Benchmark Almanac

Code Arena

Claude Fable 5.2 1,826 leads since November 2026
Claude Fable 5.2 1,826 leads since November 2026
In use
Version 2

Models act as coding agents that build web apps from user prompts, and users vote between two results. Votes yield Elo-style ratings.

It started a fresh leaderboard and does not reuse WebDev Arena votes. It splits results into Fullstack and Frontend categories, with HTML, React and domain filters. On October 27th, 2026 it listed 153 models and 952,039 votes. Image-to-WebDev is a separate board.

Released
November 2025
Kind
Web and app front ends
Scored
Ranked by votes
Answers
Open-ended
Measures
Preference
Language
English
In and out
Text, Code → Code, Actions
Interaction
Agentic
Environment
Terminal
Refresh
Live
Run by
A host
Based on
WebDev Arena
In views
Agents, Kept fresh
Strongest model tested
Claude Fable 5.2 #2 on the capability index
Last in a launch post
November 2026
Last model added
November 2026
Scores refreshed
November 18th, 2026
134
Entries on its own leaderboard, 131 models we track
3
Launch posts list it, from 3 labs
3
System cards report it, from 3 labs

Claude Fable 5.2 leads with 1,826 Claude Fable 5.2 leads with 1,826

Best score per entry from the benchmark's own leaderboard, read on November 18th, 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. This view shows only models we track, each at its best.

Claude Fable 5.2 leads with 1,826, 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.

134 entries. Scroll sideways for the rest. Bars start at 1,000.

  1. 1,826 Claude Fable 5.2
  2. 1,816 Claude Opus 5.5
  3. 1,772 Claude Sonnet 5.5
  4. 1,768 Gemini 4 Carbon
  5. 1,763 GPT-6 Astra
  6. 1,750 Qwen4-Max
  7. 1,743 Claude Fable 5.1
  8. 1,742 GPT-6.1 Sol
  9. 1,724 Muse Wonder Full
  10. 1,704 Gemini 4 Hydrogen
  11. 1,691 Claude Opus 5
  12. 1,686 Kimi K3.1 Pro
  13. 1,681 GPT-6.1 Terra
  14. 1,679 Gemini 4 Argon
  15. 1,676 Qwen3.8 Max (0902)
  16. 1,673 GPT-6 Sol
  17. 1,670 Qwen 3.8 Max
  18. 1,661 DeepSeek V4.1 Flash
  19. 1,658 Kimi K3
  20. 1,655 Muse Spark 1.3
  21. 1,647 Muse Wonder
  22. 1,645 Inkling 2 Small
  23. 1,640 Grok 4.7
  24. 1,639 MiMo-V2.6 Flash
  25. 1,632 Tencent Hy4 preview
  26. 1,626 Claude Fable 5
  27. 1,625 Qwen3.8-Flash-Next
  28. 1,624 MiMo-V2.6 Pro
  29. 1,622 GLM-5.3
  30. 1,618 Grok 4.6
  31. 1,616 GPT-5.6 Sol
  32. 1,612 U2 Flash
  33. 1,609 GLM-5.3-Flash
  34. 1,608 Muse Ember
  35. 1,608 GLM-5.2
  36. 1,593 Claude Haiku 5.5
  37. 1,590 Qwen 3.8 27B
  38. 1,588 Gemini 3.7 Flash
  39. 1,583 Gemini 3.8 Flash
  40. 1,582 MiniMax-M3.1-Flash
  41. 1,582 DeepSeek-V4-Flash
  42. 1,581 DeepSeek-V4-Pro
  43. 1,577 GPT-6 Luna
  44. 1,572 Step 5 Preview
  45. 1,566 Mistral Large 4
  46. 1,557 Claude Opus 4.7
  47. 1,555 Claude Opus 4.8
  48. 1,552 Grok 4.5
  49. 1,547 Claude Opus 4.6
  50. 1,542 Muse Spark 1.1
  51. 1,539 Claude Sonnet 5
  52. 1,538 Gemini 3.6 Flash
  53. 1,534 Muse Spark 1.2
  54. 1,527 Muse Spark Open
  55. 1,522 Claude Sonnet 4.6
  56. 1,520 GPT-5.6 Terra
  57. 1,519 Seed2.1 Pro
  58. 1,519 GPT-5.6 Luna
  59. 1,515 Qwen3.7-Max
  60. 1,512 GPT-5.5
  61. 1,510 Kimi K2.6
  62. 1,508 GLM-5.1
  63. 1,506 Tencent Hy3
  64. 1,500 Gemini 3.5 Flash
  65. 1,493 Claude Opus 4.5
  66. 1,485 Spark-X2.6
  67. 1,484 MiniMax-M3
  68. 1,482 Qwen 3.6 Max (Preview)
  69. 1,479 MiMo-V2.5-Pro
  70. 1,474 Kimi K2.7 Code
  71. 1,462 GPT-5.4
  72. 1,461 Qwen 3.6 Plus
  73. 1,446 Gemini 3.1 Pro
  74. 1,441 Gemini 3 Pro
  75. 1,440 Gemini 3 Flash
  76. 1,438 MiMo-V2.5
  77. 1,437 Kimi K2.5
  78. 1,436 Beam 1.0
  79. 1,436 GLM-4.7
  80. 1,435 GLM-5
  81. 1,434 MiMo-V2-Pro
  82. 1,432 Gemini 3.5 Flash-Lite
  83. 1,419 GPT-5.2
  84. 1,417 GPT-5
  85. 1,414 Inkling
  86. 1,408 Inkling-Small
  87. 1,406 GPT-5.3 Codex
  88. 1,401 Nemotron 3.5 Super VL
  89. 1,400 Qwen3.5 397B-A17B
  90. 1,398 MiniMax-M2.7
  91. 1,398 GPT-5.4 Mini
  92. 1,398 GPT-5.1
  93. 1,394 Claude Sonnet 4.5
  94. 1,390 Claude Opus 4.1
  95. 1,386 MiniMax-M2.5
  96. 1,384 MiniMax-M2.1
  97. 1,376 Grok 4.20
  98. 1,370 Gemma 4 31B IT
  99. 1,369 Solar Pro 4
  100. 1,362 DeepSeek-V3.2
  101. 1,360 Qwen3.5-122B-A10B
  102. 1,358 Gemma 4 26B A4B
  103. 1,358 Tencent Hy3 preview
  104. 1,357 Grok 4.3
  105. 1,357 Qwen3.5-27B
  106. 1,354 Muse Glimmer
  107. 1,350 Laguna M.1
  108. 1,342 GLM-4.6
  109. 1,339 GPT-5.2 Codex
  110. 1,338 GPT-5.1-Codex
  111. 1,331 MiMo-V2-Flash
  112. 1,330 Claude Haiku 4.5
  113. 1,322 Kimi K2 Thinking Turbo
  114. 1,304 Laguna XS.2
  115. 1,299 MiniMax-M2
  116. 1,274 Qwen3-Coder-480B-A35B
  117. 1,272 DeepSeek-V3.2-Exp
  118. 1,263 Mistral Medium 3.5
  119. 1,257 KAT-Coder-Pro V1
  120. 1,256 Gemini 3.1 Flash-Lite
  121. 1,253 Qwen3.5-35B-A3B
  122. 1,244 Qwen3.5-Flash
  123. 1,243 GPT-5.1-Codex-mini
  124. 1,242 Grok 4.1 Fast
  125. 1,237 Trinity Large Thinking
  126. 1,231 Mistral Large 3
  127. 1,226 Gemini 2.5 Pro
  128. 1,216 Grok 4.1
  129. 1,195 Devstral 2
  130. 1,193 Granite 4.1 8B
  131. 1,171 Mercury 2
  132. 1,165 grok-code-fast-1
  133. 1,159 Grok 4 Fast
  134. 1,071 Devstral Medium

Bars start at 1,000.

  1. 1 Claude Fable 5.2 xhigh 1,826
  2. 2 Claude Opus 5.5 max 1,816
  3. 3 Claude Sonnet 5.5 xhigh 1,772
  4. 4 Gemini 4 Carbon high 1,768
  5. 5 GPT-6 Astra max 1,763
  6. 6 Qwen4-Max xhigh 1,750
  7. 7 Claude Fable 5.1 max 1,743
  8. 8 GPT-6.1 Sol max 1,742
  9. 9 Muse Wonder Full max 1,724
  10. 10 Gemini 4 Hydrogen high 1,704
  11. 11 Claude Opus 5 max 1,691
  12. 12 Kimi K3.1 Pro max 1,686
  13. 13 GPT-6.1 Terra max 1,681
  14. 14 Gemini 4 Argon high 1,679
  15. 15 Qwen3.8 Max (0902) 1,676
  16. 16 GPT-6 Sol max 1,673
  17. 17 Qwen 3.8 Max 1,670
  18. 18 DeepSeek V4.1 Flash max 1,661
  19. 19 Kimi K3 max 1,658
  20. 20 Muse Spark 1.3 max 1,655
  21. 21 Muse Wonder max 1,647
  22. 22 Inkling 2 Small 1,645
  23. 23 Grok 4.7 xhigh 1,640
  24. 24 MiMo-V2.6 Flash 1,639
  25. 25 Tencent Hy4 preview 1,632
  26. 26 Claude Fable 5 high 1,626
  27. 27 Qwen3.8-Flash-Next 1,625
  28. 28 MiMo-V2.6 Pro 1,624
  29. 29 GLM-5.3 max 1,622
  30. 30 Grok 4.6 high 1,618
  31. 31 GPT-5.6 Sol 1,616
  32. 32 U2 Flash 1,612
  33. 33 GLM-5.3-Flash 1,609
  34. 34 Muse Ember max 1,608
  35. 35 GLM-5.2 max 1,608
  36. 36 Claude Haiku 5.5 high 1,593
  37. 37 Qwen 3.8 27B 1,590
  38. 38 Gemini 3.7 Flash high 1,588
  39. 39 Gemini 3.8 Flash high 1,583
  40. 40 MiniMax-M3.1-Flash 1,582
  41. 41 DeepSeek-V4-Flash high 1,582
  42. 42 DeepSeek-V4-Pro high 1,581
  43. 43 GPT-6 Luna max 1,577
  44. 44 Step 5 Preview high 1,572
  45. 45 Mistral Large 4 1,566
  46. 46 Claude Opus 4.7 high 1,557
  47. 47 Claude Opus 4.8 high 1,555
  48. 48 Grok 4.5 1,552
  49. 49 Claude Opus 4.6 high 1,547
  50. 50 Muse Spark 1.1 1,542
  51. 51 Claude Sonnet 5 high 1,539
  52. 52 Gemini 3.6 Flash high 1,538
  53. 53 Muse Spark 1.2 xhigh 1,534
  54. 54 Muse Spark Open max 1,527
  55. 55 Claude Sonnet 4.6 1,522
  56. 56 GPT-5.6 Terra 1,520
  57. 57 Seed2.1 Pro 1,519
  58. 58 GPT-5.6 Luna 1,519
  59. 59 Qwen3.7-Max 1,515
  60. 60 GPT-5.5 1,512
  61. 61 Kimi K2.6 1,510
  62. 62 GLM-5.1 1,508
  63. 63 Tencent Hy3 1,506
  64. 64 Gemini 3.5 Flash high 1,500
  65. 65 Claude Opus 4.5 high, 32k 1,493
  66. 66 Spark-X2.6 1,485
  67. 67 MiniMax-M3 1,484
  68. 68 Qwen 3.6 Max (Preview) 1,482
  69. 69 MiMo-V2.5-Pro 1,479
  70. 70 Kimi K2.7 Code 1,474
  71. 71 GPT-5.4 1,462
  72. 72 Qwen 3.6 Plus 1,461
  73. 73 Gemini 3.1 Pro 1,446
  74. 74 Gemini 3 Pro 1,441
  75. 75 Gemini 3 Flash 1,440
  76. 76 MiMo-V2.5 1,438
  77. 77 Kimi K2.5 thinking 1,437
  78. 78 Beam 1.0 1,436
  79. 79 GLM-4.7 1,436
  80. 80 GLM-5 1,435
  81. 81 MiMo-V2-Pro 1,434
  82. 82 Gemini 3.5 Flash-Lite 1,432
  83. 83 GPT-5.2 1,419
  84. 84 GPT-5 medium 1,417
  85. 85 Inkling 1,414
  86. 86 Inkling-Small 1,408
  87. 87 GPT-5.3 Codex 1,406
  88. 88 Nemotron 3.5 Super VL nvfp4 1,401
  89. 89 Qwen3.5 397B-A17B 1,400
  90. 90 MiniMax-M2.7 1,398
  91. 91 GPT-5.4 Mini high 1,398
  92. 92 GPT-5.1 medium 1,398
  93. 93 Claude Sonnet 4.5 high, 32k 1,394
  94. 94 Claude Opus 4.1 1,390
  95. 95 MiniMax-M2.5 1,386
  96. 96 MiniMax-M2.1 1,384
  97. 97 Grok 4.20 reasoning 1,376
  98. 98 Gemma 4 31B IT 1,370
  99. 99 Solar Pro 4 1,369
  100. 100 DeepSeek-V3.2 thinking 1,362
  101. 101 Qwen3.5-122B-A10B 1,360
  102. 102 Gemma 4 26B A4B 1,358
  103. 103 Tencent Hy3 preview 1,358
  104. 104 Grok 4.3 1,357
  105. 105 Qwen3.5-27B 1,357
  106. 106 Muse Glimmer 1,354
  107. 107 Laguna M.1 1,350
  108. 108 GLM-4.6 1,342
  109. 109 GPT-5.2 Codex 1,339
  110. 110 GPT-5.1-Codex 1,338
  111. 111 MiMo-V2-Flash non-thinking 1,331
  112. 112 Claude Haiku 4.5 1,330
  113. 113 Kimi K2 Thinking Turbo 1,322
  114. 114 Laguna XS.2 1,304
  115. 115 MiniMax-M2 1,299
  116. 116 Qwen3-Coder-480B-A35B 1,274
  117. 117 DeepSeek-V3.2-Exp 1,272
  118. 118 Mistral Medium 3.5 1,263
  119. 119 KAT-Coder-Pro V1 1,257
  120. 120 Gemini 3.1 Flash-Lite 1,256
  121. 121 Qwen3.5-35B-A3B 1,253
  122. 122 Qwen3.5-Flash 1,244
  123. 123 GPT-5.1-Codex-mini 1,243
  124. 124 Grok 4.1 Fast reasoning 1,242
  125. 125 Trinity Large Thinking 1,237
  126. 126 Mistral Large 3 1,231
  127. 127 Gemini 2.5 Pro Jun 2025 1,226
  128. 128 Grok 4.1 thinking 1,216
  129. 129 Devstral 2 1,195
  130. 130 Granite 4.1 8B 1,193
  131. 131 Mercury 2 1,171
  132. 132 grok-code-fast-1 1,165
  133. 133 Grok 4 Fast reasoning 1,159
  134. 134 Devstral Medium 1,071

Source: Official Code Arena leaderboard

131 models. Scroll sideways for the rest. Bars start at 1,000.

  1. 1,826 Claude Fable 5.2
  2. 1,816 Claude Opus 5.5
  3. 1,772 Claude Sonnet 5.5
  4. 1,768 Gemini 4 Carbon
  5. 1,763 GPT-6 Astra
  6. 1,750 Qwen4-Max
  7. 1,743 Claude Fable 5.1
  8. 1,742 GPT-6.1 Sol
  9. 1,724 Muse Wonder Full
  10. 1,704 Gemini 4 Hydrogen
  11. 1,691 Claude Opus 5
  12. 1,686 Kimi K3.1 Pro
  13. 1,681 GPT-6.1 Terra
  14. 1,679 Gemini 4 Argon
  15. 1,676 Qwen3.8 Max (0902)
  16. 1,673 GPT-6 Sol
  17. 1,670 Qwen 3.8 Max
  18. 1,661 DeepSeek V4.1 Flash
  19. 1,658 Kimi K3
  20. 1,655 Muse Spark 1.3
  21. 1,647 Muse Wonder
  22. 1,645 Inkling 2 Small
  23. 1,640 Grok 4.7
  24. 1,639 MiMo-V2.6 Flash
  25. 1,632 Tencent Hy4 preview
  26. 1,626 Claude Fable 5
  27. 1,625 Qwen3.8-Flash-Next
  28. 1,624 MiMo-V2.6 Pro
  29. 1,622 GLM-5.3
  30. 1,618 Grok 4.6
  31. 1,616 GPT-5.6 Sol
  32. 1,609 GLM-5.3-Flash
  33. 1,608 Muse Ember
  34. 1,608 GLM-5.2
  35. 1,593 Claude Haiku 5.5
  36. 1,590 Qwen 3.8 27B
  37. 1,588 Gemini 3.7 Flash
  38. 1,583 Gemini 3.8 Flash
  39. 1,582 MiniMax-M3.1-Flash
  40. 1,582 DeepSeek-V4-Flash
  41. 1,581 DeepSeek-V4-Pro
  42. 1,577 GPT-6 Luna
  43. 1,572 Step 5 Preview
  44. 1,566 Mistral Large 4
  45. 1,557 Claude Opus 4.7
  46. 1,555 Claude Opus 4.8
  47. 1,552 Grok 4.5
  48. 1,547 Claude Opus 4.6
  49. 1,542 Muse Spark 1.1
  50. 1,539 Claude Sonnet 5
  51. 1,538 Gemini 3.6 Flash
  52. 1,534 Muse Spark 1.2
  53. 1,527 Muse Spark Open
  54. 1,522 Claude Sonnet 4.6
  55. 1,520 GPT-5.6 Terra
  56. 1,519 Seed2.1 Pro
  57. 1,519 GPT-5.6 Luna
  58. 1,515 Qwen3.7-Max
  59. 1,512 GPT-5.5
  60. 1,510 Kimi K2.6
  61. 1,508 GLM-5.1
  62. 1,506 Tencent Hy3
  63. 1,500 Gemini 3.5 Flash
  64. 1,493 Claude Opus 4.5
  65. 1,484 MiniMax-M3
  66. 1,482 Qwen 3.6 Max (Preview)
  67. 1,479 MiMo-V2.5-Pro
  68. 1,474 Kimi K2.7 Code
  69. 1,462 GPT-5.4
  70. 1,461 Qwen 3.6 Plus
  71. 1,446 Gemini 3.1 Pro
  72. 1,441 Gemini 3 Pro
  73. 1,440 Gemini 3 Flash
  74. 1,438 MiMo-V2.5
  75. 1,437 Kimi K2.5
  76. 1,436 Beam 1.0
  77. 1,436 GLM-4.7
  78. 1,435 GLM-5
  79. 1,434 MiMo-V2-Pro
  80. 1,432 Gemini 3.5 Flash-Lite
  81. 1,419 GPT-5.2
  82. 1,417 GPT-5
  83. 1,414 Inkling
  84. 1,408 Inkling-Small
  85. 1,406 GPT-5.3 Codex
  86. 1,401 Nemotron 3.5 Super VL
  87. 1,400 Qwen3.5 397B-A17B
  88. 1,398 MiniMax-M2.7
  89. 1,398 GPT-5.4 Mini
  90. 1,398 GPT-5.1
  91. 1,394 Claude Sonnet 4.5
  92. 1,390 Claude Opus 4.1
  93. 1,386 MiniMax-M2.5
  94. 1,384 MiniMax-M2.1
  95. 1,376 Grok 4.20
  96. 1,370 Gemma 4 31B IT
  97. 1,369 Solar Pro 4
  98. 1,362 DeepSeek-V3.2
  99. 1,360 Qwen3.5-122B-A10B
  100. 1,358 Gemma 4 26B A4B
  101. 1,358 Tencent Hy3 preview
  102. 1,357 Grok 4.3
  103. 1,357 Qwen3.5-27B
  104. 1,354 Muse Glimmer
  105. 1,350 Laguna M.1
  106. 1,342 GLM-4.6
  107. 1,339 GPT-5.2 Codex
  108. 1,338 GPT-5.1-Codex
  109. 1,331 MiMo-V2-Flash
  110. 1,330 Claude Haiku 4.5
  111. 1,322 Kimi K2 Thinking Turbo
  112. 1,304 Laguna XS.2
  113. 1,299 MiniMax-M2
  114. 1,274 Qwen3-Coder-480B-A35B
  115. 1,272 DeepSeek-V3.2-Exp
  116. 1,263 Mistral Medium 3.5
  117. 1,256 Gemini 3.1 Flash-Lite
  118. 1,253 Qwen3.5-35B-A3B
  119. 1,244 Qwen3.5-Flash
  120. 1,243 GPT-5.1-Codex-mini
  121. 1,242 Grok 4.1 Fast
  122. 1,237 Trinity Large Thinking
  123. 1,231 Mistral Large 3
  124. 1,226 Gemini 2.5 Pro
  125. 1,216 Grok 4.1
  126. 1,195 Devstral 2
  127. 1,193 Granite 4.1 8B
  128. 1,171 Mercury 2
  129. 1,165 grok-code-fast-1
  130. 1,159 Grok 4 Fast
  131. 1,071 Devstral Medium

Bars start at 1,000.

  1. 1 Claude Fable 5.2 xhigh 1,826
  2. 2 Claude Opus 5.5 max 1,816
  3. 3 Claude Sonnet 5.5 xhigh 1,772
  4. 4 Gemini 4 Carbon high 1,768
  5. 5 GPT-6 Astra max 1,763
  6. 6 Qwen4-Max xhigh 1,750
  7. 7 Claude Fable 5.1 max 1,743
  8. 8 GPT-6.1 Sol max 1,742
  9. 9 Muse Wonder Full max 1,724
  10. 10 Gemini 4 Hydrogen high 1,704
  11. 11 Claude Opus 5 max 1,691
  12. 12 Kimi K3.1 Pro max 1,686
  13. 13 GPT-6.1 Terra max 1,681
  14. 14 Gemini 4 Argon high 1,679
  15. 15 Qwen3.8 Max (0902) 1,676
  16. 16 GPT-6 Sol max 1,673
  17. 17 Qwen 3.8 Max 1,670
  18. 18 DeepSeek V4.1 Flash max 1,661
  19. 19 Kimi K3 max 1,658
  20. 20 Muse Spark 1.3 max 1,655
  21. 21 Muse Wonder max 1,647
  22. 22 Inkling 2 Small 1,645
  23. 23 Grok 4.7 xhigh 1,640
  24. 24 MiMo-V2.6 Flash 1,639
  25. 25 Tencent Hy4 preview 1,632
  26. 26 Claude Fable 5 high 1,626
  27. 27 Qwen3.8-Flash-Next 1,625
  28. 28 MiMo-V2.6 Pro 1,624
  29. 29 GLM-5.3 max 1,622
  30. 30 Grok 4.6 high 1,618
  31. 31 GPT-5.6 Sol 1,616
  32. 32 GLM-5.3-Flash 1,609
  33. 33 Muse Ember max 1,608
  34. 34 GLM-5.2 max 1,608
  35. 35 Claude Haiku 5.5 high 1,593
  36. 36 Qwen 3.8 27B 1,590
  37. 37 Gemini 3.7 Flash high 1,588
  38. 38 Gemini 3.8 Flash high 1,583
  39. 39 MiniMax-M3.1-Flash 1,582
  40. 40 DeepSeek-V4-Flash high 1,582
  41. 41 DeepSeek-V4-Pro high 1,581
  42. 42 GPT-6 Luna max 1,577
  43. 43 Step 5 Preview high 1,572
  44. 44 Mistral Large 4 1,566
  45. 45 Claude Opus 4.7 high 1,557
  46. 46 Claude Opus 4.8 high 1,555
  47. 47 Grok 4.5 1,552
  48. 48 Claude Opus 4.6 high 1,547
  49. 49 Muse Spark 1.1 1,542
  50. 50 Claude Sonnet 5 high 1,539
  51. 51 Gemini 3.6 Flash high 1,538
  52. 52 Muse Spark 1.2 xhigh 1,534
  53. 53 Muse Spark Open max 1,527
  54. 54 Claude Sonnet 4.6 1,522
  55. 55 GPT-5.6 Terra 1,520
  56. 56 Seed2.1 Pro 1,519
  57. 57 GPT-5.6 Luna 1,519
  58. 58 Qwen3.7-Max 1,515
  59. 59 GPT-5.5 1,512
  60. 60 Kimi K2.6 1,510
  61. 61 GLM-5.1 1,508
  62. 62 Tencent Hy3 1,506
  63. 63 Gemini 3.5 Flash high 1,500
  64. 64 Claude Opus 4.5 high, 32k 1,493
  65. 65 MiniMax-M3 1,484
  66. 66 Qwen 3.6 Max (Preview) 1,482
  67. 67 MiMo-V2.5-Pro 1,479
  68. 68 Kimi K2.7 Code 1,474
  69. 69 GPT-5.4 1,462
  70. 70 Qwen 3.6 Plus 1,461
  71. 71 Gemini 3.1 Pro 1,446
  72. 72 Gemini 3 Pro 1,441
  73. 73 Gemini 3 Flash 1,440
  74. 74 MiMo-V2.5 1,438
  75. 75 Kimi K2.5 thinking 1,437
  76. 76 Beam 1.0 1,436
  77. 77 GLM-4.7 1,436
  78. 78 GLM-5 1,435
  79. 79 MiMo-V2-Pro 1,434
  80. 80 Gemini 3.5 Flash-Lite 1,432
  81. 81 GPT-5.2 1,419
  82. 82 GPT-5 medium 1,417
  83. 83 Inkling 1,414
  84. 84 Inkling-Small 1,408
  85. 85 GPT-5.3 Codex 1,406
  86. 86 Nemotron 3.5 Super VL nvfp4 1,401
  87. 87 Qwen3.5 397B-A17B 1,400
  88. 88 MiniMax-M2.7 1,398
  89. 89 GPT-5.4 Mini high 1,398
  90. 90 GPT-5.1 medium 1,398
  91. 91 Claude Sonnet 4.5 high, 32k 1,394
  92. 92 Claude Opus 4.1 1,390
  93. 93 MiniMax-M2.5 1,386
  94. 94 MiniMax-M2.1 1,384
  95. 95 Grok 4.20 reasoning 1,376
  96. 96 Gemma 4 31B IT 1,370
  97. 97 Solar Pro 4 1,369
  98. 98 DeepSeek-V3.2 thinking 1,362
  99. 99 Qwen3.5-122B-A10B 1,360
  100. 100 Gemma 4 26B A4B 1,358
  101. 101 Tencent Hy3 preview 1,358
  102. 102 Grok 4.3 1,357
  103. 103 Qwen3.5-27B 1,357
  104. 104 Muse Glimmer 1,354
  105. 105 Laguna M.1 1,350
  106. 106 GLM-4.6 1,342
  107. 107 GPT-5.2 Codex 1,339
  108. 108 GPT-5.1-Codex 1,338
  109. 109 MiMo-V2-Flash non-thinking 1,331
  110. 110 Claude Haiku 4.5 1,330
  111. 111 Kimi K2 Thinking Turbo 1,322
  112. 112 Laguna XS.2 1,304
  113. 113 MiniMax-M2 1,299
  114. 114 Qwen3-Coder-480B-A35B 1,274
  115. 115 DeepSeek-V3.2-Exp 1,272
  116. 116 Mistral Medium 3.5 1,263
  117. 117 Gemini 3.1 Flash-Lite 1,256
  118. 118 Qwen3.5-35B-A3B 1,253
  119. 119 Qwen3.5-Flash 1,244
  120. 120 GPT-5.1-Codex-mini 1,243
  121. 121 Grok 4.1 Fast reasoning 1,242
  122. 122 Trinity Large Thinking 1,237
  123. 123 Mistral Large 3 1,231
  124. 124 Gemini 2.5 Pro Jun 2025 1,226
  125. 125 Grok 4.1 thinking 1,216
  126. 126 Devstral 2 1,195
  127. 127 Granite 4.1 8B 1,193
  128. 128 Mercury 2 1,171
  129. 129 grok-code-fast-1 1,165
  130. 130 Grok 4 Fast reasoning 1,159
  131. 131 Devstral Medium 1,071

Source: Official Code Arena leaderboard

131 models. Scroll sideways for the rest. Bars start at 1,000.

  1. 1,826 Claude Fable 5.2
  2. 1,816 Claude Opus 5.5
  3. 1,772 Claude Sonnet 5.5
  4. 1,768 Gemini 4 Carbon
  5. 1,763 GPT-6 Astra
  6. 1,750 Qwen4-Max
  7. 1,743 Claude Fable 5.1
  8. 1,742 GPT-6.1 Sol
  9. 1,724 Muse Wonder Full
  10. 1,704 Gemini 4 Hydrogen
  11. 1,691 Claude Opus 5
  12. 1,686 Kimi K3.1 Pro
  13. 1,681 GPT-6.1 Terra
  14. 1,679 Gemini 4 Argon
  15. 1,678 Kimi K3
  16. 1,676 Qwen3.8 Max (0902)
  17. 1,673 GPT-6 Sol
  18. 1,670 Qwen 3.8 Max
  19. 1,661 DeepSeek V4.1 Flash
  20. 1,655 Muse Spark 1.3
  21. 1,653 Inkling 2 Small
  22. 1,647 Muse Wonder
  23. 1,640 Grok 4.7
  24. 1,639 MiMo-V2.6 Flash
  25. 1,632 Tencent Hy4 preview
  26. 1,626 Claude Fable 5
  27. 1,625 Qwen3.8-Flash-Next
  28. 1,624 MiMo-V2.6 Pro
  29. 1,622 GLM-5.3
  30. 1,618 Grok 4.6
  31. 1,616 GPT-5.6 Sol
  32. 1,609 GLM-5.3-Flash
  33. 1,608 Muse Ember
  34. 1,608 GLM-5.2
  35. 1,593 Claude Haiku 5.5
  36. 1,590 Qwen 3.8 27B
  37. 1,588 Gemini 3.7 Flash
  38. 1,583 Gemini 3.8 Flash
  39. 1,582 MiniMax-M3.1-Flash
  40. 1,582 DeepSeek-V4-Flash
  41. 1,581 DeepSeek-V4-Pro
  42. 1,577 GPT-6 Luna
  43. 1,572 Step 5 Preview
  44. 1,566 Mistral Large 4
  45. 1,557 Claude Opus 4.7
  46. 1,555 Claude Opus 4.8
  47. 1,552 Grok 4.5
  48. 1,547 Claude Opus 4.6
  49. 1,542 Muse Spark 1.1
  50. 1,539 Claude Sonnet 5
  51. 1,538 Gemini 3.6 Flash
  52. 1,534 Muse Spark 1.2
  53. 1,527 Muse Spark Open
  54. 1,522 Claude Sonnet 4.6
  55. 1,520 GPT-5.6 Terra
  56. 1,519 Seed2.1 Pro
  57. 1,519 GPT-5.6 Luna
  58. 1,515 Qwen3.7-Max
  59. 1,512 GPT-5.5
  60. 1,510 Kimi K2.6
  61. 1,508 GLM-5.1
  62. 1,506 Tencent Hy3
  63. 1,500 Gemini 3.5 Flash
  64. 1,493 Claude Opus 4.5
  65. 1,484 MiniMax-M3
  66. 1,482 Qwen 3.6 Max (Preview)
  67. 1,479 MiMo-V2.5-Pro
  68. 1,474 Kimi K2.7 Code
  69. 1,462 GPT-5.4
  70. 1,461 Qwen 3.6 Plus
  71. 1,449 GLM-5
  72. 1,446 Gemini 3.1 Pro
  73. 1,441 Gemini 3 Pro
  74. 1,440 Gemini 3 Flash
  75. 1,438 MiMo-V2.5
  76. 1,437 Kimi K2.5
  77. 1,436 Beam 1.0
  78. 1,436 GLM-4.7
  79. 1,434 MiMo-V2-Pro
  80. 1,432 Gemini 3.5 Flash-Lite
  81. 1,419 GPT-5.2
  82. 1,417 GPT-5
  83. 1,414 Inkling
  84. 1,408 Inkling-Small
  85. 1,406 GPT-5.3 Codex
  86. 1,401 Nemotron 3.5 Super VL
  87. 1,400 Qwen3.5 397B-A17B
  88. 1,398 MiniMax-M2.7
  89. 1,398 GPT-5.4 Mini
  90. 1,398 GPT-5.1
  91. 1,394 Claude Sonnet 4.5
  92. 1,390 Claude Opus 4.1
  93. 1,386 MiniMax-M2.5
  94. 1,384 MiniMax-M2.1
  95. 1,376 Grok 4.20
  96. 1,370 Gemma 4 31B IT
  97. 1,369 Solar Pro 4
  98. 1,362 DeepSeek-V3.2
  99. 1,360 Qwen3.5-122B-A10B
  100. 1,358 Gemma 4 26B A4B
  101. 1,358 Tencent Hy3 preview
  102. 1,357 Grok 4.3
  103. 1,357 Qwen3.5-27B
  104. 1,354 Muse Glimmer
  105. 1,350 Laguna M.1
  106. 1,342 GLM-4.6
  107. 1,339 GPT-5.2 Codex
  108. 1,338 GPT-5.1-Codex
  109. 1,331 MiMo-V2-Flash
  110. 1,330 Claude Haiku 4.5
  111. 1,322 Kimi K2 Thinking Turbo
  112. 1,304 Laguna XS.2
  113. 1,299 MiniMax-M2
  114. 1,274 Qwen3-Coder-480B-A35B
  115. 1,272 DeepSeek-V3.2-Exp
  116. 1,263 Mistral Medium 3.5
  117. 1,256 Gemini 3.1 Flash-Lite
  118. 1,253 Qwen3.5-35B-A3B
  119. 1,244 Qwen3.5-Flash
  120. 1,243 GPT-5.1-Codex-mini
  121. 1,242 Grok 4.1 Fast
  122. 1,237 Trinity Large Thinking
  123. 1,231 Mistral Large 3
  124. 1,226 Gemini 2.5 Pro
  125. 1,216 Grok 4.1
  126. 1,195 Devstral 2
  127. 1,193 Granite 4.1 8B
  128. 1,171 Mercury 2
  129. 1,165 grok-code-fast-1
  130. 1,159 Grok 4 Fast
  131. 1,071 Devstral Medium

Bars start at 1,000.

  1. 1 Claude Fable 5.2 xhigh 1,826
  2. 2 Claude Opus 5.5 max 1,816
  3. 3 Claude Sonnet 5.5 xhigh 1,772
  4. 4 Gemini 4 Carbon high 1,768
  5. 5 GPT-6 Astra max 1,763
  6. 6 Qwen4-Max 1,750
  7. 7 Claude Fable 5.1 max 1,743
  8. 8 GPT-6.1 Sol max 1,742
  9. 9 Muse Wonder Full max 1,724
  10. 10 Gemini 4 Hydrogen high 1,704
  11. 11 Claude Opus 5 max 1,691
  12. 12 Kimi K3.1 Pro max 1,686
  13. 13 GPT-6.1 Terra max 1,681
  14. 14 Gemini 4 Argon high 1,679
  15. 15 Kimi K3 1,678
  16. 16 Qwen3.8 Max (0902) 1,676
  17. 17 GPT-6 Sol max 1,673
  18. 18 Qwen 3.8 Max 1,670
  19. 19 DeepSeek V4.1 Flash max 1,661
  20. 20 Muse Spark 1.3 max 1,655
  21. 21 Inkling 2 Small 1,653
  22. 22 Muse Wonder max 1,647
  23. 23 Grok 4.7 xhigh 1,640
  24. 24 MiMo-V2.6 Flash 1,639
  25. 25 Tencent Hy4 preview 1,632
  26. 26 Claude Fable 5 high 1,626
  27. 27 Qwen3.8-Flash-Next 1,625
  28. 28 MiMo-V2.6 Pro 1,624
  29. 29 GLM-5.3 max 1,622
  30. 30 Grok 4.6 high 1,618
  31. 31 GPT-5.6 Sol 1,616
  32. 32 GLM-5.3-Flash 1,609
  33. 33 Muse Ember max 1,608
  34. 34 GLM-5.2 max 1,608
  35. 35 Claude Haiku 5.5 high 1,593
  36. 36 Qwen 3.8 27B 1,590
  37. 37 Gemini 3.7 Flash high 1,588
  38. 38 Gemini 3.8 Flash high 1,583
  39. 39 MiniMax-M3.1-Flash 1,582
  40. 40 DeepSeek-V4-Flash high 1,582
  41. 41 DeepSeek-V4-Pro high 1,581
  42. 42 GPT-6 Luna max 1,577
  43. 43 Step 5 Preview high 1,572
  44. 44 Mistral Large 4 1,566
  45. 45 Claude Opus 4.7 high 1,557
  46. 46 Claude Opus 4.8 high 1,555
  47. 47 Grok 4.5 1,552
  48. 48 Claude Opus 4.6 high 1,547
  49. 49 Muse Spark 1.1 1,542
  50. 50 Claude Sonnet 5 high 1,539
  51. 51 Gemini 3.6 Flash high 1,538
  52. 52 Muse Spark 1.2 xhigh 1,534
  53. 53 Muse Spark Open max 1,527
  54. 54 Claude Sonnet 4.6 1,522
  55. 55 GPT-5.6 Terra 1,520
  56. 56 Seed2.1 Pro 1,519
  57. 57 GPT-5.6 Luna 1,519
  58. 58 Qwen3.7-Max 1,515
  59. 59 GPT-5.5 1,512
  60. 60 Kimi K2.6 1,510
  61. 61 GLM-5.1 1,508
  62. 62 Tencent Hy3 1,506
  63. 63 Gemini 3.5 Flash high 1,500
  64. 64 Claude Opus 4.5 high, 32k 1,493
  65. 65 MiniMax-M3 1,484
  66. 66 Qwen 3.6 Max (Preview) 1,482
  67. 67 MiMo-V2.5-Pro 1,479
  68. 68 Kimi K2.7 Code 1,474
  69. 69 GPT-5.4 1,462
  70. 70 Qwen 3.6 Plus 1,461
  71. 71 GLM-5 1,449
  72. 72 Gemini 3.1 Pro 1,446
  73. 73 Gemini 3 Pro 1,441
  74. 74 Gemini 3 Flash 1,440
  75. 75 MiMo-V2.5 1,438
  76. 76 Kimi K2.5 thinking 1,437
  77. 77 Beam 1.0 1,436
  78. 78 GLM-4.7 1,436
  79. 79 MiMo-V2-Pro 1,434
  80. 80 Gemini 3.5 Flash-Lite 1,432
  81. 81 GPT-5.2 1,419
  82. 82 GPT-5 medium 1,417
  83. 83 Inkling 1,414
  84. 84 Inkling-Small 1,408
  85. 85 GPT-5.3 Codex 1,406
  86. 86 Nemotron 3.5 Super VL nvfp4 1,401
  87. 87 Qwen3.5 397B-A17B 1,400
  88. 88 MiniMax-M2.7 1,398
  89. 89 GPT-5.4 Mini high 1,398
  90. 90 GPT-5.1 medium 1,398
  91. 91 Claude Sonnet 4.5 high, 32k 1,394
  92. 92 Claude Opus 4.1 1,390
  93. 93 MiniMax-M2.5 1,386
  94. 94 MiniMax-M2.1 1,384
  95. 95 Grok 4.20 reasoning 1,376
  96. 96 Gemma 4 31B IT 1,370
  97. 97 Solar Pro 4 1,369
  98. 98 DeepSeek-V3.2 thinking 1,362
  99. 99 Qwen3.5-122B-A10B 1,360
  100. 100 Gemma 4 26B A4B 1,358
  101. 101 Tencent Hy3 preview 1,358
  102. 102 Grok 4.3 1,357
  103. 103 Qwen3.5-27B 1,357
  104. 104 Muse Glimmer 1,354
  105. 105 Laguna M.1 1,350
  106. 106 GLM-4.6 1,342
  107. 107 GPT-5.2 Codex 1,339
  108. 108 GPT-5.1-Codex 1,338
  109. 109 MiMo-V2-Flash non-thinking 1,331
  110. 110 Claude Haiku 4.5 1,330
  111. 111 Kimi K2 Thinking Turbo 1,322
  112. 112 Laguna XS.2 1,304
  113. 113 MiniMax-M2 1,299
  114. 114 Qwen3-Coder-480B-A35B 1,274
  115. 115 DeepSeek-V3.2-Exp 1,272
  116. 116 Mistral Medium 3.5 1,263
  117. 117 Gemini 3.1 Flash-Lite 1,256
  118. 118 Qwen3.5-35B-A3B 1,253
  119. 119 Qwen3.5-Flash 1,244
  120. 120 GPT-5.1-Codex-mini 1,243
  121. 121 Grok 4.1 Fast reasoning 1,242
  122. 122 Trinity Large Thinking 1,237
  123. 123 Mistral Large 3 1,231
  124. 124 Gemini 2.5 Pro Jun 2025 1,226
  125. 125 Grok 4.1 thinking 1,216
  126. 126 Devstral 2 1,195
  127. 127 Granite 4.1 8B 1,193
  128. 128 Mercury 2 1,171
  129. 129 grok-code-fast-1 1,165
  130. 130 Grok 4 Fast reasoning 1,159
  131. 131 Devstral Medium 1,071

Sources: Official Code Arena leaderboard and labs’ model cards

#EntryScore ± 95% CISettingReleasedRun onSource
1 Claude Fable 5.2 1,826 ±18.8 xhigh Nov 2026 Nov 2026 Official leaderboard
2 Claude Opus 5.5 1,816 ±11.5 max Sep 2026 Nov 2026 Official leaderboard
3 Claude Sonnet 5.5 1,772 ±9.7 xhigh Sep 2026 Nov 2026 Official leaderboard
4 Gemini 4 Carbon 1,768 ±15.4 high Oct 2026 Nov 2026 Official leaderboard
5 GPT-6 Astra 1,763 ±8.4 max Sep 2026 Nov 2026 Official leaderboard
6 Qwen4-Max 1,750 ±15.5 xhigh Nov 2026 Nov 2026 Official leaderboard
7 Claude Fable 5.1 1,743 ±7.9 max Sep 2026 Nov 2026 Official leaderboard
8 GPT-6.1 Sol 1,742 ±9.6 max Sep 2026 Nov 2026 Official leaderboard
9 Muse Wonder Full 1,724 ±14.4 max Oct 2026 Nov 2026 Official leaderboard
10 Gemini 4 Hydrogen 1,704 ±14.2 high Nov 2026 Nov 2026 Official leaderboard
11 Claude Opus 5 1,691 ±6.1 max Jul 2026 Nov 2026 Official leaderboard
12 Kimi K3.1 Pro 1,686 ±9.5 max Oct 2026 Nov 2026 Official leaderboard
13 GPT-6.1 Terra 1,681 ±10.3 max Oct 2026 Nov 2026 Official leaderboard
14 Gemini 4 Argon 1,679 ±9.5 high Sep 2026 Nov 2026 Official leaderboard
15 Qwen3.8 Max (0902) 1,676 ±6.1 Sep 2026 Nov 2026 Official leaderboard
16 GPT-6 Sol 1,673 ±8.2 max Sep 2026 Nov 2026 Official leaderboard
17 Qwen 3.8 Max 1,670 ±12.1 Aug 2026 Nov 2026 Official leaderboard
18 DeepSeek V4.1 Flash 1,661 ±6.7 max Sep 2026 Nov 2026 Official leaderboard
19 Kimi K3 1,658 ±5.7 max Jul 2026 Nov 2026 Official leaderboard
20 Muse Spark 1.3 1,655 ±6.9 max Sep 2026 Nov 2026 Official leaderboard
21 Muse Wonder 1,647 ±9.1 max Oct 2026 Nov 2026 Official leaderboard
22 Inkling 2 Small 1,645 ±18.6 Nov 2026 Nov 2026 Official leaderboard
23 Grok 4.7 1,640 ±7.8 xhigh Sep 2026 Nov 2026 Official leaderboard
24 MiMo-V2.6 Flash 1,639 ±7.6 Sep 2026 Nov 2026 Official leaderboard
25 Tencent Hy4 preview 1,632 ±9.8 Aug 2026 Nov 2026 Official leaderboard
26 Claude Fable 5 1,626 ±5.9 high Jun 2026 Nov 2026 Official leaderboard
27 Qwen3.8-Flash-Next 1,625 ±7 Aug 2026 Nov 2026 Official leaderboard
28 MiMo-V2.6 Pro 1,624 ±7.6 Sep 2026 Nov 2026 Official leaderboard
29 GLM-5.3 1,622 ±6.8 max Aug 2026 Nov 2026 Official leaderboard
30 Grok 4.6 1,618 ±6.9 high Aug 2026 Nov 2026 Official leaderboard
31 GPT-5.6 Sol 1,616 ±5.8 xHigh, Codex Jul 2026 Nov 2026 Official leaderboard
32 U2 Flash 1,612 ±16.7 Nov 2026 Official leaderboard
33 GLM-5.3-Flash 1,609 ±6.1 Aug 2026 Nov 2026 Official leaderboard
34 Muse Ember 1,608 ±16.9 max Nov 2026 Nov 2026 Official leaderboard
35 GLM-5.2 1,608 ±5.9 max Jun 2026 Nov 2026 Official leaderboard
36 Claude Haiku 5.5 1,593 ±8.2 high Oct 2026 Nov 2026 Official leaderboard
37 Qwen 3.8 27B 1,590 ±6 Aug 2026 Nov 2026 Official leaderboard
38 Gemini 3.7 Flash 1,588 ±6.4 high Aug 2026 Nov 2026 Official leaderboard
39 Gemini 3.8 Flash 1,583 ±6.5 high Sep 2026 Nov 2026 Official leaderboard
40 MiniMax-M3.1-Flash 1,582 ±9.4 Oct 2026 Nov 2026 Official leaderboard
41 DeepSeek-V4-Flash 1,582 ±9.4 high Apr 2026 Nov 2026 Official leaderboard
42 DeepSeek-V4-Pro 1,581 ±9.6 high Apr 2026 Aug 2026 Official leaderboard
43 GPT-6 Luna 1,577 ±5.9 max Sep 2026 Nov 2026 Official leaderboard
44 Step 5 Preview 1,572 ±8 high Sep 2026 Nov 2026 Official leaderboard
45 Mistral Large 4 1,566 ±14.1 Oct 2026 Nov 2026 Official leaderboard
46 Claude Opus 4.7 1,557 ±5.8 high Apr 2026 Nov 2026 Official leaderboard
47 Claude Opus 4.8 1,555 ±5.8 high May 2026 Nov 2026 Official leaderboard
48 Grok 4.5 1,552 ±6.8 Jul 2026 Nov 2026 Official leaderboard
49 Claude Opus 4.6 1,547 ±5.5 high Feb 2026 Nov 2026 Official leaderboard
50 Muse Spark 1.1 1,542 ±7.6 Jul 2026 Nov 2026 Official leaderboard
51 Claude Sonnet 5 1,539 ±5.8 high Jun 2026 Nov 2026 Official leaderboard
52 Gemini 3.6 Flash 1,538 ±7.5 high Jul 2026 Nov 2026 Official leaderboard
53 Muse Spark 1.2 1,534 ±13.9 xhigh Aug 2026 Nov 2026 Official leaderboard
54 Muse Spark Open 1,527 ±14.8 max Oct 2026 Nov 2026 Official leaderboard
55 Claude Sonnet 4.6 1,522 ±5.2 Feb 2026 Nov 2026 Official leaderboard
56 GPT-5.6 Terra 1,520 ±6 xHigh, Codex Jul 2026 Nov 2026 Official leaderboard
57 Seed2.1 Pro 1,519 ±5.6 Jun 2026 Nov 2026 Official leaderboard
58 GPT-5.6 Luna 1,519 ±6.5 xHigh, Codex Jul 2026 Nov 2026 Official leaderboard
59 Qwen3.7-Max 1,515 ±7.4 May 2026 May 2026 Official leaderboard
60 GPT-5.5 1,512 ±6 xHigh, Codex Apr 2026 Nov 2026 Official leaderboard
61 Kimi K2.6 1,510 ±7.3 Apr 2026 Nov 2026 Official leaderboard
62 GLM-5.1 1,508 ±6.8 Apr 2026 Nov 2026 Official leaderboard
63 Tencent Hy3 1,506 ±7.9 Jul 2026 Nov 2026 Official leaderboard
64 Gemini 3.5 Flash 1,500 ±7.4 high May 2026 Nov 2026 Official leaderboard
65 Claude Opus 4.5 1,493 ±8.4 high, 32k Nov 2025 Nov 2025 Official leaderboard
66 Spark-X2.6 1,485 ±19.3 Nov 2026 Official leaderboard
67 MiniMax-M3 1,484 ±5.5 Jun 2026 Nov 2026 Official leaderboard
68 Qwen 3.6 Max (Preview) 1,482 ±12.6 Apr 2026 Nov 2026 Official leaderboard
69 MiMo-V2.5-Pro 1,479 ±5.3 Apr 2026 Nov 2026 Official leaderboard
70 Kimi K2.7 Code 1,474 ±9.5 Jun 2026 Nov 2026 Official leaderboard
71 GPT-5.4 1,462 ±19 High, Codex Mar 2026 Nov 2026 Official leaderboard
72 Qwen 3.6 Plus 1,461 ±5.6 Mar 2026 Nov 2026 Official leaderboard
73 Gemini 3.1 Pro 1,446 ±5.1 Feb 2026 Nov 2026 Official leaderboard
74 Gemini 3 Pro 1,441 ±8.5 Nov 2025 Nov 2026 Official leaderboard
75 Gemini 3 Flash 1,440 ±8.7 Dec 2025 Nov 2026 Official leaderboard
76 MiMo-V2.5 1,438 ±6 Apr 2026 Nov 2026 Official leaderboard
77 Kimi K2.5 1,437 ±5.3 thinking Jan 2026 Nov 2026 Official leaderboard
78 Beam 1.0 1,436 ±13.7 Oct 2026 Nov 2026 Official leaderboard
79 GLM-4.7 1,436 ±12 Dec 2025 Nov 2026 Official leaderboard
80 GLM-5 1,435 ±8.2 Feb 2026 Nov 2026 Official leaderboard
81 MiMo-V2-Pro 1,434 ±8.2 Mar 2026 Nov 2026 Official leaderboard
82 Gemini 3.5 Flash-Lite 1,432 ±41.4 Jul 2026 Nov 2026 Official leaderboard
83 GPT-5.2 1,419 ±22.8 Dec 2025 Nov 2026 Official leaderboard
84 GPT-5 1,417 ±15.6 medium Aug 2025 Nov 2026 Official leaderboard
85 Inkling 1,414 ±5.9 Jul 2026 Nov 2026 Official leaderboard
86 Inkling-Small 1,408 ±9.1 Jul 2026 Nov 2026 Official leaderboard
87 GPT-5.3 Codex 1,406 ±13.7 Codex Feb 2026 Nov 2026 Official leaderboard
88 Nemotron 3.5 Super VL 1,401 ±10.5 nvfp4 Oct 2026 Nov 2026 Official leaderboard
89 Qwen3.5 397B-A17B 1,400 ±5.1 Feb 2026 Nov 2026 Official leaderboard
90 MiniMax-M2.7 1,398 ±5.9 Mar 2026 Nov 2026 Official leaderboard
91 GPT-5.4 Mini 1,398 ±6.5 high Mar 2026 Nov 2026 Official leaderboard
92 GPT-5.1 1,398 ±11.6 medium Nov 2025 Nov 2026 Official leaderboard
93 Claude Sonnet 4.5 1,394 ±7.8 high, 32k Sep 2025 Sep 2025 Official leaderboard
94 Claude Opus 4.1 1,390 ±10.8 Aug 2025 Aug 2025 Official leaderboard
95 MiniMax-M2.5 1,386 ±8.4 Feb 2026 Nov 2026 Official leaderboard
96 MiniMax-M2.1 1,384 ±9.6 Dec 2025 Nov 2026 Official leaderboard
97 Grok 4.20 1,376 ±6.1 reasoning Feb 2026 Nov 2026 Official leaderboard
98 Gemma 4 31B IT 1,370 ±6 Apr 2026 Nov 2026 Official leaderboard
99 Solar Pro 4 1,369 ±10.5 Aug 2026 Nov 2026 Official leaderboard
100 DeepSeek-V3.2 1,362 ±9.1 thinking Dec 2025 Nov 2026 Official leaderboard
101 Qwen3.5-122B-A10B 1,360 ±7.7 Feb 2026 Nov 2026 Official leaderboard
102 Gemma 4 26B A4B 1,358 ±17 Apr 2026 Nov 2026 Official leaderboard
103 Tencent Hy3 preview 1,358 ±17.5 Apr 2026 Nov 2026 Official leaderboard
104 Grok 4.3 1,357 ±6.3 Apr 2026 Nov 2026 Official leaderboard
105 Qwen3.5-27B 1,357 ±8.1 Feb 2026 Nov 2026 Official leaderboard
106 Muse Glimmer 1,354 ±15.8 Aug 2026 Nov 2026 Official leaderboard
107 Laguna M.1 1,350 ±9.4 Apr 2026 Nov 2026 Official leaderboard
108 GLM-4.6 1,342 ±10.9 Sep 2025 Nov 2026 Official leaderboard
109 GPT-5.2 Codex 1,339 ±9 Dec 2025 Nov 2026 Official leaderboard
110 GPT-5.1-Codex 1,338 ±11.6 Nov 2025 Nov 2026 Official leaderboard
111 MiMo-V2-Flash 1,331 ±9.8 non-thinking Dec 2025 Nov 2026 Official leaderboard
112 Claude Haiku 4.5 1,330 ±4.9 Oct 2025 Oct 2025 Official leaderboard
113 Kimi K2 Thinking Turbo 1,322 ±7.5 Nov 2025 Nov 2026 Official leaderboard
114 Laguna XS.2 1,304 ±10.8 Apr 2026 Nov 2026 Official leaderboard
115 MiniMax-M2 1,299 ±11.1 Oct 2025 Nov 2026 Official leaderboard
116 Qwen3-Coder-480B-A35B 1,274 ±7.9 Jul 2025 Nov 2026 Official leaderboard
117 DeepSeek-V3.2-Exp 1,272 ±13.6 Sep 2025 Nov 2026 Official leaderboard
118 Mistral Medium 3.5 1,263 ±14.9 Apr 2026 Nov 2026 Official leaderboard
119 KAT-Coder-Pro V1 1,257 ±19.6 Nov 2026 Official leaderboard
120 Gemini 3.1 Flash-Lite 1,256 ±6.9 Mar 2026 Nov 2026 Official leaderboard
121 Qwen3.5-35B-A3B 1,253 ±17.5 Feb 2026 Nov 2026 Official leaderboard
122 Qwen3.5-Flash 1,244 ±19.7 Feb 2026 Nov 2026 Official leaderboard
123 GPT-5.1-Codex-mini 1,243 ±22.3 Nov 2025 Nov 2026 Official leaderboard
124 Grok 4.1 Fast 1,242 ±11.1 reasoning Nov 2025 Nov 2026 Official leaderboard
125 Trinity Large Thinking 1,237 ±20 Apr 2026 Nov 2026 Official leaderboard
126 Mistral Large 3 1,231 ±25.9 Dec 2025 Nov 2026 Official leaderboard
127 Gemini 2.5 Pro Jun 2025 1,226 ±15.9 Jun 2025 Nov 2026 Official leaderboard
128 Grok 4.1 1,216 ±25 thinking Nov 2025 Nov 2026 Official leaderboard
129 Devstral 2 1,195 ±20.8 Dec 2025 Nov 2026 Official leaderboard
130 Granite 4.1 8B 1,193 ±18.6 Apr 2026 Nov 2026 Official leaderboard
131 Mercury 2 1,171 ±24.8 Feb 2026 Nov 2026 Official leaderboard
132 grok-code-fast-1 1,165 ±28.5 Aug 2025 Nov 2026 Official leaderboard
133 Grok 4 Fast 1,159 ±27.5 reasoning Sep 2025 Nov 2026 Official leaderboard
134 Devstral Medium 1,071 ±30.9 Jul 2025 Nov 2026 Official leaderboard
#ModelScore ± 95% CISettingReleasedRun onSource
1 Claude Fable 5.2 1,826 ±18.8 xhigh Nov 2026 Nov 2026 Official leaderboard
2 Claude Opus 5.5 1,816 ±11.5 max Sep 2026 Nov 2026 Official leaderboard
3 Claude Sonnet 5.5 1,772 ±9.7 xhigh Sep 2026 Nov 2026 Official leaderboard
4 Gemini 4 Carbon 1,768 ±15.4 high Oct 2026 Nov 2026 Official leaderboard
5 GPT-6 Astra 1,763 ±8.4 max Sep 2026 Nov 2026 Official leaderboard
6 Qwen4-Max 1,750 ±15.5 xhigh Nov 2026 Nov 2026 Official leaderboard
7 Claude Fable 5.1 1,743 ±7.9 max Sep 2026 Nov 2026 Official leaderboard
8 GPT-6.1 Sol 1,742 ±9.6 max Sep 2026 Nov 2026 Official leaderboard
9 Muse Wonder Full 1,724 ±14.4 max Oct 2026 Nov 2026 Official leaderboard
10 Gemini 4 Hydrogen 1,704 ±14.2 high Nov 2026 Nov 2026 Official leaderboard
11 Claude Opus 5 1,691 ±6.1 max Jul 2026 Nov 2026 Official leaderboard
12 Kimi K3.1 Pro 1,686 ±9.5 max Oct 2026 Nov 2026 Official leaderboard
13 GPT-6.1 Terra 1,681 ±10.3 max Oct 2026 Nov 2026 Official leaderboard
14 Gemini 4 Argon 1,679 ±9.5 high Sep 2026 Nov 2026 Official leaderboard
15 Qwen3.8 Max (0902) 1,676 ±6.1 Sep 2026 Nov 2026 Official leaderboard
16 GPT-6 Sol 1,673 ±8.2 max Sep 2026 Nov 2026 Official leaderboard
17 Qwen 3.8 Max 1,670 ±12.1 Aug 2026 Nov 2026 Official leaderboard
18 DeepSeek V4.1 Flash 1,661 ±6.7 max Sep 2026 Nov 2026 Official leaderboard
19 Kimi K3 1,658 ±5.7 max Jul 2026 Nov 2026 Official leaderboard
20 Muse Spark 1.3 1,655 ±6.9 max Sep 2026 Nov 2026 Official leaderboard
21 Muse Wonder 1,647 ±9.1 max Oct 2026 Nov 2026 Official leaderboard
22 Inkling 2 Small 1,645 ±18.6 Nov 2026 Nov 2026 Official leaderboard
23 Grok 4.7 1,640 ±7.8 xhigh Sep 2026 Nov 2026 Official leaderboard
24 MiMo-V2.6 Flash 1,639 ±7.6 Sep 2026 Nov 2026 Official leaderboard
25 Tencent Hy4 preview 1,632 ±9.8 Aug 2026 Nov 2026 Official leaderboard
26 Claude Fable 5 1,626 ±5.9 high Jun 2026 Nov 2026 Official leaderboard
27 Qwen3.8-Flash-Next 1,625 ±7 Aug 2026 Nov 2026 Official leaderboard
28 MiMo-V2.6 Pro 1,624 ±7.6 Sep 2026 Nov 2026 Official leaderboard
29 GLM-5.3 1,622 ±6.8 max Aug 2026 Nov 2026 Official leaderboard
30 Grok 4.6 1,618 ±6.9 high Aug 2026 Nov 2026 Official leaderboard
31 GPT-5.6 Sol 1,616 ±5.8 xHigh, Codex Jul 2026 Nov 2026 Official leaderboard
32 GLM-5.3-Flash 1,609 ±6.1 Aug 2026 Nov 2026 Official leaderboard
33 Muse Ember 1,608 ±16.9 max Nov 2026 Nov 2026 Official leaderboard
34 GLM-5.2 1,608 ±5.9 max Jun 2026 Nov 2026 Official leaderboard
35 Claude Haiku 5.5 1,593 ±8.2 high Oct 2026 Nov 2026 Official leaderboard
36 Qwen 3.8 27B 1,590 ±6 Aug 2026 Nov 2026 Official leaderboard
37 Gemini 3.7 Flash 1,588 ±6.4 high Aug 2026 Nov 2026 Official leaderboard
38 Gemini 3.8 Flash 1,583 ±6.5 high Sep 2026 Nov 2026 Official leaderboard
39 MiniMax-M3.1-Flash 1,582 ±9.4 Oct 2026 Nov 2026 Official leaderboard
40 DeepSeek-V4-Flash 1,582 ±9.4 high Apr 2026 Nov 2026 Official leaderboard
41 DeepSeek-V4-Pro 1,581 ±9.6 high Apr 2026 Aug 2026 Official leaderboard
42 GPT-6 Luna 1,577 ±5.9 max Sep 2026 Nov 2026 Official leaderboard
43 Step 5 Preview 1,572 ±8 high Sep 2026 Nov 2026 Official leaderboard
44 Mistral Large 4 1,566 ±14.1 Oct 2026 Nov 2026 Official leaderboard
45 Claude Opus 4.7 1,557 ±5.8 high Apr 2026 Nov 2026 Official leaderboard
46 Claude Opus 4.8 1,555 ±5.8 high May 2026 Nov 2026 Official leaderboard
47 Grok 4.5 1,552 ±6.8 Jul 2026 Nov 2026 Official leaderboard
48 Claude Opus 4.6 1,547 ±5.5 high Feb 2026 Nov 2026 Official leaderboard
49 Muse Spark 1.1 1,542 ±7.6 Jul 2026 Nov 2026 Official leaderboard
50 Claude Sonnet 5 1,539 ±5.8 high Jun 2026 Nov 2026 Official leaderboard
51 Gemini 3.6 Flash 1,538 ±7.5 high Jul 2026 Nov 2026 Official leaderboard
52 Muse Spark 1.2 1,534 ±13.9 xhigh Aug 2026 Nov 2026 Official leaderboard
53 Muse Spark Open 1,527 ±14.8 max Oct 2026 Nov 2026 Official leaderboard
54 Claude Sonnet 4.6 1,522 ±5.2 Feb 2026 Nov 2026 Official leaderboard
55 GPT-5.6 Terra 1,520 ±6 xHigh, Codex Jul 2026 Nov 2026 Official leaderboard
56 Seed2.1 Pro 1,519 ±5.6 Jun 2026 Nov 2026 Official leaderboard
57 GPT-5.6 Luna 1,519 ±6.5 xHigh, Codex Jul 2026 Nov 2026 Official leaderboard
58 Qwen3.7-Max 1,515 ±7.4 May 2026 May 2026 Official leaderboard
59 GPT-5.5 1,512 ±6 xHigh, Codex Apr 2026 Nov 2026 Official leaderboard
60 Kimi K2.6 1,510 ±7.3 Apr 2026 Nov 2026 Official leaderboard
61 GLM-5.1 1,508 ±6.8 Apr 2026 Nov 2026 Official leaderboard
62 Tencent Hy3 1,506 ±7.9 Jul 2026 Nov 2026 Official leaderboard
63 Gemini 3.5 Flash 1,500 ±7.4 high May 2026 Nov 2026 Official leaderboard
64 Claude Opus 4.5 1,493 ±8.4 high, 32k Nov 2025 Nov 2025 Official leaderboard
65 MiniMax-M3 1,484 ±5.5 Jun 2026 Nov 2026 Official leaderboard
66 Qwen 3.6 Max (Preview) 1,482 ±12.6 Apr 2026 Nov 2026 Official leaderboard
67 MiMo-V2.5-Pro 1,479 ±5.3 Apr 2026 Nov 2026 Official leaderboard
68 Kimi K2.7 Code 1,474 ±9.5 Jun 2026 Nov 2026 Official leaderboard
69 GPT-5.4 1,462 ±19 High, Codex Mar 2026 Nov 2026 Official leaderboard
70 Qwen 3.6 Plus 1,461 ±5.6 Mar 2026 Nov 2026 Official leaderboard
71 Gemini 3.1 Pro 1,446 ±5.1 Feb 2026 Nov 2026 Official leaderboard
72 Gemini 3 Pro 1,441 ±8.5 Nov 2025 Nov 2026 Official leaderboard
73 Gemini 3 Flash 1,440 ±8.7 Dec 2025 Nov 2026 Official leaderboard
74 MiMo-V2.5 1,438 ±6 Apr 2026 Nov 2026 Official leaderboard
75 Kimi K2.5 1,437 ±5.3 thinking Jan 2026 Nov 2026 Official leaderboard
76 Beam 1.0 1,436 ±13.7 Oct 2026 Nov 2026 Official leaderboard
77 GLM-4.7 1,436 ±12 Dec 2025 Nov 2026 Official leaderboard
78 GLM-5 1,435 ±8.2 Feb 2026 Nov 2026 Official leaderboard
79 MiMo-V2-Pro 1,434 ±8.2 Mar 2026 Nov 2026 Official leaderboard
80 Gemini 3.5 Flash-Lite 1,432 ±41.4 Jul 2026 Nov 2026 Official leaderboard
81 GPT-5.2 1,419 ±22.8 Dec 2025 Nov 2026 Official leaderboard
82 GPT-5 1,417 ±15.6 medium Aug 2025 Nov 2026 Official leaderboard
83 Inkling 1,414 ±5.9 Jul 2026 Nov 2026 Official leaderboard
84 Inkling-Small 1,408 ±9.1 Jul 2026 Nov 2026 Official leaderboard
85 GPT-5.3 Codex 1,406 ±13.7 Codex Feb 2026 Nov 2026 Official leaderboard
86 Nemotron 3.5 Super VL 1,401 ±10.5 nvfp4 Oct 2026 Nov 2026 Official leaderboard
87 Qwen3.5 397B-A17B 1,400 ±5.1 Feb 2026 Nov 2026 Official leaderboard
88 MiniMax-M2.7 1,398 ±5.9 Mar 2026 Nov 2026 Official leaderboard
89 GPT-5.4 Mini 1,398 ±6.5 high Mar 2026 Nov 2026 Official leaderboard
90 GPT-5.1 1,398 ±11.6 medium Nov 2025 Nov 2026 Official leaderboard
91 Claude Sonnet 4.5 1,394 ±7.8 high, 32k Sep 2025 Sep 2025 Official leaderboard
92 Claude Opus 4.1 1,390 ±10.8 Aug 2025 Aug 2025 Official leaderboard
93 MiniMax-M2.5 1,386 ±8.4 Feb 2026 Nov 2026 Official leaderboard
94 MiniMax-M2.1 1,384 ±9.6 Dec 2025 Nov 2026 Official leaderboard
95 Grok 4.20 1,376 ±6.1 reasoning Feb 2026 Nov 2026 Official leaderboard
96 Gemma 4 31B IT 1,370 ±6 Apr 2026 Nov 2026 Official leaderboard
97 Solar Pro 4 1,369 ±10.5 Aug 2026 Nov 2026 Official leaderboard
98 DeepSeek-V3.2 1,362 ±9.1 thinking Dec 2025 Nov 2026 Official leaderboard
99 Qwen3.5-122B-A10B 1,360 ±7.7 Feb 2026 Nov 2026 Official leaderboard
100 Gemma 4 26B A4B 1,358 ±17 Apr 2026 Nov 2026 Official leaderboard
101 Tencent Hy3 preview 1,358 ±17.5 Apr 2026 Nov 2026 Official leaderboard
102 Grok 4.3 1,357 ±6.3 Apr 2026 Nov 2026 Official leaderboard
103 Qwen3.5-27B 1,357 ±8.1 Feb 2026 Nov 2026 Official leaderboard
104 Muse Glimmer 1,354 ±15.8 Aug 2026 Nov 2026 Official leaderboard
105 Laguna M.1 1,350 ±9.4 Apr 2026 Nov 2026 Official leaderboard
106 GLM-4.6 1,342 ±10.9 Sep 2025 Nov 2026 Official leaderboard
107 GPT-5.2 Codex 1,339 ±9 Dec 2025 Nov 2026 Official leaderboard
108 GPT-5.1-Codex 1,338 ±11.6 Nov 2025 Nov 2026 Official leaderboard
109 MiMo-V2-Flash 1,331 ±9.8 non-thinking Dec 2025 Nov 2026 Official leaderboard
110 Claude Haiku 4.5 1,330 ±4.9 Oct 2025 Oct 2025 Official leaderboard
111 Kimi K2 Thinking Turbo 1,322 ±7.5 Nov 2025 Nov 2026 Official leaderboard
112 Laguna XS.2 1,304 ±10.8 Apr 2026 Nov 2026 Official leaderboard
113 MiniMax-M2 1,299 ±11.1 Oct 2025 Nov 2026 Official leaderboard
114 Qwen3-Coder-480B-A35B 1,274 ±7.9 Jul 2025 Nov 2026 Official leaderboard
115 DeepSeek-V3.2-Exp 1,272 ±13.6 Sep 2025 Nov 2026 Official leaderboard
116 Mistral Medium 3.5 1,263 ±14.9 Apr 2026 Nov 2026 Official leaderboard
117 Gemini 3.1 Flash-Lite 1,256 ±6.9 Mar 2026 Nov 2026 Official leaderboard
118 Qwen3.5-35B-A3B 1,253 ±17.5 Feb 2026 Nov 2026 Official leaderboard
119 Qwen3.5-Flash 1,244 ±19.7 Feb 2026 Nov 2026 Official leaderboard
120 GPT-5.1-Codex-mini 1,243 ±22.3 Nov 2025 Nov 2026 Official leaderboard
121 Grok 4.1 Fast 1,242 ±11.1 reasoning Nov 2025 Nov 2026 Official leaderboard
122 Trinity Large Thinking 1,237 ±20 Apr 2026 Nov 2026 Official leaderboard
123 Mistral Large 3 1,231 ±25.9 Dec 2025 Nov 2026 Official leaderboard
124 Gemini 2.5 Pro Jun 2025 1,226 ±15.9 Jun 2025 Nov 2026 Official leaderboard
125 Grok 4.1 1,216 ±25 thinking Nov 2025 Nov 2026 Official leaderboard
126 Devstral 2 1,195 ±20.8 Dec 2025 Nov 2026 Official leaderboard
127 Granite 4.1 8B 1,193 ±18.6 Apr 2026 Nov 2026 Official leaderboard
128 Mercury 2 1,171 ±24.8 Feb 2026 Nov 2026 Official leaderboard
129 grok-code-fast-1 1,165 ±28.5 Aug 2025 Nov 2026 Official leaderboard
130 Grok 4 Fast 1,159 ±27.5 reasoning Sep 2025 Nov 2026 Official leaderboard
131 Devstral Medium 1,071 ±30.9 Jul 2025 Nov 2026 Official leaderboard
#ModelScoreSettingDateSource
1 Claude Fable 5.2 1,826 xhigh Nov 2026 Official leaderboard
2 Claude Opus 5.5 1,816 max Sep 2026 Official leaderboard
3 Claude Sonnet 5.5 1,772 xhigh Sep 2026 Official leaderboard
4 Gemini 4 Carbon 1,768 high Oct 2026 Official leaderboard
5 GPT-6 Astra 1,763 max Sep 2026 Official leaderboard
6 Qwen4-Max 1,750 Nov 2026 Lab model card
7 Claude Fable 5.1 1,743 max Sep 2026 Official leaderboard
8 GPT-6.1 Sol 1,742 max Sep 2026 Official leaderboard
9 Muse Wonder Full 1,724 max Oct 2026 Official leaderboard
10 Gemini 4 Hydrogen 1,704 high Nov 2026 Official leaderboard
11 Claude Opus 5 1,691 max Jul 2026 Official leaderboard
12 Kimi K3.1 Pro 1,686 max Oct 2026 Official leaderboard
13 GPT-6.1 Terra 1,681 max Oct 2026 Official leaderboard
14 Gemini 4 Argon 1,679 high Sep 2026 Official leaderboard
15 Kimi K3 1,678 Jul 2026 Lab model card
16 Qwen3.8 Max (0902) 1,676 Sep 2026 Official leaderboard
17 GPT-6 Sol 1,673 max Sep 2026 Official leaderboard
18 Qwen 3.8 Max 1,670 Aug 2026 Official leaderboard
19 DeepSeek V4.1 Flash 1,661 max Sep 2026 Official leaderboard
20 Muse Spark 1.3 1,655 max Sep 2026 Official leaderboard
21 Inkling 2 Small 1,653 Nov 2026 Lab model card
22 Muse Wonder 1,647 max Oct 2026 Official leaderboard
23 Grok 4.7 1,640 xhigh Sep 2026 Official leaderboard
24 MiMo-V2.6 Flash 1,639 Sep 2026 Official leaderboard
25 Tencent Hy4 preview 1,632 Aug 2026 Official leaderboard
26 Claude Fable 5 1,626 high Jun 2026 Official leaderboard
27 Qwen3.8-Flash-Next 1,625 Aug 2026 Official leaderboard
28 MiMo-V2.6 Pro 1,624 Sep 2026 Official leaderboard
29 GLM-5.3 1,622 max Aug 2026 Official leaderboard
30 Grok 4.6 1,618 high Aug 2026 Official leaderboard
31 GPT-5.6 Sol 1,616 xHigh, Codex Jul 2026 Official leaderboard
32 GLM-5.3-Flash 1,609 Aug 2026 Official leaderboard
33 Muse Ember 1,608 max Nov 2026 Official leaderboard
34 GLM-5.2 1,608 max Jun 2026 Official leaderboard
35 Claude Haiku 5.5 1,593 high Oct 2026 Official leaderboard
36 Qwen 3.8 27B 1,590 Aug 2026 Official leaderboard
37 Gemini 3.7 Flash 1,588 high Aug 2026 Official leaderboard
38 Gemini 3.8 Flash 1,583 high Sep 2026 Official leaderboard
39 MiniMax-M3.1-Flash 1,582 Oct 2026 Official leaderboard
40 DeepSeek-V4-Flash 1,582 high Apr 2026 Official leaderboard
41 DeepSeek-V4-Pro 1,581 high Apr 2026 Official leaderboard
42 GPT-6 Luna 1,577 max Sep 2026 Official leaderboard
43 Step 5 Preview 1,572 high Sep 2026 Official leaderboard
44 Mistral Large 4 1,566 Oct 2026 Official leaderboard
45 Claude Opus 4.7 1,557 high Apr 2026 Official leaderboard
46 Claude Opus 4.8 1,555 high May 2026 Official leaderboard
47 Grok 4.5 1,552 Jul 2026 Official leaderboard
48 Claude Opus 4.6 1,547 high Feb 2026 Official leaderboard
49 Muse Spark 1.1 1,542 Jul 2026 Official leaderboard
50 Claude Sonnet 5 1,539 high Jun 2026 Official leaderboard
51 Gemini 3.6 Flash 1,538 high Jul 2026 Official leaderboard
52 Muse Spark 1.2 1,534 xhigh Aug 2026 Official leaderboard
53 Muse Spark Open 1,527 max Oct 2026 Official leaderboard
54 Claude Sonnet 4.6 1,522 Feb 2026 Official leaderboard
55 GPT-5.6 Terra 1,520 xHigh, Codex Jul 2026 Official leaderboard
56 Seed2.1 Pro 1,519 Jun 2026 Official leaderboard
57 GPT-5.6 Luna 1,519 xHigh, Codex Jul 2026 Official leaderboard
58 Qwen3.7-Max 1,515 May 2026 Official leaderboard
59 GPT-5.5 1,512 xHigh, Codex Apr 2026 Official leaderboard
60 Kimi K2.6 1,510 Apr 2026 Official leaderboard
61 GLM-5.1 1,508 Apr 2026 Official leaderboard
62 Tencent Hy3 1,506 Jul 2026 Official leaderboard
63 Gemini 3.5 Flash 1,500 high May 2026 Official leaderboard
64 Claude Opus 4.5 1,493 high, 32k Nov 2025 Official leaderboard
65 MiniMax-M3 1,484 Jun 2026 Official leaderboard
66 Qwen 3.6 Max (Preview) 1,482 Apr 2026 Official leaderboard
67 MiMo-V2.5-Pro 1,479 Apr 2026 Official leaderboard
68 Kimi K2.7 Code 1,474 Jun 2026 Official leaderboard
69 GPT-5.4 1,462 High, Codex Mar 2026 Official leaderboard
70 Qwen 3.6 Plus 1,461 Mar 2026 Official leaderboard
71 GLM-5 1,449 Feb 2026 Lab model card
72 Gemini 3.1 Pro 1,446 Feb 2026 Official leaderboard
73 Gemini 3 Pro 1,441 Nov 2025 Official leaderboard
74 Gemini 3 Flash 1,440 Dec 2025 Official leaderboard
75 MiMo-V2.5 1,438 Apr 2026 Official leaderboard
76 Kimi K2.5 1,437 thinking Jan 2026 Official leaderboard
77 Beam 1.0 1,436 Oct 2026 Official leaderboard
78 GLM-4.7 1,436 Dec 2025 Official leaderboard
79 MiMo-V2-Pro 1,434 Mar 2026 Official leaderboard
80 Gemini 3.5 Flash-Lite 1,432 Jul 2026 Official leaderboard
81 GPT-5.2 1,419 Dec 2025 Official leaderboard
82 GPT-5 1,417 medium Aug 2025 Official leaderboard
83 Inkling 1,414 Jul 2026 Official leaderboard
84 Inkling-Small 1,408 Jul 2026 Official leaderboard
85 GPT-5.3 Codex 1,406 Codex Feb 2026 Official leaderboard
86 Nemotron 3.5 Super VL 1,401 nvfp4 Oct 2026 Official leaderboard
87 Qwen3.5 397B-A17B 1,400 Feb 2026 Official leaderboard
88 MiniMax-M2.7 1,398 Mar 2026 Official leaderboard
89 GPT-5.4 Mini 1,398 high Mar 2026 Official leaderboard
90 GPT-5.1 1,398 medium Nov 2025 Official leaderboard
91 Claude Sonnet 4.5 1,394 high, 32k Sep 2025 Official leaderboard
92 Claude Opus 4.1 1,390 Aug 2025 Official leaderboard
93 MiniMax-M2.5 1,386 Feb 2026 Official leaderboard
94 MiniMax-M2.1 1,384 Dec 2025 Official leaderboard
95 Grok 4.20 1,376 reasoning Feb 2026 Official leaderboard
96 Gemma 4 31B IT 1,370 Apr 2026 Official leaderboard
97 Solar Pro 4 1,369 Aug 2026 Official leaderboard
98 DeepSeek-V3.2 1,362 thinking Dec 2025 Official leaderboard
99 Qwen3.5-122B-A10B 1,360 Feb 2026 Official leaderboard
100 Gemma 4 26B A4B 1,358 Apr 2026 Official leaderboard
101 Tencent Hy3 preview 1,358 Apr 2026 Official leaderboard
102 Grok 4.3 1,357 Apr 2026 Official leaderboard
103 Qwen3.5-27B 1,357 Feb 2026 Official leaderboard
104 Muse Glimmer 1,354 Aug 2026 Official leaderboard
105 Laguna M.1 1,350 Apr 2026 Official leaderboard
106 GLM-4.6 1,342 Sep 2025 Official leaderboard
107 GPT-5.2 Codex 1,339 Dec 2025 Official leaderboard
108 GPT-5.1-Codex 1,338 Nov 2025 Official leaderboard
109 MiMo-V2-Flash 1,331 non-thinking Dec 2025 Official leaderboard
110 Claude Haiku 4.5 1,330 Oct 2025 Official leaderboard
111 Kimi K2 Thinking Turbo 1,322 Nov 2025 Official leaderboard
112 Laguna XS.2 1,304 Apr 2026 Official leaderboard
113 MiniMax-M2 1,299 Oct 2025 Official leaderboard
114 Qwen3-Coder-480B-A35B 1,274 Jul 2025 Official leaderboard
115 DeepSeek-V3.2-Exp 1,272 Sep 2025 Official leaderboard
116 Mistral Medium 3.5 1,263 Apr 2026 Official leaderboard
117 Gemini 3.1 Flash-Lite 1,256 Mar 2026 Official leaderboard
118 Qwen3.5-35B-A3B 1,253 Feb 2026 Official leaderboard
119 Qwen3.5-Flash 1,244 Feb 2026 Official leaderboard
120 GPT-5.1-Codex-mini 1,243 Nov 2025 Official leaderboard
121 Grok 4.1 Fast 1,242 reasoning Nov 2025 Official leaderboard
122 Trinity Large Thinking 1,237 Apr 2026 Official leaderboard
123 Mistral Large 3 1,231 Dec 2025 Official leaderboard
124 Gemini 2.5 Pro Jun 2025 1,226 Jun 2025 Official leaderboard
125 Grok 4.1 1,216 thinking Nov 2025 Official leaderboard
126 Devstral 2 1,195 Dec 2025 Official leaderboard
127 Granite 4.1 8B 1,193 Apr 2026 Official leaderboard
128 Mercury 2 1,171 Feb 2026 Official leaderboard
129 grok-code-fast-1 1,165 Aug 2025 Official leaderboard
130 Grok 4 Fast 1,159 reasoning Sep 2025 Official leaderboard
131 Devstral Medium 1,071 Jul 2025 Official leaderboard

Labs report scores for 5 models in their cards. Switch the scores above to rank them together.

Rankings by category

We read 2 categories from Arena: HTML and React. Each is rated on the votes for one kind of prompt. One vote counts in every category its prompt fits. GPT-6.1 Sol leads HTML and Claude Fable 5.2 leads React. Arrows show how far a model moved from its overall rank among the models we track.

HTML

130 models we track have a rating here.

  1. 1 GPT-6.1 Sol ↑7 1,796
  2. 2 GPT-6 Astra ↑3 1,786
  3. 3 Gemini 4 Carbon ↑1 1,768
  4. 4 Claude Fable 5.2 ↓3 1,760
  5. 5 Claude Sonnet 5.5 ↓2 1,753
  6. 6 Gemini 4 Hydrogen ↑4 1,748
  7. 7 Qwen4-Max ↓1 1,747
  8. 8 GPT-6.1 Terra ↑5 1,736
  9. 9 Claude Opus 5.5 ↓7 1,729
  10. 10 Muse Wonder Full ↓1 1,723

More effort adds a median 35 elo

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 Sonnet 5.5
high xhigh
1,772
Claude Opus 5
high
1,691
Muse Spark 1.3
xhigh
1,655
DeepSeek-V4-Pro
high high
1,581
Claude Opus 4.7
high
1,557
Claude Opus 4.8
high
1,555
Claude Opus 4.6
high
1,547
Gemini 3.5 Flash
medium
1,500
Claude Opus 4.5
high, 32k
1,493
Gemini 3 Flash
minimal
1,440
Kimi K2.5
instant
1,437
GPT-5.1
medium
1,398

Source: Official Code Arena leaderboard

ModelEffortHarnessScoreCost per taskOutput tokens
Claude Fable 5.2 xhigh 1,826
Claude Opus 5.5 max 1,816
Claude Sonnet 5.5 xhigh 1,772
Gemini 4 Carbon high 1,768
GPT-6 Astra max 1,763
Qwen4-Max xhigh 1,750
Claude Fable 5.1 max 1,743
GPT-6.1 Sol max 1,742
Muse Wonder Full max 1,724
Claude Sonnet 5.5 high 1,716
Gemini 4 Hydrogen high 1,704
Claude Opus 5 max 1,691
Kimi K3.1 Pro max 1,686
GPT-6.1 Terra max 1,681
Gemini 4 Argon high 1,679
Qwen3.8 Max (0902) 1,676
GPT-6 Sol max 1,673
Qwen 3.8 Max 1,670
DeepSeek V4.1 Flash max 1,661
Kimi K3 max 1,658
Claude Opus 5 high 1,657
Muse Spark 1.3 max 1,655
Muse Wonder max 1,647
Inkling 2 Small 1,645
Grok 4.7 xhigh 1,640
MiMo-V2.6 Flash 1,639
Tencent Hy4 preview 1,632
Claude Fable 5 high 1,626
Qwen3.8-Flash-Next 1,625
MiMo-V2.6 Pro 1,624
GLM-5.3 max 1,622
Muse Spark 1.3 xhigh 1,621
DeepSeek V4.1 Flash max 1,621
Grok 4.6 high 1,618
GPT-5.6 Sol xHigh, Codex 1,616
GLM-5.3-Flash 1,609
Muse Ember max 1,608
GLM-5.2 max 1,608
Claude Haiku 5.5 high 1,593
Qwen 3.8 27B 1,590
Gemini 3.7 Flash high 1,588
Gemini 3.8 Flash high 1,583
MiniMax-M3.1-Flash 1,582
DeepSeek-V4-Flash high 1,582
DeepSeek-V4-Pro high 1,581
GPT-6 Luna max 1,577
Step 5 Preview high 1,572
Mistral Large 4 1,566
Claude Opus 4.7 high 1,557
Claude Opus 4.8 high 1,555
Claude Opus 4.7 1,555
Grok 4.5 1,552
Claude Opus 4.6 high 1,547
Muse Spark 1.1 1,542
Claude Sonnet 5 high 1,539
Gemini 3.6 Flash high 1,538
Claude Opus 4.6 1,537
Claude Opus 4.8 1,536
Muse Spark 1.2 xhigh 1,534
Muse Spark Open max 1,527
Claude Sonnet 4.6 1,522
GPT-5.6 Terra xHigh, Codex 1,520
Seed2.1 Pro 1,519
GPT-5.6 Luna xHigh, Codex 1,519
Qwen3.7-Max 1,515
GPT-5.5 xHigh, Codex 1,512
Kimi K2.6 1,510
GLM-5.1 1,508
Tencent Hy3 1,506
Gemini 3.5 Flash high 1,500
Claude Opus 4.5 high, 32k 1,493
Gemini 3.5 Flash medium 1,490
GPT-5.5 High, Codex 1,487
MiniMax-M3 1,484
Qwen 3.6 Max (Preview) 1,482
MiMo-V2.5-Pro 1,479
Kimi K2.7 Code 1,474
Claude Opus 4.5 1,469
DeepSeek-V4-Pro high 1,464
GPT-5.4 High, Codex 1,462
Qwen 3.6 Plus 1,461
GPT-5.5 Codex 1,456
DeepSeek-V4-Pro 1,449
Gemini 3.1 Pro 1,446
GPT-5.4 Medium, Codex 1,442
Gemini 3 Pro 1,441
Gemini 3 Flash 1,440
MiMo-V2.5 1,438
Kimi K2.5 thinking 1,437
Beam 1.0 1,436
GLM-4.7 1,436
GLM-5 1,435
MiMo-V2-Pro 1,434
Gemini 3.5 Flash-Lite 1,432
DeepSeek-V4-Flash high 1,431
GPT-5.2 1,419
GPT-5 medium 1,417
Inkling 1,414
Inkling-Small 1,408
GPT-5.3 Codex Codex 1,406
Kimi K2.5 instant 1,406
Nemotron 3.5 Super VL nvfp4 1,401
Qwen3.5 397B-A17B 1,400
GPT-5.4 1,400
MiniMax-M2.7 1,398
GPT-5.4 Mini high 1,398
GPT-5.1 medium 1,398
Claude Sonnet 4.5 high, 32k 1,394
Claude Opus 4.1 1,390
MiniMax-M2.5 1,386
Claude Sonnet 4.5 1,385
Gemini 3 Flash minimal 1,385
MiniMax-M2.1 1,384
Grok 4.20 reasoning 1,376
GPT-5.3 Codex Codex 1,371
Gemma 4 31B IT 1,370
Solar Pro 4 1,369
DeepSeek-V3.2 thinking 1,362
Qwen3.5-122B-A10B 1,360
Gemma 4 26B A4B 1,358
Tencent Hy3 preview 1,358
Grok 4.3 1,357
Qwen3.5-27B 1,357
Muse Glimmer 1,354
Laguna M.1 1,350
GPT-5.1 1,342
GLM-4.6 1,342
GPT-5.2 Codex 1,339
GPT-5.1-Codex 1,338
MiMo-V2-Flash non-thinking 1,331
Claude Haiku 4.5 1,330
DeepSeek-V3.2 1,326
Kimi K2 Thinking Turbo 1,322
Laguna XS.2 1,304
MiniMax-M2 1,299
MiMo-V2-Flash thinking 1,292
Qwen3-Coder-480B-A35B 1,274
DeepSeek-V3.2-Exp 1,272
Mistral Medium 3.5 1,263
Gemini 3.1 Flash-Lite 1,256
Qwen3.5-35B-A3B 1,253
Qwen3.5-Flash 1,244
GPT-5.1-Codex-mini 1,243
Grok 4.1 Fast reasoning 1,242
Trinity Large Thinking 1,237
Mistral Large 3 1,231
Gemini 2.5 Pro Jun 2025 1,226
Grok 4.1 thinking 1,216
Devstral 2 1,195
Granite 4.1 8B 1,193
Mercury 2 1,171
grok-code-fast-1 1,165
Grok 4 Fast reasoning 1,159
Devstral Medium 1,071

More effort adds a median 35 elo

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 Sonnet 5.5
high xhigh
1,772
Claude Opus 5
high
1,691
Muse Spark 1.3
xhigh
1,655
DeepSeek-V4-Pro
high high
1,581
Claude Opus 4.7
high
1,557
Claude Opus 4.8
high
1,555
Claude Opus 4.6
high
1,547
Gemini 3.5 Flash
medium
1,500
Claude Opus 4.5
high, 32k
1,493
Gemini 3 Flash
minimal
1,440
Kimi K2.5
instant
1,437
GPT-5.1
medium
1,398

Source: Official Code Arena leaderboard

ModelEffortHarnessScoreCost per taskOutput tokens
Claude Fable 5.2 xhigh 1,826
Claude Opus 5.5 max 1,816
Claude Sonnet 5.5 xhigh 1,772
Gemini 4 Carbon high 1,768
GPT-6 Astra max 1,763
Qwen4-Max xhigh 1,750
Claude Fable 5.1 max 1,743
GPT-6.1 Sol max 1,742
Muse Wonder Full max 1,724
Claude Sonnet 5.5 high 1,716
Gemini 4 Hydrogen high 1,704
Claude Opus 5 max 1,691
Kimi K3.1 Pro max 1,686
GPT-6.1 Terra max 1,681
Gemini 4 Argon high 1,679
Qwen3.8 Max (0902) 1,676
GPT-6 Sol max 1,673
Qwen 3.8 Max 1,670
DeepSeek V4.1 Flash max 1,661
Kimi K3 max 1,658
Claude Opus 5 high 1,657
Muse Spark 1.3 max 1,655
Muse Wonder max 1,647
Inkling 2 Small 1,645
Grok 4.7 xhigh 1,640
MiMo-V2.6 Flash 1,639
Tencent Hy4 preview 1,632
Claude Fable 5 high 1,626
Qwen3.8-Flash-Next 1,625
MiMo-V2.6 Pro 1,624
GLM-5.3 max 1,622
Muse Spark 1.3 xhigh 1,621
DeepSeek V4.1 Flash max 1,621
Grok 4.6 high 1,618
GPT-5.6 Sol xHigh, Codex 1,616
GLM-5.3-Flash 1,609
Muse Ember max 1,608
GLM-5.2 max 1,608
Claude Haiku 5.5 high 1,593
Qwen 3.8 27B 1,590
Gemini 3.7 Flash high 1,588
Gemini 3.8 Flash high 1,583
MiniMax-M3.1-Flash 1,582
DeepSeek-V4-Flash high 1,582
DeepSeek-V4-Pro high 1,581
GPT-6 Luna max 1,577
Step 5 Preview high 1,572
Mistral Large 4 1,566
Claude Opus 4.7 high 1,557
Claude Opus 4.8 high 1,555
Claude Opus 4.7 1,555
Grok 4.5 1,552
Claude Opus 4.6 high 1,547
Muse Spark 1.1 1,542
Claude Sonnet 5 high 1,539
Gemini 3.6 Flash high 1,538
Claude Opus 4.6 1,537
Claude Opus 4.8 1,536
Muse Spark 1.2 xhigh 1,534
Muse Spark Open max 1,527
Claude Sonnet 4.6 1,522
GPT-5.6 Terra xHigh, Codex 1,520
Seed2.1 Pro 1,519
GPT-5.6 Luna xHigh, Codex 1,519
Qwen3.7-Max 1,515
GPT-5.5 xHigh, Codex 1,512
Kimi K2.6 1,510
GLM-5.1 1,508
Tencent Hy3 1,506
Gemini 3.5 Flash high 1,500
Claude Opus 4.5 high, 32k 1,493
Gemini 3.5 Flash medium 1,490
GPT-5.5 High, Codex 1,487
MiniMax-M3 1,484
Qwen 3.6 Max (Preview) 1,482
MiMo-V2.5-Pro 1,479
Kimi K2.7 Code 1,474
Claude Opus 4.5 1,469
DeepSeek-V4-Pro high 1,464
GPT-5.4 High, Codex 1,462
Qwen 3.6 Plus 1,461
GPT-5.5 Codex 1,456
DeepSeek-V4-Pro 1,449
Gemini 3.1 Pro 1,446
GPT-5.4 Medium, Codex 1,442
Gemini 3 Pro 1,441
Gemini 3 Flash 1,440
MiMo-V2.5 1,438
Kimi K2.5 thinking 1,437
Beam 1.0 1,436
GLM-4.7 1,436
GLM-5 1,435
MiMo-V2-Pro 1,434
Gemini 3.5 Flash-Lite 1,432
DeepSeek-V4-Flash high 1,431
GPT-5.2 1,419
GPT-5 medium 1,417
Inkling 1,414
Inkling-Small 1,408
GPT-5.3 Codex Codex 1,406
Kimi K2.5 instant 1,406
Nemotron 3.5 Super VL nvfp4 1,401
Qwen3.5 397B-A17B 1,400
GPT-5.4 1,400
MiniMax-M2.7 1,398
GPT-5.4 Mini high 1,398
GPT-5.1 medium 1,398
Claude Sonnet 4.5 high, 32k 1,394
Claude Opus 4.1 1,390
MiniMax-M2.5 1,386
Claude Sonnet 4.5 1,385
Gemini 3 Flash minimal 1,385
MiniMax-M2.1 1,384
Grok 4.20 reasoning 1,376
GPT-5.3 Codex Codex 1,371
Gemma 4 31B IT 1,370
Solar Pro 4 1,369
DeepSeek-V3.2 thinking 1,362
Qwen3.5-122B-A10B 1,360
Gemma 4 26B A4B 1,358
Tencent Hy3 preview 1,358
Grok 4.3 1,357
Qwen3.5-27B 1,357
Muse Glimmer 1,354
Laguna M.1 1,350
GPT-5.1 1,342
GLM-4.6 1,342
GPT-5.2 Codex 1,339
GPT-5.1-Codex 1,338
MiMo-V2-Flash non-thinking 1,331
Claude Haiku 4.5 1,330
DeepSeek-V3.2 1,326
Kimi K2 Thinking Turbo 1,322
Laguna XS.2 1,304
MiniMax-M2 1,299
MiMo-V2-Flash thinking 1,292
Qwen3-Coder-480B-A35B 1,274
DeepSeek-V3.2-Exp 1,272
Mistral Medium 3.5 1,263
Gemini 3.1 Flash-Lite 1,256
Qwen3.5-35B-A3B 1,253
Qwen3.5-Flash 1,244
GPT-5.1-Codex-mini 1,243
Grok 4.1 Fast reasoning 1,242
Trinity Large Thinking 1,237
Mistral Large 3 1,231
Gemini 2.5 Pro Jun 2025 1,226
Grok 4.1 thinking 1,216
Devstral 2 1,195
Granite 4.1 8B 1,193
Mercury 2 1,171
grok-code-fast-1 1,165
Grok 4 Fast reasoning 1,159
Devstral Medium 1,071

13 models have held number one on the official leaderboard since its release in November 2025 13 models have held number one with claims included since its release in November 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 Google DeepMind Anthropic DeepSeek Moonshot AI Z.ai Qwen
Own leaderboard 13 leaders
Lab claims 3 leaders
Qwen4-Max 1,750

Sources: Official Code Arena leaderboard and labs’ model cards

Scores over time

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

Plot with other benchmarks
On the benchmark’s own leaderboard Reported by the lab in its model card
1,000 1,200 1,400 1,600 1,800 2,000 2025 2026 2027 1,000 1,200 1,400 1,600 1,800 2,000 2025 2026 2027

Sources: Official Code Arena leaderboard and labs’ model cards

3 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. Google DeepMind accounts for 4 of the 8 releases that named it since 2024.

Google DeepMind
Thinking Machines
Qwen
DateLaunch postScoreAs the post writes it
Nov 15, 2026 Qwen4-Max 1750 Web development, CodeArena (Elo), cited from Arena
Nov 5, 2026 Inkling 2 Small 1653 Code Arena, 1653 Elo
Aug 13, 2026 Gemini 3.7 Flash 1588 Code Arena (Web development, Elo)

3 system cards report it, from 3 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
Aug 13, 2026 Gemini 3.7 Flash model card 1588 Code Arena, web development, Elo (results table, p.5) Capabilities
Jul 27, 2026 Kimi K3 technical report 1678 WebDev Arena (Elo), rank 1 of 99 (Table 5). Mapped to the current Arena WebDev board Other
Feb 17, 2026 GLM-5 technical report 1449 LMArena Code Arena (Agentic WebDev) score, rank 6 (Figure 3 screenshot) Capabilities

5 lab claims next to the leaderboard

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. Every benchmark.

Model Lab says Board says Gap What differs
Kimi K3 1,678 WebDev Arena (Elo), rank 1 of 99 (Table 5). Mapped to the current Arena WebDev board 1,658 Leaderboard, max +20 Moonshot quotes Arena's July 23 rating, while the board reflects votes collected through November.
GLM-5 1,449 LMArena Code Arena (Agentic WebDev) score, rank 6 (Figure 3 screenshot) 1,435 Leaderboard +14 The lab reproduces an early Code Arena snapshot, while the board uses a later rating from additional votes.
Inkling 2 Small 1,653 Code Arena, 1653 Elo 1,645 Leaderboard +8
Gemini 3.7 Flash 1,588 Code Arena (Web development, Elo) 1,588 Leaderboard, high Same Google quotes an August Arena rating as an integer, while the board supplies a later rating with decimal precision.
Qwen4-Max 1,750 Web development, CodeArena (Elo), cited from Arena 1,750 Leaderboard, xhigh Same

Versions

More in Coding

All 523 in Coding
  • SWE-bench Verified In use 500 human-validated GitHub issues from 12 Python repos. Agent writes a patch that must pass hidden tests. Claude Opus 4.7 83.5%
  • LiveCodeBench v6 In use Competitive programming problems collected after model cutoffs from LeetCode, AtCoder, Codeforces. Scored pass@1 on hidden tests. DeepSeek-V4-Pro 93.5%
  • SWE-bench Multilingual In use 300 GitHub-issue tasks across nine programming languages in SWE-bench format. Patch graded by repository tests. Claude Fable 5.2 96.6%
  • DeepSWE In use 113 original long-horizon engineering tasks across 91 repos and five languages, written from scratch. Hand-written verifiers accept alternative solutions. GPT-6 Astra 74.1%
  • SciCode In use Scientist-curated research coding problems split into subproblems across natural sciences. Code checked against test cases. Seed2.1 Pro 59.8%
  • Codeforces rating In use Model solves recent Codeforces contest problems. An Elo-style rating is computed from simulated contest performance. DeepSeek V4.1 Flash 3,471

Data audit

10 of 11 checks pass, 1 warning. Look first at the Task access check. We don’t know whether the tasks are public. Every benchmark

Catalog record 1 warning 1 pass
  • Warning Task access We don’t know whether the tasks are public.
  • Pass Confidence Checked against a primary source.
Scores 4 pass 1 note
  • Pass Independent runs Scores from the official leaderboard (134 entries), launch posts (3 scores) and system cards (3 scores).
  • Pass Models scored 131 models we track, plus 3 other entries on its leaderboard.
  • Pass Newest score The newest is from November 2026, for Qwen4-Max.
  • Pass Frontier models 9 of the top 10 have a score, led by Claude Fable 5.2 (#2).
  • Note Headroom Scored as an Elo rating, with no fixed ceiling.
Leaderboard import 3 pass
  • Pass Importer We read the board on arena.ai: 154 rows for models we track and 3 other entries at the last read.
  • Pass Last read November 18th, 2026.
  • Pass Read worked The last read worked.
Consistency 2 pass
  • Pass Lab claims All 5 pairs agree within 10 points.
  • Pass Known issues No published audit found problems.

How we check