Skip to content
Model leaderboard

Every AI model, ranked

123 models rated on the benchmarks that matter, from paid work and coding agents to the hardest exams, like a chess rating: every benchmark two models share is a game between them. Open one for its price, its strengths and the source of every number.

Updated Nov 12, 2026.

  1. 1stClaude Fable 5.22,275
  2. 2ndGemini 4 Carbon2,266
  3. 3rdClaude Opus 5.52,045
  4. 4thGemini 4 Argon2,039
  5. 5thGPT-6 Astra1,927
  6. 6thClaude Fable 5.11,922
  7. 7thClaude Sonnet 5.51,887
  8. 8thGPT-6.1 Sol1,852
  9. 9thClaude Opus 51,844
  10. 10thMuse Wonder1,824
  11. 11thGPT-6.1 Terra1,818
  12. 12thGPT-5.5 Pro1,769
  13. 13thClaude Fable 51,748
  14. 14thKimi K3.1 Pro1,722
  15. 15thMuse Spark 1.31,700
  16. 16thGPT-5.6 Sol1,677
  17. 17thGemini 3.7 Flash1,661
  18. 18thMuse Ember1,654
  19. 19thGPT-5.4 Pro1,600
  20. 20thGemini 3.8 Flash1,597
  21. 21stGPT-6 Sol1,589
  22. 22ndQwen3.8 Max1,571
  23. 23rdGLM-5.31,552
  24. 24thClaude Opus 4.81,539
  25. 25thKimi K31,537
  26. 26thGrok 4.61,532
  27. 27thDeepSeek-V4.1-Flash1,530
  28. 28thGPT-5.51,520
  29. 29thMuse Spark 1.11,503
  30. 30thClaude Opus 4.71,496
  31. 31stGPT-5.6 Terra1,482
  32. 32ndSeed 2.1 Pro1,476
  33. 33rdGLM-5.3-Flash1,454
  34. 34thMuse Spark 1.21,448
  35. 35thGemini 3.6 Flash1,440
  36. 36thQwen3.8-Flash-Next1,438
  37. 37thDeepSeek-V4-Pro-08131,426
  38. 38thGrok 4.51,421
  39. 39thGrok 4.71,421
  40. 40thQwen3.7 Max1,418
  41. 41stClaude Sonnet 51,413
  42. 42ndSeed 2.1 Turbo1,403
  43. 43rdClaude Haiku 5.51,386
  44. 44thGLM-5.21,386
  45. 45thQwen3.8 Flash1,380
  46. 46thGPT-5.41,379
  47. 47thGemini 3.5 Flash1,367
  48. 48thClaude Opus 4.61,363
  49. 49thGemini 3.1 Pro1,353
  50. 50thGemini 3 Pro1,344
  51. 51stQwen3.8-27B1,306
  52. 52ndMuse Spark Open1,305
  53. 53rdMistral Large 41,305
  54. 54thKimi K2.61,301
  55. 55thGPT-5.6 Luna1,291
  56. 56thQwen3.6 Max1,277
  57. 57thDeepSeek-V4-Pro-Max1,275
  58. 58thGPT-6 Luna1,273
  59. 59thMuse Spark1,249
  60. 60thGPT-5.2 Pro1,249
  61. 61stGLM-5.11,241
  62. 62ndClaude Sonnet 4.61,222
  63. 63rdGemini 3 Flash1,211
  64. 64thMistral Large 41,197
  65. 65thQwen3.7-Plus1,194
  66. 66thMiniMax M31,184
  67. 67thClaude Opus 4.51,171
  68. 68thKimi K2.7 Code1,170
  69. 69thDeepSeek-V4-Flash-07311,126
  70. 70thGPT-5.21,125
  71. 71stQwen3.6 Plus1,118
  72. 72ndDeepSeek-V4-Flash-Max1,117
  73. 73rdGLM-51,115
  74. 74thGPT-5.1 Thinking1,107
  75. 75thGPT-51,038
  76. 76thKimi K2.51,020
  77. 77thNemotron 3.5 Super VL (120B A12B)999
  78. 78thGLM-4.7994
  79. 79thQwen3.5-397B-A17B983
  80. 80thQwen3.5-122B-A10B978
  81. 81stClaude Sonnet 4.5959
  82. 82ndQwen3.5-27B949
  83. 83rdMuse Glimmer-30B943
  84. 84thGPT-5.4 mini943
  85. 85thMiniMax M2.5940
  86. 86thNemotron 3 Ultra (550B A55B)933
  87. 87thQwen3.6-27B920
  88. 88thGemini 3.5 Flash-Lite917
  89. 89thGemma 4 31B904
  90. 90thGPT-5.5 Instant878
  91. 91stQwen3 Max Thinking862
  92. 92ndGrok 4.3862
  93. 93rdGemini 2.5 Pro Preview 06-05858
  94. 94thQwen3.5-35B-A3B858
  95. 95thSeed 1.8858
  96. 96thClaude Opus 4.1853
  97. 97thGemini 3.1 Flash-Lite824
  98. 98thDeepSeek-V3.2 (Thinking)799
  99. 99thMiniMax M2.1788
  100. 100thGLM-4.6777
  101. 101stQwen3.6-35B-A3B772
  102. 102ndGemma 4 26B-A4B765
  103. 103rdDeepSeek-V3.2716
  104. 104thGPT-5.4 nano709
  105. 105thGPT-5 mini679
  106. 106thClaude Haiku 4.5654
  107. 107thGrok 4 Fast652
  108. 108thQwen3 VL 235B A22B Instruct636
  109. 109thSeed 2.0 Mini633
  110. 110thQwen3.5 Flash612
  111. 111thClaude Sonnet 4611
  112. 112thNemotron 3 Super (120B A12B)582
  113. 113thGPT OSS 120B492
  114. 114thDeepSeek-R1-0528485
  115. 115thMiniMax M2473
  116. 116thKimi K2-Thinking-0905460
  117. 117thQwen3 VL 32B Instruct452
  118. 118thGemma 4 12B372
  119. 119thNemotron 3.5 Lightning (30B A3B)368
  120. 120thQwen3 VL 30B A3B Instruct353
  121. 121stGPT-5 nano273
  122. 122ndQwen3 VL 8B Instruct171
  123. 123rdQwen3 VL 4B Instruct73