 Ring-2.6-1T
  31. 65.8 GLM-5.3-Flash
  32. 65.1 Grok 4.20
  33. 62.5 Seed2.1 Pro
  34. 61.4 DeepSeek V4 Flash 0731
  35. 61.4 Grok 4.7
  36. 61.3 DeepSeek V4 Pro 0813
  37. 61.3 Claude Haiku 5.5
  38. 60.4 Claude Sonnet 4.6
  39. 60.4 Kimi K3
  40. 60.4 Gemini 3.6 Flash
  41. 59.6 GPT-5.6 Luna
  42. 59.3 GPT-6 Luna
  43. 57.5 Muse Spark Open
  44. 54.2 GPT-5.2 Pro
  45. 52.9 GPT-5.2
  46. 52.6 Grok 4.5
  47. 42.5 Muse Spark
  48. 42.4 Qwen 3.8 27B
  49. 40.1 Inkling-Small
  50. 37.6 Claude Opus 4.5
  51. 37.5 Seed2.0 Pro
  52. 36.5 Inkling
  53. 33.6 Gemini 3 Flash
  54. 31.1 Gemini 3 Pro
  55. 23.5 Beam 1.0
  56. 22.8 GLM-5.2
  57. 19.3 Ring-2.5-1T
  58. 18.9 GPT-5.4 Mini
  59. 18.3 GPT-5 Pro
  60. 17.6 GPT-5.1
  61. 16.0 Grok 4
  62. 13.6 Claude Sonnet 4.5
  63. 11.8 Kimi K2.5
  64. 10.3 Gemini 3.5 Flash-Lite
  65. 9.86 GPT-5
  66. 8.61 Claude Opus 4
  67. 6.53 o3
  68. 6.25 tiny-recursion-model
  69. 6.11 o4-mini
  70. 5.93 Claude Sonnet 4
  71. 5.69 GPT-5.4 Nano
  72. 5.28 Grok 4 Fast
  73. 4.86 Gemini 2.5 Pro
  74. 4.86 o3-pro
  75. 4.86 GLM-5
  76. 4.86 MiniMax-M2.5
  77. 4.44 GPT-5 mini
  78. 4.03 Claude Haiku 4.5
  79. 4.03 DeepSeek-V3.2
  80. 2.99 o3-mini
  81. 2.61 GPT-5 nano
  82. 2.54 Gemini 2.5 Flash
  83. 1.94 Nemotron 3.5 Super VL
  84. 1.45 seed-oss-36b-instruct
  85. 1.30 Gemini 2.0 Flash
  86. 1.30 DeepSeek-R1
  87. 1.30 Gemini 2.0 Flash
  88. 1.27 codex-mini-2025-05-16
  89. 1.25 Qwen3-235B-A22B-Instruct
  90. 1.12 DeepSeek-R1
  91. 0.90 Claude 3.7 Sonnet
  92. 0.83 o1-mini
  93. 0.80 Gemini 1.5 Pro
  94. 0.80 GPT-4.5
  95. 0.42 Grok-3 mini
  96. 0.42 GPT-4.1
  97. 0.0 GPT-4o mini
  98. 0.0 GPT-4o
  99. 0.0 Llama 4 Maverick
  100. 0.0 Llama 4 Scout
  101. 0.0 Grok 3
  102. 0.0 GPT-4.1 mini
  103. 0.0 GPT-4.1 nano
  104. 0.0 Magistral Medium 1.0
  105. 0.0 Magistral Small 1.0
  106. 0.0 Magistral Medium 1.1
  1. 1 GPT-6 Astra max 95%
  2. 2 GPT-6.1 Sol max 94.2%
  3. 3 Gemini 4 Carbon medium 94.2%
  4. 4 Claude Fable 5.2 xhigh 93.8%
  5. 5 Claude Opus 5.5 high 93.3%
  6. 6 GPT-5.6 Sol max 92.5%
  7. 7 Gemini 4 Argon high 91.3%
  8. 8 Claude Opus 5 max 90.4%
  9. 9 Claude Fable 5.1 max 90%
  10. 10 GPT-6 Sol max 89.6%
  11. 11 Claude Fable 5 max 89.2%
  12. 12 Gemini 3.8 Flash high 89.2%
  13. 13 GPT-5.5 xhigh 85%
  14. 14 Gemini 3 Deep Think 84.6%
  15. 15 GPT-5.5 Pro high 84.6%
  16. 16 Gemini 3.7 Flash high 84.6%
  17. 17 GPT-5.6 Terra max 83.9%
  18. 18 Claude Sonnet 5.5 xhigh 83.9%
  19. 19 GPT-5.4 Pro xhigh 83.3%
  20. 20 Inkling 2 Small xhigh 81.7%
  21. 21 DeepSeek V4.1 Flash 1017 max 78.1%
  22. 22 Gemini 3.1 Pro 77.1%
  23. 23 Claude Opus 4.7 max 75.8%
  24. 24 GPT-5.4 xhigh 74%
  25. 25 DeepSeek V4.1 Flash max 72.9%
  26. 26 Gemini 3.5 Flash 72.1%
  27. 27 Claude Opus 4.8 high 72.1%
  28. 28 Claude Opus 4.6 120k, high 69.2%
  29. 29 Grok 4.6 xhigh 67.1%
  30. 30 Ring-2.6-1T 66.2%
  31. 31 GLM-5.3-Flash max 65.8%
  32. 32 Grok 4.20 reasoning 65.1%
  33. 33 Seed2.1 Pro 62.5%
  34. 34 DeepSeek V4 Flash 0731 max 61.4%
  35. 35 Grok 4.7 xhigh 61.4%
  36. 36 DeepSeek V4 Pro 0813 max 61.3%
  37. 37 Claude Haiku 5.5 xhigh 61.3%
  38. 38 Claude Sonnet 4.6 high 60.4%
  39. 39 Kimi K3 max 60.4%
  40. 40 Gemini 3.6 Flash high 60.4%
  41. 41 GPT-5.6 Luna max 59.6%
  42. 42 GPT-6 Luna max 59.3%
  43. 43 Muse Spark Open xhigh 57.5%
  44. 44 GPT-5.2 Pro 54.2%
  45. 45 GPT-5.2 xhigh 52.9%
  46. 46 Grok 4.5 high 52.6%
  47. 47 Muse Spark 42.5%
  48. 48 Qwen 3.8 27B xhigh 42.4%
  49. 49 Inkling-Small xhigh 40.1%
  50. 50 Claude Opus 4.5 thinking, 64k 37.6%
  51. 51 Seed2.0 Pro 37.5%
  52. 52 Inkling 36.5%
  53. 53 Gemini 3 Flash high 33.6%
  54. 54 Gemini 3 Pro 31.1%
  55. 55 Beam 1.0 xhigh 23.5%
  56. 56 GLM-5.2 22.8%
  57. 57 Ring-2.5-1T 19.3%
  58. 58 GPT-5.4 Mini xhigh 18.9%
  59. 59 GPT-5 Pro 18.3%
  60. 60 GPT-5.1 thinking, high 17.6%
  61. 61 Grok 4 thinking 16%
  62. 62 Claude Sonnet 4.5 thinking 32k 13.6%
  63. 63 Kimi K2.5 11.8%
  64. 64 Gemini 3.5 Flash-Lite high 10.3%
  65. 65 GPT-5 high 9.86%
  66. 66 Claude Opus 4 thinking 16k 8.61%
  67. 67 o3 high 6.53%
  68. 68 tiny-recursion-model 6.25%
  69. 69 o4-mini high 6.11%
  70. 70 Claude Sonnet 4 thinking 16k 5.93%
  71. 71 GPT-5.4 Nano xhigh 5.69%
  72. 72 Grok 4 Fast 5.28%
  73. 73 Gemini 2.5 Pro Jun 2025, thinking 32k 4.86%
  74. 74 o3-pro high 4.86%
  75. 75 GLM-5 4.86%
  76. 76 MiniMax-M2.5 4.86%
  77. 77 GPT-5 mini high 4.44%
  78. 78 Claude Haiku 4.5 thinking 32k 4.03%
  79. 79 DeepSeek-V3.2 4.03%
  80. 80 o3-mini high 2.99%
  81. 81 GPT-5 nano high 2.61%
  82. 82 Gemini 2.5 Flash May 2025, thinking 24k 2.54%
  83. 83 Nemotron 3.5 Super VL medium 1.94%
  84. 84 seed-oss-36b-instruct 1.45%
  85. 85 Gemini 2.0 Flash Dec 2024 1.30%
  86. 86 DeepSeek-R1 1.30%
  87. 87 Gemini 2.0 Flash Feb 2025 1.30%
  88. 88 codex-mini-2025-05-16 1.27%
  89. 89 Qwen3-235B-A22B-Instruct Jul 2025 1.25%
  90. 90 DeepSeek-R1 May 2025 1.12%
  91. 91 Claude 3.7 Sonnet 8k 0.90%
  92. 92 o1-mini 0.83%
  93. 93 Gemini 1.5 Pro Sep 2024 0.80%
  94. 94 GPT-4.5 0.80%
  95. 95 Grok-3 mini low 0.42%
  96. 96 GPT-4.1 0.42%
  97. 97 GPT-4o mini 0%
  98. 98 GPT-4o Nov 2024 0%
  99. 99 Llama 4 Maverick 0%
  100. 100 Llama 4 Scout 0%
  101. 101 Grok 3 0%
  102. 102 GPT-4.1 mini 0%
  103. 103 GPT-4.1 nano 0%
  104. 104 Magistral Medium 1.0 0%
  105. 105 Magistral Small 1.0 0%
  106. 106 Magistral Medium 1.1 0%

Sources: Official ARC-AGI-2 leaderboard, labs’ model cards and Another board, via Epoch AI (CC BY 4.0)

#EntryScoreSettingDateSource
1 GPT-6 Astra 95% max Sep 2026 Official leaderboard
2 GPT-6.1 Sol 94.2% max Sep 2026 Official leaderboard
3 Gemini 4 Carbon 94.2% medium Oct 2026 Official leaderboard
4 Claude Fable 5.2 93.8% xhigh Nov 2026 Official leaderboard
5 Claude Opus 5.5 93.3% high Sep 2026 Official leaderboard
6 GPT-5.6 Sol 92.5% max Jul 2026 Official leaderboard
7 Gemini 4 Argon 91.3% high Sep 2026 Official leaderboard
8 Claude Opus 5 90.4% max Jul 2026 Official leaderboard
9 Claude Fable 5.1 90% max Sep 2026 Official leaderboard
10 GPT-6 Sol 89.6% max Sep 2026 Official leaderboard
11 Claude Fable 5 89.2% max Jun 2026 Official leaderboard
12 Gemini 3.8 Flash 89.2% high Sep 2026 Official leaderboard
13 GPT-5.5 85% xhigh Apr 2026 Official leaderboard
14 Gemini 3 Deep Think 84.6% Feb 2026 Official leaderboard
15 GPT-5.5 Pro 84.6% high Apr 2026 Official leaderboard
16 Gemini 3.7 Flash 84.6% high Aug 2026 Official leaderboard
17 GPT-5.6 Terra 83.9% max Jul 2026 Official leaderboard
18 Claude Sonnet 5.5 83.9% xhigh Sep 2026 Official leaderboard
19 GPT-5.4 Pro 83.3% xhigh Mar 2026 Official leaderboard
20 Inkling 2 Small 81.7% xhigh Nov 2026 Official leaderboard
21 DeepSeek V4.1 Flash 1017 78.1% max Oct 2026 Official leaderboard
22 Gemini 3.1 Pro 77.1% Feb 2026 Official leaderboard
23 Dots3-Note Preview (Max) 76.8% Aug 2026 Official leaderboard
24 Claude Opus 4.7 75.8% max Apr 2026 Official leaderboard
25 GPT-5.4 74% xhigh Mar 2026 Official leaderboard
26 DeepSeek V4.1 Flash 72.9% max Sep 2026 Official leaderboard
27 GPT-5.2 (Refinement) 72.9% Feb 2026 Official leaderboard
28 Gemini 3.5 Flash 72.1% high May 2026 Official leaderboard
29 Claude Opus 4.8 72.1% high May 2026 Official leaderboard
30 Claude Opus 4.6 69.2% 120k, high Feb 2026 Official leaderboard
31 Grok 4.6 67.1% xhigh Aug 2026 Official leaderboard
32 GLM-5.3-Flash 65.8% max Aug 2026 Official leaderboard
33 Grok 4.20 65.1% reasoning Feb 2026 Official leaderboard
34 DeepSeek V4 Flash 0731 61.4% max Jul 2026 Official leaderboard
35 Grok 4.7 61.4% xhigh Sep 2026 Official leaderboard
36 DeepSeek V4 Pro 0813 61.3% max Aug 2026 Official leaderboard
37 Claude Haiku 5.5 61.3% xhigh Oct 2026 Official leaderboard
38 Claude Sonnet 4.6 60.4% high Feb 2026 Official leaderboard
39 Kimi K3 60.4% max Jul 2026 Official leaderboard
40 Gemini 3.6 Flash 60.4% high Jul 2026 Official leaderboard
41 GPT-5.6 Luna 59.6% max Jul 2026 Official leaderboard
42 GPT-6 Luna 59.3% max Sep 2026 Official leaderboard
43 Muse Spark Open 57.5% xhigh Oct 2026 Official leaderboard
44 GPT-5.2 Pro 54.2% high Dec 2025 Official leaderboard
45 Gemini 3 Pro (Refinement) 54% Dec 2025 Official leaderboard
46 GPT-5.2 52.9% xhigh Dec 2025 Official leaderboard
47 Grok 4.5 52.6% high Jul 2026 Official leaderboard
48 Gemini 3 Deep Think (Preview) 45.1% Feb 2026 Official leaderboard
49 Qwen 3.8 27B 42.4% xhigh Aug 2026 Official leaderboard
50 Inkling-Small 40.1% xhigh Jul 2026 Official leaderboard
51 Claude Opus 4.5 37.6% thinking, 64k Nov 2025 Official leaderboard
52 Inkling 36.5% Jul 2026 Official leaderboard
53 Gemini 3 Flash 33.6% high Dec 2025 Official leaderboard
54 Gemini 3 Pro 31.1% Nov 2025 Official leaderboard
55 Grok 4 (Refinement) 29.4% Aug 2025 Official leaderboard
56 Beam 1.0 23.5% xhigh Oct 2026 Official leaderboard
57 GLM-5.2 22.8% Jun 2026 Official leaderboard
58 GPT-5.4 Mini 18.9% xhigh Mar 2026 Official leaderboard
59 GPT-5 Pro 18.3% Oct 2025 Official leaderboard
60 GPT-5.1 17.6% thinking, high Nov 2025 Official leaderboard
61 Grok 4 16% thinking Jul 2025 Official leaderboard
62 Claude Sonnet 4.5 13.6% thinking 32k Sep 2025 Official leaderboard
63 Kimi K2.5 11.8% Jan 2026 Official leaderboard
64 Gemini 3.5 Flash-Lite 10.3% high Jul 2026 Official leaderboard
65 GPT-5 9.86% high Aug 2025 Official leaderboard
66 Claude Opus 4 8.61% thinking 16k May 2025 Official leaderboard
67 o3 6.53% high Apr 2025 Official leaderboard
68 tiny-recursion-model 6.25% Oct 2025 Official leaderboard
69 o4-mini 6.11% high Apr 2025 Official leaderboard
70 Claude Sonnet 4 5.93% thinking 16k May 2025 Official leaderboard
71 GPT-5.4 Nano 5.69% xhigh Mar 2026 Official leaderboard
72 Grok 4 Fast 5.28% Sep 2025 Official leaderboard
73 Gemini 2.5 Pro Jun 2025 4.86% thinking 32k Jun 2025 Official leaderboard
74 o3-pro 4.86% high Jun 2025 Official leaderboard
75 GLM-5 4.86% Feb 2026 Official leaderboard
76 MiniMax-M2.5 4.86% Feb 2026 Official leaderboard
77 GPT-5 mini 4.44% high Aug 2025 Official leaderboard
78 Claude Haiku 4.5 4.03% thinking 32k Oct 2025 Official leaderboard
79 DeepSeek-V3.2 4.03% Dec 2025 Official leaderboard
80 o3-mini 2.99% high Jan 2025 Official leaderboard
81 GPT-5 nano 2.61% high Aug 2025 Official leaderboard
82 Gemini 2.5 Flash May 2025 2.54% thinking 24k May 2025 Official leaderboard
83 Nemotron 3.5 Super VL 1.94% medium Oct 2026 Official leaderboard
84 Gemini 2.0 Flash Dec 2024 1.30% Dec 2024 Official leaderboard
85 DeepSeek-R1 1.30% Jan 2025 Official leaderboard
86 codex-mini-2025-05-16 1.27% May 2025 Official leaderboard
87 Qwen3-235B-A22B-Instruct Jul 2025 1.25% Jul 2025 Official leaderboard
88 DeepSeek-R1 May 2025 1.12% May 2025 Official leaderboard
89 Claude 3.7 Sonnet 0.90% 8k Feb 2025 Official leaderboard
90 o1-mini 0.83% Sep 2024 Official leaderboard
91 Gemini 1.5 Pro Sep 2024 0.80% Sep 2024 Official leaderboard
92 GPT-4.5 0.80% Feb 2025 Official leaderboard
93 Grok-3 mini 0.42% low Apr 2025 Official leaderboard
94 GPT-4.1 0.42% Apr 2025 Official leaderboard
95 GPT-4o mini 0% Jul 2024 Official leaderboard
96 GPT-4o Nov 2024 0% Nov 2024 Official leaderboard
97 Llama 4 Maverick 0% Apr 2025 Official leaderboard
98 Llama 4 Scout 0% Apr 2025 Official leaderboard
99 Grok 3 0% Apr 2025 Official leaderboard
100 GPT-4.1 mini 0% Apr 2025 Official leaderboard
101 GPT-4.1 nano 0% Apr 2025 Official leaderboard
102 Magistral Medium 1.0 0% Jun 2025 Official leaderboard
103 Magistral Small 1.0 0% Jun 2025 Official leaderboard
#ModelScoreSettingDateSource
1 GPT-6 Astra 95% max Sep 2026 Official leaderboard
2 GPT-6.1 Sol 94.2% max Sep 2026 Official leaderboard
3 Gemini 4 Carbon 94.2% medium Oct 2026 Official leaderboard
4 Claude Fable 5.2 93.8% xhigh Nov 2026 Official leaderboard
5 Claude Opus 5.5 93.3% high Sep 2026 Official leaderboard
6 GPT-5.6 Sol 92.5% max Jul 2026 Official leaderboard
7 Gemini 4 Argon 91.3% high Sep 2026 Official leaderboard
8 Claude Opus 5 90.4% max Jul 2026 Official leaderboard
9 Claude Fable 5.1 90% max Sep 2026 Official leaderboard
10 GPT-6 Sol 89.6% max Sep 2026 Official leaderboard
11 Claude Fable 5 89.2% max Jun 2026 Official leaderboard
12 Gemini 3.8 Flash 89.2% high Sep 2026 Official leaderboard
13 GPT-5.5 85% xhigh Apr 2026 Official leaderboard
14 Gemini 3 Deep Think 84.6% Feb 2026 Lab model card
15 GPT-5.5 Pro 84.6% high Apr 2026 Official leaderboard
16 Gemini 3.7 Flash 84.6% high Aug 2026 Official leaderboard
17 GPT-5.6 Terra 83.9% max Jul 2026 Official leaderboard
18 Claude Sonnet 5.5 83.9% xhigh Sep 2026 Official leaderboard
19 GPT-5.4 Pro 83.3% xhigh Mar 2026 Official leaderboard
20 Inkling 2 Small 81.7% xhigh Nov 2026 Official leaderboard
21 DeepSeek V4.1 Flash 1017 78.1% max Oct 2026 Official leaderboard
22 Gemini 3.1 Pro 77.1% Feb 2026 Lab model card
23 Claude Opus 4.7 75.8% max Apr 2026 Official leaderboard
24 GPT-5.4 74% xhigh Mar 2026 Official leaderboard
25 DeepSeek V4.1 Flash 72.9% max Sep 2026 Official leaderboard
26 Gemini 3.5 Flash 72.1% May 2026 Lab model card
27 Claude Opus 4.8 72.1% high May 2026 Official leaderboard
28 Claude Opus 4.6 69.2% 120k, high Feb 2026 Official leaderboard
29 Grok 4.6 67.1% xhigh Aug 2026 Official leaderboard
30 Ring-2.6-1T 66.2% May 2026 Lab model card
31 GLM-5.3-Flash 65.8% max Aug 2026 Official leaderboard
32 Grok 4.20 65.1% reasoning Feb 2026 Official leaderboard
33 Seed2.1 Pro 62.5% Jun 2026 Lab model card
34 DeepSeek V4 Flash 0731 61.4% max Jul 2026 Official leaderboard
35 Grok 4.7 61.4% xhigh Sep 2026 Official leaderboard
36 DeepSeek V4 Pro 0813 61.3% max Aug 2026 Official leaderboard
37 Claude Haiku 5.5 61.3% xhigh Oct 2026 Official leaderboard
38 Claude Sonnet 4.6 60.4% high Feb 2026 Official leaderboard
39 Kimi K3 60.4% max Jul 2026 Official leaderboard
40 Gemini 3.6 Flash 60.4% high Jul 2026 Official leaderboard
41 GPT-5.6 Luna 59.6% max Jul 2026 Official leaderboard
42 GPT-6 Luna 59.3% max Sep 2026 Official leaderboard
43 Muse Spark Open 57.5% xhigh Oct 2026 Official leaderboard
44 GPT-5.2 Pro 54.2% Dec 2025 Lab model card
45 GPT-5.2 52.9% xhigh Dec 2025 Official leaderboard
46 Grok 4.5 52.6% high Jul 2026 Official leaderboard
47 Muse Spark 42.5% Apr 2026 Lab model card
48 Qwen 3.8 27B 42.4% xhigh Aug 2026 Official leaderboard
49 Inkling-Small 40.1% xhigh Jul 2026 Official leaderboard
50 Claude Opus 4.5 37.6% thinking, 64k Nov 2025 Official leaderboard
51 Seed2.0 Pro 37.5% Feb 2026 Lab model card
52 Inkling 36.5% Jul 2026 Official leaderboard
53 Gemini 3 Flash 33.6% high Dec 2025 Official leaderboard
54 Gemini 3 Pro 31.1% Nov 2025 Official leaderboard
55 Beam 1.0 23.5% xhigh Oct 2026 Official leaderboard
56 GLM-5.2 22.8% Jun 2026 Official leaderboard
57 Ring-2.5-1T 19.3% Feb 2026 Lab model card
58 GPT-5.4 Mini 18.9% xhigh Mar 2026 Official leaderboard
59 GPT-5 Pro 18.3% Oct 2025 Official leaderboard
60 GPT-5.1 17.6% thinking, high Nov 2025 Official leaderboard
61 Grok 4 16% thinking Jul 2025 Official leaderboard
62 Claude Sonnet 4.5 13.6% thinking 32k Sep 2025 Official leaderboard
63 Kimi K2.5 11.8% Jan 2026 Official leaderboard
64 Gemini 3.5 Flash-Lite 10.3% high Jul 2026 Official leaderboard
65 GPT-5 9.86% high Aug 2025 Official leaderboard
66 Claude Opus 4 8.61% thinking 16k May 2025 Official leaderboard
67 o3 6.53% high Apr 2025 Official leaderboard
68 tiny-recursion-model 6.25% Oct 2025 Official leaderboard
69 o4-mini 6.11% high Apr 2025 Official leaderboard
70 Claude Sonnet 4 5.93% thinking 16k May 2025 Official leaderboard
71 GPT-5.4 Nano 5.69% xhigh Mar 2026 Official leaderboard
72 Grok 4 Fast 5.28% Sep 2025 Official leaderboard
73 Gemini 2.5 Pro Jun 2025 4.86% thinking 32k Jun 2025 Official leaderboard
74 o3-pro 4.86% high Jun 2025 Official leaderboard
75 GLM-5 4.86% Feb 2026 Official leaderboard
76 MiniMax-M2.5 4.86% Feb 2026 Official leaderboard
77 GPT-5 mini 4.44% high Aug 2025 Official leaderboard
78 Claude Haiku 4.5 4.03% thinking 32k Oct 2025 Official leaderboard
79 DeepSeek-V3.2 4.03% Dec 2025 Official leaderboard
80 o3-mini 2.99% high Jan 2025 Official leaderboard
81 GPT-5 nano 2.61% high Aug 2025 Official leaderboard
82 Gemini 2.5 Flash May 2025 2.54% thinking 24k May 2025 Official leaderboard
83 Nemotron 3.5 Super VL 1.94% medium Oct 2026 Official leaderboard
84 seed-oss-36b-instruct 1.45% Aug 2025 Lab model card
85 Gemini 2.0 Flash Dec 2024 1.30% Dec 2024 Official leaderboard
86 DeepSeek-R1 1.30% Jan 2025 Official leaderboard
87 Gemini 2.0 Flash Feb 2025 1.30% Feb 2025 Collected by Epoch AI, source not named
88 codex-mini-2025-05-16 1.27% May 2025 Official leaderboard
89 Qwen3-235B-A22B-Instruct Jul 2025 1.25% Jul 2025 Official leaderboard
90 DeepSeek-R1 May 2025 1.12% May 2025 Official leaderboard
91 Claude 3.7 Sonnet 0.90% 8k Feb 2025 Official leaderboard
92 o1-mini 0.83% Sep 2024 Official leaderboard
93 Gemini 1.5 Pro Sep 2024 0.80% Sep 2024 Official leaderboard
94 GPT-4.5 0.80% Feb 2025 Official leaderboard
95 Grok-3 mini 0.42% low Apr 2025 Official leaderboard
96 GPT-4.1 0.42% Apr 2025 Official leaderboard
97 GPT-4o mini 0% Jul 2024 Official leaderboard
98 GPT-4o Nov 2024 0% Nov 2024 Official leaderboard
99 Llama 4 Maverick 0% Apr 2025 Official leaderboard
100 Llama 4 Scout 0% Apr 2025 Official leaderboard
101 Grok 3 0% Apr 2025 Official leaderboard
102 GPT-4.1 mini 0% Apr 2025 Official leaderboard
103 GPT-4.1 nano 0% Apr 2025 Official leaderboard
104 Magistral Medium 1.0 0% Jun 2025 Official leaderboard
105 Magistral Small 1.0 0% Jun 2025 Official leaderboard
106 Magistral Medium 1.1 0% Jun 2025 Collected by Epoch AI, source not named

Labs report scores for 24 models in their cards. Epoch AI collected claims for 97 models from labs’ reports and papers. Switch the scores above to rank them together.

The best score, 95%, costs $1.12 a task

Runs on the cost frontier score higher than any run that's cheaper. GPT-6.1 Sol at high comes within 3.3 points of the best for $0.13 a task, 8 times cheaper. The costs are the leaderboard's own estimates, so compare them only within this benchmark.

OpenAI DeepSeek Cost frontier One model at each effort level
0% 20% 40% 60% 80% 100% $0.001 $0.01 $0.10 $1.00 $10 $100 Cost per task, log scale GPT-6 Astra, max GPT-6.1 Sol, max GPT-6.1 Sol, medium GPT-6.1 Sol, low DeepSeek V4 Flash 0731, max DeepSeek V4 Flash 0731, low GPT-6 Luna, medium 0% 20% 40% 60% 80% 100% $0.001 $0.01 $0.10 $1.00 $10 $100 Cost per task, log scale GPT-6 Astra, max GPT-6.1 Sol, medium

Source: Official ARC-AGI-2 leaderboard

ModelEffortHarnessScoreCost per taskOutput tokens
GPT-6 Astra max 95% $1.12
GPT-6.1 Sol max 94.2% $0.25
Gemini 4 Carbon medium 94.2% $0.38
Claude Fable 5.2 xhigh 93.8% $0.98
GPT-6 Astra xhigh 93.3% $0.83
Claude Opus 5.5 high 93.3% $0.41
GPT-5.6 Sol max 92.5% $1.44
Claude Opus 5.5 xhigh 92.5% $0.67
Claude Fable 5.2 max 92.5% $2.81
GPT-6 Astra high 92.1% $0.67
GPT-6 Astra medium 92.1% $0.48
Gemini 4 Carbon high 92.1% $0.68
Claude Opus 5.5 max 91.7% $1.85
GPT-6.1 Sol xhigh 91.7% $0.18
GPT-6.1 Sol high 91.7% $0.13
Gemini 4 Argon high 91.3% $0.32
Claude Opus 5 max 90.4% $2.06
Claude Fable 5.2 high 90.4% $0.91
GPT-5.6 Sol xhigh 90% $1.04
Claude Fable 5.1 max 90% $4.49
Claude Fable 5.1 xhigh 90% $3.12
GPT-6 Sol max 89.6% $0.44
Claude Fable 5.2 medium 89.6% $0.63
Claude Fable 5 max 89.2% $5.45
Gemini 3.8 Flash high 89.2% $0.40
Claude Fable 5.1 high 88.8% $1.67
Claude Fable 5 xhigh 88.3% $3.00
Claude Opus 5 high 88.3% $1.45
Claude Fable 5 high 87.5% $2.44
Claude Opus 5.5 medium 87.5% $0.34
Gemini 4 Argon medium 87.1% $0.14
GPT-6.1 Sol medium 86.7% $0.10
Claude Fable 5.2 low 86.7% $0.52
Claude Fable 5.1 medium 86.3% $1.22
GPT-5.6 Sol high 85.4% $0.74
GPT-6 Astra low 85.4% $0.42
GPT-5.5 xhigh 85% $1.87
Gemini 3 Deep Think 84.6% $14
GPT-5.5 Pro high 84.6% $11
Gemini 3.7 Flash high 84.6% $0.25
GPT-5.5 Pro xhigh 84.2% $11
GPT-5.6 Terra max 83.9% $1.09
Claude Sonnet 5.5 xhigh 83.9% $0.55
GPT-5.4 Pro xhigh 83.3% $16
GPT-5.5 high 83.3% $1.45
Gemini 3.8 Flash medium 82.9% $0.25
Claude Fable 5 medium 82.5% $1.93
Inkling 2 Small xhigh 81.7% $0.27
Claude Fable 5.1 low 78.3% $0.95
GPT-6 Sol xhigh 78.1% $0.28
DeepSeek V4.1 Flash 1017 max 78.1% $0.16
Gemini 3.8 Flash low 77.5% $0.15
Gemini 3.1 Pro 77.1% $0.96
Claude Fable 5 low 76.8% $1.45
GPT-6.1 Sol low 76.7% $0.09
Claude Opus 4.7 max 75.8% $7.43
GPT-5.6 Terra xhigh 74.2% $0.69
GPT-5.4 xhigh 74% $1.52
DeepSeek V4.1 Flash 1017 low 73.6% $0.13
DeepSeek V4.1 Flash max 72.9% $0.13
Gemini 3.5 Flash high 72.1% $0.85
Claude Opus 4.8 high 72.1% $2.74
Claude Opus 4.8 medium 71.7% $2.39
GPT-5.5 medium 70.4% $0.86
Claude Opus 5.5 low 70.1% $0.24
Claude Opus 4.6 120k, high 69.2% $3.47
GPT-6 Sol high 68.9% $0.20
Claude Opus 4.6 120k, max 68.8% $3.64
DeepSeek V4.1 Flash 1017 high 68.6% $0.15
Claude Opus 4.7 high 68.3% $3.17
GPT-5.4 high 67.5% $1.02
Claude Opus 4.7 medium 67.5% $2.96
DeepSeek V4.1 Flash high 67.5% $0.13
Claude Sonnet 5.5 high 67.4% $0.28
GPT-5.6 Sol medium 67.1% $0.47
GPT-5.6 Terra high 67.1% $0.55
Grok 4.6 xhigh 67.1% $0.76
Claude Opus 4.6 120k, medium 66.3% $2.72
GLM-5.3-Flash max 65.8% $0.09
Grok 4.20 reasoning 65.1% $0.92
Grok 4.6 high 65.1% $0.73
Claude Opus 4.6 120k, low 64.6% $2.25
Gemini 3.7 Flash medium 63.8% $0.12
Claude Opus 4.8 low 62.2% $1.68
Claude Opus 4.7 low 62.1% $2.38
DeepSeek V4 Flash 0731 max 61.4% $0.04
Grok 4.7 xhigh 61.4% $2.02
Grok 4.6 medium 61.3% $0.66
DeepSeek V4 Pro 0813 max 61.3% $0.60
Claude Haiku 5.5 xhigh 61.3% $0.08
DeepSeek V4.1 Flash low 60.6% $0.12
Claude Sonnet 4.6 high 60.4% $2.70
Kimi K3 max 60.4% $1.59
Gemini 3.6 Flash high 60.4% $0.61
DeepSeek V4 Pro 0813 high 59.7% $0.60
GPT-5.6 Luna max 59.6% $0.18
GPT-6 Astra none 59.6% $0.37
GPT-5.6 Luna max 59.5% $0.67
GPT-6 Luna max 59.3% $0.06
Grok 4.7 medium 58.8% $1.48
Claude Sonnet 4.6 max 58.3% $2.72
Grok 4.7 high 58.3% $1.55
GPT-6 Sol medium 57.8% $0.15
Muse Spark Open xhigh 57.5% $0.73
DeepSeek V4 Pro 0813 low 56.3% $0.37
DeepSeek V4 Flash 0731 high 56% $0.05
GPT-5.4 medium 55.4% $0.68
Kimi K3 high 55% $0.95
GPT-5.2 Pro high 54.2% $16
Gemini 3.7 Flash low 52.9% $0.08
GPT-5.2 xhigh 52.9% $1.90
Grok 4.5 high 52.6% $0.78
Grok 4.5 medium 52.6% $0.75
Gemini 3.6 Flash medium 50.4% $0.46
GLM-5.3-Flash high 50.1% $0.08
Gemini 4 Carbon low 49.6% $0.10
GPT-5.6 Luna xhigh 47.6% $0.54
Muse Spark Open high 47.5% $0.62
DeepSeek V4 Flash 0731 low 46% $0.02
GPT-5.6 Luna xhigh 43.5% $0.13
GPT-5.2 high 43.3% $1.39
GPT-5.6 Sol low 42.5% $0.32
Qwen 3.8 27B xhigh 42.4% $0.45
Gemini 4 Argon low 42.1% $0.07
GPT-6 Luna xhigh 41.9% $0.03
Inkling-Small xhigh 40.1% $0.23
GPT-5.2 Pro medium 38.5% $8.99
Claude Opus 4.5 thinking, 64k 37.6% $2.40
GPT-5.6 Terra medium 37.5% $0.27
Inkling 36.5% $0.64
Gemini 3 Flash high 33.6% $0.23
GPT-5.5 low 33.3% $0.35
GPT-5.6 Luna high 33.3% $0.06
Grok 4.5 low 33.1% $0.40
Inkling-Small high 33.1% $0.13
Claude Sonnet 5.5 medium 32.8% $0.16
GPT-6 Sol low 31.5% $0.10
GPT-6 Luna high 31.4% $0.02
Gemini 3 Pro 31.1% $0.81
Claude Haiku 5.5 high 30.7% $0.05
Gemini 3.6 Flash low 30.4% $0.22
GPT-5.6 Luna high 29.3% $0.29
GPT-5.4 low 29.2% $0.27
GLM-5.3-Flash low 27.9% $0.06
Grok 4.6 low 27.6% $0.21
Muse Spark Open medium 27.5% $0.25
GPT-5.2 medium 26.7% $0.76
Claude Sonnet 5.5 low 24% $0.11
Beam 1.0 xhigh 23.5% $0.61
Claude Opus 4.5 thinking, 16k 22.8% $0.79
GLM-5.2 22.8% $0.25
Qwen 3.8 27B low 22.8% $0.24
Beam 1.0 high 20% $0.35
GPT-5.4 Mini xhigh 18.9% $0.75
GPT-5.6 Terra low 18.8% $0.17
GPT-5 Pro 18.3% $7.14
GPT-6 Luna medium 18.1% $0.01
GPT-5.1 thinking, high 17.6% $1.17
Grok 4.7 low 16.7% $0.17
Grok 4 thinking 16% $2.17
Claude Opus 4.5 thinking, 8k 13.9% $0.48
Claude Sonnet 4.5 thinking 32k 13.6% $0.76
Inkling-Small medium 13.6% $0.06
GPT-5.4 Mini high 13.2% $0.56
Qwen 3.8 27B medium 13.2% $0.29
Gemini 3 Flash medium 12.8% $0.08
Kimi K3 low 12.4% $0.25
Muse Spark Open low 12.2% $0.11
Kimi K2.5 11.8% $0.28
Gemini 3.5 Flash-Lite high 10.3% $0.14
GPT-5 high 9.86% $0.73
GPT-5.2 low 9.72% $0.26
Claude Haiku 5.5 medium 9.44% $0.01
Gemini 3.5 Flash minimal 8.89% $0.11
Claude Opus 4 thinking 16k 8.61% $1.93
Claude Opus 4.5 thinking, none 7.78% $0.22
GPT-5 medium 7.49% $0.45
GPT-5.6 Luna medium 7.36% $0.02
GPT-5.6 Luna medium 7.36% $0.11
Claude Sonnet 4.5 thinking 8k 6.94% $0.23
Claude Sonnet 4.5 thinking 16k 6.94% $0.35
o3 high 6.53% $0.83
GPT-5.1 thinking, medium 6.53% $0.42
Beam 1.0 medium 6.39% $0.18
tiny-recursion-model 6.25% $2.10
o4-mini high 6.11% $0.86
Claude Sonnet 4 thinking 16k 5.93% $0.49
Claude Sonnet 4.5 thinking 1k 5.83% $0.14
GPT-5.4 Nano xhigh 5.69% $0.16
Grok 4 Fast 5.28% $0.06
Gemini 3.5 Flash-Lite medium 5.28% $0.04
GPT-5.6 Luna low 5.14% $0.07
Inkling-Small low 4.86% $0.06
Gemini 2.5 Pro Jun 2025 thinking 32k 4.86% $0.76
o3-pro high 4.86% $7.55
GLM-5 4.86% $0.27
MiniMax-M2.5 4.86% $0.17
GPT-6 Luna low 4.58% $0.005
Claude Opus 4 thinking 8k 4.52% $1.16
GPT-5 mini high 4.44% $0.20
GPT-5.4 Mini medium 4.44% $0.33
Gemini 2.5 Pro Jun 2025 thinking 16k 4.03% $0.71
GPT-5 mini medium 4.03% $0.06
Claude Haiku 4.5 thinking 32k 4.03% $0.38
DeepSeek-V3.2 4.03% $0.12
Inkling-Small minimal 4.03% $0.05
Claude Sonnet 4.5 3.75% $0.13
GPT-5.6 Luna low 3.61% $0.01
GPT-5.4 Nano high 3.61% $0.13
Gemini 3 Flash minimal 3.33% $0.02
o3-mini high 2.99% $0.55
o3 medium 2.98% $0.48
Gemini 2.5 Pro Jun 2025 thinking 8k 2.92% $0.44
Claude Haiku 4.5 thinking 16k 2.78% $0.14
Beam 1.0 low 2.78% $0.10
Claude Haiku 5.5 low 2.78% $0.008
Gemini 3.6 Flash minimal 2.64% $0.07
GPT-5 nano high 2.61% $0.03
Gemini 2.5 Flash May 2025 thinking 24k 2.54% $0.32
o4-mini medium 2.36% $0.23
Gemini 2.5 Flash May 2025 thinking 1k 2.16% $0.03
Gemini 2.5 Flash May 2025 thinking 8k 2.12% $0.20
Claude Sonnet 4 thinking 8k 2.12% $0.27
DeepSeek V4 Flash 0731 none 2.08% $0.004
DeepSeek V4.1 Flash 1017 none 2.08% $0.01
o3-mini medium 2.08% $0.28
o3-pro low 2.05% $2.23
o3 low 1.99% $0.23
Gemini 2.5 Flash May 2025 thinking 16k 1.98% $0.32
Nemotron 3.5 Super VL medium 1.94% $0.02
o3-pro medium 1.94% $4.74
GPT-5 low 1.94% $0.19
GPT-5.1 thinking, low 1.94% $0.13
GPT-5.4 Nano medium 1.94% $0.06
Gemini 2.5 Flash May 2025 1.69% $0.06
o4-mini low 1.67% $0.05
GPT-5 mini minimal 1.67% $0.009
Claude Haiku 4.5 thinking 8k 1.67% $0.09
GPT-6 Sol none 1.67% $0.07
GPT-5.4 Nano low 1.53% $0.01
Gemini 3.5 Flash-Lite low 1.53% $0.02
Qwen 3.8 27B none 1.53% $0.06
Nemotron 3.5 Super VL high 1.53% $0.04
Gemini 2.0 Flash Dec 2024 1.30% $0.004
DeepSeek-R1 1.30% $0.08
codex-mini-2025-05-16 1.27% $0.23
Claude Opus 4 1.27% $0.64
Claude Sonnet 4 1.27% $0.13
Qwen3-235B-A22B-Instruct Jul 2025 1.25% $0.004
Claude Haiku 4.5 1.25% $0.04
Claude Haiku 4.5 thinking 1k 1.25% $0.05
Gemini 3 Flash low 1.25% $0.02
DeepSeek V4.1 Flash none 1.25% $0.01
DeepSeek-R1 May 2025 1.12% $0.05
GPT-5.4 Mini low 1.11% $0.06
Claude 3.7 Sonnet 8k 0.90% $0.36
GPT-5 nano medium 0.88% $0.01
Claude Sonnet 4 thinking 1k 0.85% $0.14
GPT-5.6 Luna none 0.83% $0.008
Gemini 3.5 Flash-Lite minimal 0.83% $0.01
DeepSeek V4 Pro 0813 none 0.83% $0.04
Nemotron 3.5 Super VL none 0.83% $0.006
o1-mini 0.83% $0.19
GPT-5 mini low 0.83% $0.02
GPT-5.2 0.83% $0.08
Gemini 1.5 Pro Sep 2024 0.80% $0.04
GPT-4.5 0.80% $2.10
Claude 3.7 Sonnet 16k 0.70% $0.51
Grok-3 mini low 0.42% $0.01
GPT-4.1 0.42% $0.07
GPT-5.1 thinking, none 0.42% $0.06
Claude 3.7 Sonnet 1k 0.40% $0.14
GPT-4o mini 0% $0.01
GPT-4o Nov 2024 0% $0.08
o3-mini low 0% $0.06
Claude 3.7 Sonnet 0% $0.12
Llama 4 Maverick 0% $0.01
Llama 4 Scout 0% $0.006
Grok 3 0% $0.14
GPT-4.1 mini 0% $0.01
GPT-4.1 nano 0% $0.004
Claude Opus 4 thinking 1k 0% $0.75
Gemini 2.5 Pro Jun 2025 thinking 1k 0% $0.09
Magistral Medium 1.0 0% $0.11
Magistral Medium 1.0 thinking 0% $0.12
Magistral Small 1.0 0% $0.05
GPT-5 minimal 0% $0.06
GPT-5 nano low 0% $0.003
GPT-5 nano minimal 0% $0.003
Inkling-Small none 0% $0.01
GPT-6 Luna none 0% $0.004

14 models have held number one on the official leaderboard since its release in March 2025 14 models have held number one with claims included since its release in March 2025

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

OpenAI Anthropic xAI Google DeepMind
Own leaderboard Passed 85% in Apr 2026, by GPT-5.5
GPT-6 Astra 95%
Lab claims Passed 85% in Apr 2026, by GPT-5.5
Claude Opus 5 90.4%

Sources: Official ARC-AGI-2 leaderboard and labs’ model cards

GPT-5.5 on the official leaderboard passed 85% in April 2026

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

On the benchmark’s own 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% 2025 2026 2027 Near the ceiling (85%) GPT-6 Astra Claude Fable 5 GPT-5.5 Claude Opus 4.6 GPT-5.2 Pro Claude Opus 4.5 Gemini 3 Pro 0% 20% 40% 60% 80% 100% 2025 2026 2027 Near the ceiling (85%) GPT-6 Astra GPT-5.5

Sources: Official ARC-AGI-2 leaderboard, labs’ model cards and claims collected by Epoch AI (CC BY 4.0)

2 labs put it in a launch post in the last six months

Launch posts from every lab that has listed it, one tick per post. Tall colored ticks include it, and short gray ones leave it out.

xAI
ByteDance Seed
Google DeepMind
Anthropic
OpenAI
Ant Group
Meta
Thinking Machines
DateLaunch postScoreAs the post writes it
Sep 1, 2026 Claude Fable 5.1 90 ARC-AGI-2
Jul 30, 2026 Inkling-Small 40.1 ARC-AGI-2
Jul 24, 2026 Claude Opus 5 90.4 ARC-AGI-2
May 19, 2026 Gemini 3.5 Flash 72.1 ARC-AGI-2
May 14, 2026 Ring-2.6-1T 66.2 ARC-AGI-V2 (xhigh)
Apr 23, 2026 GPT-5.5 85 ARC-AGI-2 (Verified)
Apr 16, 2026 Claude Opus 4.7 75.8 ARC-AGI-2
Apr 8, 2026 Muse Spark 42.5 ARC AGI 2 (Abstract Reasoning Puzzles (Public))
Mar 5, 2026 GPT-5.4 Pro 83.3 ARC-AGI-2 (Verified)
Mar 5, 2026 GPT-5.4 73.3 ARC-AGI-2 (Verified)
Feb 19, 2026 Gemini 3.1 Pro 77.1 ARC-AGI-2 (ARC Prize Verified)
Feb 17, 2026 Claude Sonnet 4.6 58.3 Novel problem-solving ARC-AGI-2
Feb 14, 2026 Seed2.0 Pro 37.5 ARC-AGI-2 (text) 37.5 / ArcAGI2-Image 43.3
Feb 12, 2026 Gemini 3 Deep Think 84.6 ARC-AGI-2 (verified by the ARC Prize Foundation)
Feb 10, 2026 Ring-2.5-1T 19.3 ARC-AGI-V2 (Pass@4)
Feb 5, 2026 Claude Opus 4.6 68.8 Novel problem-solving ARC AGI 2
Dec 17, 2025 Gemini 3 Flash 33.6 ARC-AGI-2 (ARC Prize Verified)
Dec 11, 2025 GPT-5.2 Pro 54.2 ARC-AGI-2 (Verified), high
Dec 11, 2025 GPT-5.2 52.9 ARC-AGI-2 (Verified) Abstract reasoning
Nov 24, 2025 Claude Opus 4.5 37.6 Novel problem solving ARC-AGI-2 (Verified)
Nov 18, 2025 Gemini 3 Pro 31.1 ARC-AGI-2 (ARC Prize Verified)
Aug 20, 2025 seed-oss-36b-instruct 1.45 ArcAGI V2 (official evaluation set)
Jul 9, 2025 Grok 4 15.9 ARC-AGI-2

12 system cards report it, from 5 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
Sep 1, 2026 Claude Fable 5.1 system card 90 ARC-AGI-2 semi-private set, max effort, verified by ARC Prize Foundation (Table 8.1.A) Capabilities
Jul 30, 2026 Inkling-Small model card 40.1 ARC-AGI-2 (5. Evaluations table) Capabilities
Jul 24, 2026 Claude Opus 5 system card 90.4 ARC-AGI-2 semi-private set, max effort, verified by ARC Prize Foundation (90.42%) (Table 8.1.A, 8.14.1) Capabilities
Jun 23, 2026 Seed2.1 Pro model card 62.5 ArcAGI2 (Table 11) Capabilities
Jun 13, 2026 Ring-2.6-1T technical report 66.2 ARC-AGI-2 (Pass@2), xhigh (Table 6) Capabilities
May 19, 2026 Gemini 3.5 Flash model card 72.1 ARC-AGI-2 (results table, p.4) Capabilities
Apr 16, 2026 Claude Opus 4.7 system card 75.8 ARC-AGI-2, max thinking (Table 8.1.A, 8.11) Capabilities
Feb 19, 2026 Gemini 3.1 Pro model card 77.1 ARC-AGI-2, ARC Prize Verified (results table, p.4) Capabilities
Feb 17, 2026 Claude Sonnet 4.6 system card 58.3 ARC-AGI-2 (Verified), max effort (Table 2.1.A); 60.42 at high effort with 120k thinking tokens per ARC Prize (2.7) Capabilities
Feb 14, 2026 Seed2.0 Pro model card 37.5 ARC-AGI-2, text input (Table 3). ArcAGI2-Image with text and image input 43.3 (Table 8) Capabilities
Feb 5, 2026 Claude Opus 4.6 system card 68.8 ARC-AGI-2 (Verified), adaptive thinking, max effort (Table 2.3.A); ARC Prize reports 69.17 at high effort with 120k thinking tokens on the private set (2.9) Capabilities
Nov 24, 2025 Claude Opus 4.5 system card 37.6 ARC-AGI-2 (Verified), semi-private set, 64k thinking (Table 2.3.A, 2.10) Capabilities

The lab's number comes out ahead in 0 of 3 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. 15 of them match, which usually means one side copied the other. Every benchmark.

Model Lab says Board says Gap
Claude Sonnet 4.6 58.3% Novel problem-solving ARC-AGI-2 60.4% Leaderboard, high −2.1 pts
GPT-5.4 73.3% ARC-AGI-2 (Verified) 74% Leaderboard, xhigh −0.7 pts
Claude Opus 4.6 68.8% Novel problem-solving ARC AGI 2 69.2% Leaderboard, 120k, high −0.4 pts
Grok 4 15.9% ARC-AGI-2 16% Leaderboard, thinking Same
GPT-5.2 Pro 54.2% ARC-AGI-2 (Verified), high 54.2% Leaderboard, high Same
Claude Opus 4.5 37.6% Novel problem solving ARC-AGI-2 (Verified) 37.6% Leaderboard, thinking, 64k Same
Inkling-Small 40.1% ARC-AGI-2 40.1% Leaderboard, xhigh Same
GPT-5.4 Pro 83.3% ARC-AGI-2 (Verified) 83.3% Leaderboard, xhigh Same
Gemini 3 Deep Think 84.6% ARC-AGI-2 (verified by the ARC Prize Foundation) 84.6% Leaderboard Same
Gemini 3.1 Pro 77.1% ARC-AGI-2 (ARC Prize Verified) 77.1% Leaderboard Same
Gemini 3.5 Flash 72.1% ARC-AGI-2 72.1% Leaderboard, high Same
Claude Opus 5 90.4% ARC-AGI-2 90.4% Leaderboard, max Same
Gemini 3 Pro 31.1% ARC-AGI-2 (ARC Prize Verified) 31.1% Leaderboard Same
GPT-5.2 52.9% ARC-AGI-2 (Verified) Abstract reasoning 52.9% Leaderboard, xhigh Same
Gemini 3 Flash 33.6% ARC-AGI-2 (ARC Prize Verified) 33.6% Leaderboard, high Same
Claude Opus 4.7 75.8% ARC-AGI-2 75.8% Leaderboard, max Same
GPT-5.5 85% ARC-AGI-2 (Verified) 85% Leaderboard, xhigh Same
Claude Fable 5.1 90% ARC-AGI-2 90% Leaderboard, max Same

2 logged changes that move scores

Changes by the maintainers, so a score from before a change may not compare with one from after it. Newest first, each with the maintainers' own source. The list may be incomplete. What we log.

  1. Leaderboard rules changed December 5th, 2025

    The maintainers added a Model Refinements leaderboard category for systems with application-layer refinement. Readers can distinguish those evaluations from baseline model runs. Source

  2. Leaderboard rules changed November 4th, 2025

    The maintainers introduced certified scores through ARC Prize Verified. Only official evaluations on hidden datasets receive verification, distinguishing them from independently reported results. Source

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 Google DeepMind Anthropic
ARC-AGI-3 Passed 85% in Sep 2026, by GPT-6 Astra
GPT-6 Astra 99.95%
ARC-AGI Passed 85% in Dec 2025, by GPT-5.2 Pro
Claude Fable 5 98.5%
ARC-AGI-2 Passed 85% in Apr 2026, by GPT-5.5
GPT-6 Astra 95%
ARC-AGI-3 Passed 85% in Sep 2026, by GPT-6 Astra
GPT-6 Astra 99.95%

Source: Official leaderboards

Replaces ARC-AGI Replaced by ARC-AGI-3

More in Science and reasoning

All 93 in Science and reasoning
  • GPQA Diamond In use 198 graduate-level 'Google-proof' multiple-choice questions in biology, chemistry and physics. Gemini 4 Carbon 96.5%
  • Terminal-Bench-Science In use 70 scientific research-workflow tasks across five science areas, run in Harbor containers. Hidden tests give the resolution rate. GPT-6 Astra 68.1%
  • FrontierScience In use Models solve physics, chemistry, and biology problems in an Olympiad track graded by short answer and a Research track graded by 10-point rubrics. Intern-S2-397B 87%
  • BioMysteryBench In use Bioinformatics problems on anonymized real datasets that require real analysis with tools. Rubric-graded, with human-solvable and human-difficult splits. Claude Fable 5.2 83.7%
  • HiPhO In use Models solve theory problems from 2024 and 2025 physics olympiad exams, some with diagrams. Official marking schemes grade answers and steps, mapped to medal levels. Gemini 3 Pro 78.3%
  • LABBench2 In use 11 biology research sub-tasks (literature, figures, tables, patents, trials and more) with tool access. Macro-averaged accuracy. GPT-5.2 60.9%