Get started

One scale, fit over other people's scores.

The openly licensed boards on /benchmarks measure different things on scales that do not convert, so none of them is added to another. This is the other way to put them on one axis: a capability per run and a difficulty per benchmark column, fit together, so both sit on the same rule. Vitna ran none of the evaluations behind it.

319 ranked of 521 runs · 46 columns · 3,630 cells · 15.2% full·boards read ·fit

Top of the scale135.84gpt-6.2-astraat max effort · 14 columns on 1 board
Widest evidence38google/gemini-3.5-flashcolumns behind it, at high effort · 111.12 on the scale
Hardest column153FrontierMath-ErdosEpoch AI Benchmarking Hub · above every ranked run, one in four to three in four across 15 points

12 of 46 columns sort runs within one standard deviation of their difficulty; 5 are wider than the whole ranked range and sort nothing on it.

405570851001151301451600570807060504030201columns, at their difficultycapability, mean 100, one tick per standard deviationranked runs per 5 points40 to 45 on the scale: 0 ranked runs · 0 set aside40 to 45 on the scale0 ranked runs · 0 set aside45 to 50 on the scale: 0 ranked runs · 0 set aside45 to 50 on the scale0 ranked runs · 0 set aside50 to 55 on the scale: 0 ranked runs · 0 set aside50 to 55 on the scale0 ranked runs · 0 set aside55 to 60 on the scale: 0 ranked runs · 1 set aside55 to 60 on the scale0 ranked runs · 1 set aside60 to 65 on the scale: 2 ranked runs · 2 set aside60 to 65 on the scale2 ranked runs · 2 set aside65 to 70 on the scale: 3 ranked runs · 6 set aside65 to 70 on the scale3 ranked runs · 6 set aside70 to 75 on the scale: 10 ranked runs · 17 set aside70 to 75 on the scale10 ranked runs · 17 set aside75 to 80 on the scale: 9 ranked runs · 15 set aside75 to 80 on the scale9 ranked runs · 15 set aside80 to 85 on the scale: 20 ranked runs · 7 set aside80 to 85 on the scale20 ranked runs · 7 set aside85 to 90 on the scale: 14 ranked runs · 15 set aside85 to 90 on the scale14 ranked runs · 15 set aside90 to 95 on the scale: 33 ranked runs · 17 set aside90 to 95 on the scale33 ranked runs · 17 set aside95 to 100 on the scale: 30 ranked runs · 36 set aside95 to 100 on the scale30 ranked runs · 36 set aside100 to 105 on the scale: 49 ranked runs · 27 set aside100 to 105 on the scale49 ranked runs · 27 set aside105 to 110 on the scale: 44 ranked runs · 24 set aside105 to 110 on the scale44 ranked runs · 24 set aside110 to 115 on the scale: 57 ranked runs · 12 set aside110 to 115 on the scale57 ranked runs · 12 set aside115 to 120 on the scale: 27 ranked runs · 9 set aside115 to 120 on the scale27 ranked runs · 9 set aside120 to 125 on the scale: 10 ranked runs · 5 set aside120 to 125 on the scale10 ranked runs · 5 set aside125 to 130 on the scale: 4 ranked runs · 5 set aside125 to 130 on the scale4 ranked runs · 5 set aside130 to 135 on the scale: 6 ranked runs · 4 set aside130 to 135 on the scale6 ranked runs · 4 set aside135 to 140 on the scale: 1 ranked run · 0 set aside135 to 140 on the scale1 ranked run · 0 set aside140 to 145 on the scale: 0 ranked runs · 0 set aside140 to 145 on the scale0 ranked runs · 0 set aside145 to 150 on the scale: 0 ranked runs · 0 set aside145 to 150 on the scale0 ranked runs · 0 set aside150 to 155 on the scale: 0 ranked runs · 0 set aside150 to 155 on the scale0 ranked runs · 0 set aside155 to 160 on the scale: 0 ranked runs · 0 set aside155 to 160 on the scale0 ranked runs · 0 set asidetablereformat · LiveBench: 41 on the scale · 40 points from one in four to three in four · below every ranked runtablereformat · LiveBench41 on the scale · 40 points from one in four to three in four · below every ranked runmath_comp · LiveBench: 42 on the scale · 51 points from one in four to three in four · below every ranked runmath_comp · LiveBench42 on the scale · 51 points from one in four to three in four · below every ranked runAMPS_Hard · LiveBench: 47 on the scale · 45 points from one in four to three in four · below every ranked runAMPS_Hard · LiveBench47 on the scale · 45 points from one in four to three in four · below every ranked runspatial · LiveBench: 53 on the scale · 39 points from one in four to three in four · below every ranked runspatial · LiveBench53 on the scale · 39 points from one in four to three in four · below every ranked runolympiad · LiveBench: 72 on the scale · 43 points from one in four to three in fourolympiad · LiveBench72 on the scale · 43 points from one in four to three in fourstory_generation · LiveBench: 74 on the scale · 98 points from one in four to three in fourstory_generation · LiveBench74 on the scale · 98 points from one in four to three in fourcode_generation · LiveBench: 76 on the scale · 66 points from one in four to three in fourcode_generation · LiveBench76 on the scale · 66 points from one in four to three in fourtypos · LiveBench: 77 on the scale · 61 points from one in four to three in fourtypos · LiveBench77 on the scale · 61 points from one in four to three in fourMATH level 5 · Epoch AI Benchmarking Hub: 81 on the scale · 13 points from one in four to three in four · sorts within one standard deviationMATH level 5 · Epoch AI Benchmarking Hub81 on the scale · 13 points from one in four to three in four · sorts within one standard deviationGPQA diamond · Epoch AI Benchmarking Hub: 83 on the scale · 30 points from one in four to three in fourGPQA diamond · Epoch AI Benchmarking Hub83 on the scale · 30 points from one in four to three in fourSWE-Bench verified · Epoch AI Benchmarking Hub: 84 on the scale · 50 points from one in four to three in fourSWE-Bench verified · Epoch AI Benchmarking Hub84 on the scale · 50 points from one in four to three in foursummarize · LiveBench: 85 on the scale · 75 points from one in four to three in foursummarize · LiveBench85 on the scale · 75 points from one in four to three in fourparaphrase · LiveBench: 86 on the scale · 91 points from one in four to three in fourparaphrase · LiveBench86 on the scale · 91 points from one in four to three in fourcode_completion · LiveBench: 87 on the scale · 48 points from one in four to three in fourcode_completion · LiveBench87 on the scale · 48 points from one in four to three in fourtheory_of_mind · LiveBench: 88 on the scale · 44 points from one in four to three in fourtheory_of_mind · LiveBench88 on the scale · 44 points from one in four to three in fourconnections · LiveBench: 91 on the scale · 15 points from one in four to three in fourconnections · LiveBench91 on the scale · 15 points from one in four to three in foursimplify · LiveBench: 92 on the scale · 89 points from one in four to three in foursimplify · LiveBench92 on the scale · 89 points from one in four to three in fourOTIS Mock AIME 2024-2025 · Epoch AI Benchmarking Hub: 94 on the scale · 13 points from one in four to three in four · sorts within one standard deviationOTIS Mock AIME 2024-2025 · Epoch AI Benchmarking Hub94 on the scale · 13 points from one in four to three in four · sorts within one standard deviationlogic_with_navigation · LiveBench: 96 on the scale · 41 points from one in four to three in fourlogic_with_navigation · LiveBench96 on the scale · 41 points from one in four to three in fourpolyglot pass rate · Aider polyglot: 97 on the scale · 21 points from one in four to three in fourpolyglot pass rate · Aider polyglot97 on the scale · 21 points from one in four to three in fourjavascript · LiveBench: 99 on the scale · 57 points from one in four to three in fourjavascript · LiveBench99 on the scale · 57 points from one in four to three in fourzebra_puzzle · LiveBench: 102 on the scale · 10 points from one in four to three in four · sorts within one standard deviationzebra_puzzle · LiveBench102 on the scale · 10 points from one in four to three in four · sorts within one standard deviationconsecutive_events · LiveBench: 102 on the scale · 23 points from one in four to three in fourconsecutive_events · LiveBench102 on the scale · 23 points from one in four to three in fourintegrals_with_game · LiveBench: 104 on the scale · 15 points from one in four to three in fourintegrals_with_game · LiveBench104 on the scale · 15 points from one in four to three in fourplot_unscrambling · LiveBench: 106 on the scale · 37 points from one in four to three in fourplot_unscrambling · LiveBench106 on the scale · 37 points from one in four to three in fourFrontierMath-2025-02-28-Public · Epoch AI Benchmarking Hub: 106 on the scale · 7 points from one in four to three in four · sorts within one standard deviationFrontierMath-2025-02-28-Public · Epoch AI Benchmarking Hub106 on the scale · 7 points from one in four to three in four · sorts within one standard deviationFrontierMath-Tiers-1-3-v2-Private · Epoch AI Benchmarking Hub: 109 on the scale · 16 points from one in four to three in fourFrontierMath-Tiers-1-3-v2-Private · Epoch AI Benchmarking Hub109 on the scale · 16 points from one in four to three in fourpython · LiveBench: 109 on the scale · 64 points from one in four to three in fourpython · LiveBench109 on the scale · 64 points from one in four to three in fourFrontierMath-2025-02-28-Private · Epoch AI Benchmarking Hub: 115 on the scale · 16 points from one in four to three in fourFrontierMath-2025-02-28-Private · Epoch AI Benchmarking Hub115 on the scale · 16 points from one in four to three in fourSimpleQA Verified · Epoch AI Benchmarking Hub: 115 on the scale · 33 points from one in four to three in fourSimpleQA Verified · Epoch AI Benchmarking Hub115 on the scale · 33 points from one in four to three in fourFrontierMath-Tier-4-v2-Private · Epoch AI Benchmarking Hub: 116 on the scale · 10 points from one in four to three in four · sorts within one standard deviationFrontierMath-Tier-4-v2-Private · Epoch AI Benchmarking Hub116 on the scale · 10 points from one in four to three in four · sorts within one standard deviationFrontierMath-Tier-4-2025-07-01-Public · Epoch AI Benchmarking Hub: 116 on the scale · 3 points from one in four to three in four · sorts within one standard deviationFrontierMath-Tier-4-2025-07-01-Public · Epoch AI Benchmarking Hub116 on the scale · 3 points from one in four to three in four · sorts within one standard deviationtablejoin · LiveBench: 117 on the scale · 103 points from one in four to three in fourtablejoin · LiveBench117 on the scale · 103 points from one in four to three in fourMirrorCode · Epoch AI Benchmarking Hub: 119 on the scale · 24 points from one in four to three in fourMirrorCode · Epoch AI Benchmarking Hub119 on the scale · 24 points from one in four to three in fourChess Puzzles · Epoch AI Benchmarking Hub: 119 on the scale · 24 points from one in four to three in fourChess Puzzles · Epoch AI Benchmarking Hub119 on the scale · 24 points from one in four to three in fourFurniture Assembly · Epoch AI Benchmarking Hub: 120 on the scale · 17 points from one in four to three in fourFurniture Assembly · Epoch AI Benchmarking Hub120 on the scale · 17 points from one in four to three in fourFrontierMath-Tier-4-2025-07-01-Private · Epoch AI Benchmarking Hub: 120 on the scale · 12 points from one in four to three in four · sorts within one standard deviationFrontierMath-Tier-4-2025-07-01-Private · Epoch AI Benchmarking Hub120 on the scale · 12 points from one in four to three in four · sorts within one standard deviationMystery Game Puzzles · Epoch AI Benchmarking Hub: 121 on the scale · 24 points from one in four to three in fourMystery Game Puzzles · Epoch AI Benchmarking Hub121 on the scale · 24 points from one in four to three in fourtypescript · LiveBench: 122 on the scale · 38 points from one in four to three in fourtypescript · LiveBench122 on the scale · 38 points from one in four to three in fourOEIS Open Lite · Epoch AI Benchmarking Hub: 122 on the scale · 27 points from one in four to three in fourOEIS Open Lite · Epoch AI Benchmarking Hub122 on the scale · 27 points from one in four to three in fourEBR-bench · Epoch AI Benchmarking Hub: 123 on the scale · 15 points from one in four to three in four · sorts within one standard deviationEBR-bench · Epoch AI Benchmarking Hub123 on the scale · 15 points from one in four to three in four · sorts within one standard deviationOEIS Open · Epoch AI Benchmarking Hub: 127 on the scale · 27 points from one in four to three in fourOEIS Open · Epoch AI Benchmarking Hub127 on the scale · 27 points from one in four to three in fourSpireClimb (Slay the Spire 2, Ascension 10) · Epoch AI Benchmarking Hub: 136 on the scale · 10 points from one in four to three in four · above every ranked runSpireClimb (Slay the Spire 2, Ascension 10) · Epoch AI Benchmarking Hub136 on the scale · 10 points from one in four to three in four · above every ranked runSpireClimb · Epoch AI Benchmarking Hub: 137 on the scale · 10 points from one in four to three in four · above every ranked runSpireClimb · Epoch AI Benchmarking Hub137 on the scale · 10 points from one in four to three in four · above every ranked runSpireClimb (Slay the Spire 1, Ascension 20 Heart) · Epoch AI Benchmarking Hub: 139 on the scale · 10 points from one in four to three in four · above every ranked runSpireClimb (Slay the Spire 1, Ascension 20 Heart) · Epoch AI Benchmarking Hub139 on the scale · 10 points from one in four to three in four · above every ranked runFrontierMath-Erdos · Epoch AI Benchmarking Hub: 153 on the scale · 15 points from one in four to three in four · above every ranked runFrontierMath-Erdos · Epoch AI Benchmarking Hub153 on the scale · 15 points from one in four to three in four · above every ranked run
  1. 01FrontierMath-ErdosEpoch AI Benchmarking Hub · 153 on the scale · above every ranked run
  2. 02SpireClimb (Slay the Spire 1, Ascension 20 Heart)Epoch AI Benchmarking Hub · 139 on the scale · above every ranked run
  3. 03SpireClimbEpoch AI Benchmarking Hub · 137 on the scale · above every ranked run
  4. 04SpireClimb (Slay the Spire 2, Ascension 10)Epoch AI Benchmarking Hub · 136 on the scale · above every ranked run
  5. 05spatialLiveBench · 53 on the scale · below every ranked run
  6. 06AMPS_HardLiveBench · 47 on the scale · below every ranked run
  7. 07math_compLiveBench · 42 on the scale · below every ranked run
  8. 08tablereformatLiveBench · 41 on the scale · below every ranked run

The ranked runs span 61 to 136. 8 columns sit outside that: 4 sit above every ranked run, where nobody yet has an even chance, and 4 sit below every ranked run, where almost everything passes. The dashed outline is the 202 runs set aside for standing on fewer than 3 columns, kept in the fit and out of the ordering; 0 of them sit beyond the right edge. Runs are counted in bins of 5 points. A column in the accent sorts runs within one standard deviation of its difficulty; the rest are the field. Each numbered column is a door to its row below.

Ranked runs319 runs · 130 priced in the catalogmean 100, 15 to a standard deviation
  1. 001gpt-6.2-astranot in the catalogmax135.84141

    14 columns on 1 board, hardest first are the whole evidence behind 135.84. Each is a door to the column and everything else scored on it.

    1. FrontierMath-ErdosEpoch AI Benchmarking Hub0.10153 on the scale
    2. SpireClimb (Slay the Spire 1, Ascension 20 Heart)Epoch AI Benchmarking Hub0.33139 on the scale
    3. SpireClimbEpoch AI Benchmarking Hub0.41137 on the scale
    4. SpireClimb (Slay the Spire 2, Ascension 10)Epoch AI Benchmarking Hub0.49136 on the scale
    5. EBR-benchEpoch AI Benchmarking Hub0.92123 on the scale
    6. Mystery Game PuzzlesEpoch AI Benchmarking Hub0.95121 on the scale
    7. Furniture AssemblyEpoch AI Benchmarking Hub0.89120 on the scale
    8. Chess PuzzlesEpoch AI Benchmarking Hub0.78119 on the scale
    9. MirrorCodeEpoch AI Benchmarking Hub0.68119 on the scale
    10. FrontierMath-Tier-4-v2-PrivateEpoch AI Benchmarking Hub1116 on the scale
    11. SimpleQA VerifiedEpoch AI Benchmarking Hub0.79115 on the scale
    12. FrontierMath-Tiers-1-3-v2-PrivateEpoch AI Benchmarking Hub0.93109 on the scale
    13. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub194 on the scale
    14. GPQA diamondEpoch AI Benchmarking Hub0.9783 on the scale
  2. 002gemini-4-neonnot in the catalogxhigh134.5481

    8 columns on 1 board, hardest first are the whole evidence behind 134.54. Each is a door to the column and everything else scored on it.

    1. Mystery Game PuzzlesEpoch AI Benchmarking Hub0.85121 on the scale
    2. Furniture AssemblyEpoch AI Benchmarking Hub0.89120 on the scale
    3. Chess PuzzlesEpoch AI Benchmarking Hub0.83119 on the scale
    4. FrontierMath-Tier-4-v2-PrivateEpoch AI Benchmarking Hub0.98116 on the scale
    5. SimpleQA VerifiedEpoch AI Benchmarking Hub0.75115 on the scale
    6. FrontierMath-Tiers-1-3-v2-PrivateEpoch AI Benchmarking Hub0.91109 on the scale
    7. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub194 on the scale
    8. GPQA diamondEpoch AI Benchmarking Hub0.9683 on the scale
  3. 003openai/gpt-6-astramax132.41372

    37 columns on 2 boards, hardest first are the whole evidence behind 132.41. Each is a door to the column and everything else scored on it.

    1. FrontierMath-ErdosEpoch AI Benchmarking Hub0.03153 on the scale
    2. SpireClimb (Slay the Spire 1, Ascension 20 Heart)Epoch AI Benchmarking Hub0.33139 on the scale
    3. SpireClimbEpoch AI Benchmarking Hub0.34137 on the scale
    4. SpireClimb (Slay the Spire 2, Ascension 10)Epoch AI Benchmarking Hub0.35136 on the scale
    5. EBR-benchEpoch AI Benchmarking Hub0.76123 on the scale
    6. typescriptLiveBench43.33122 on the scale
    7. Mystery Game PuzzlesEpoch AI Benchmarking Hub0.84121 on the scale
    8. Furniture AssemblyEpoch AI Benchmarking Hub0.80120 on the scale
    9. Chess PuzzlesEpoch AI Benchmarking Hub0.74119 on the scale
    10. MirrorCodeEpoch AI Benchmarking Hub0.60119 on the scale
    11. tablejoinLiveBench58.37117 on the scale
    12. FrontierMath-Tier-4-v2-PrivateEpoch AI Benchmarking Hub0.98116 on the scale
    13. SimpleQA VerifiedEpoch AI Benchmarking Hub0.76115 on the scale
    14. pythonLiveBench65109 on the scale
    15. FrontierMath-Tiers-1-3-v2-PrivateEpoch AI Benchmarking Hub0.94109 on the scale
    16. plot_unscramblingLiveBench86.29106 on the scale
    17. integrals_with_gameLiveBench100104 on the scale
    18. consecutive_eventsLiveBench90.56102 on the scale
    19. zebra_puzzleLiveBench100102 on the scale
    20. javascriptLiveBench63.6499 on the scale
    21. logic_with_navigationLiveBench8896 on the scale
    22. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub194 on the scale
    23. simplifyLiveBench70.5392 on the scale
    24. connectionsLiveBench10091 on the scale
    25. theory_of_mindLiveBench84.6188 on the scale
    26. code_completionLiveBench80.4487 on the scale
    27. paraphraseLiveBench78.2586 on the scale
    28. summarizeLiveBench79.5585 on the scale
    29. GPQA diamondEpoch AI Benchmarking Hub0.9683 on the scale
    30. typosLiveBench8277 on the scale
    31. code_generationLiveBench80.2876 on the scale
    32. story_generationLiveBench73.9874 on the scale
    33. olympiadLiveBench92.1772 on the scale
    34. spatialLiveBench9853 on the scale
    35. AMPS_HardLiveBench9847 on the scale
    36. math_compLiveBench97.0642 on the scale
    37. tablereformatLiveBench10041 on the scale
  4. 004claude-fable-5-2not in the catalogmax132.06121

    12 columns on 1 board, hardest first are the whole evidence behind 132.06. Each is a door to the column and everything else scored on it.

    1. SpireClimb (Slay the Spire 1, Ascension 20 Heart)Epoch AI Benchmarking Hub0.13139 on the scale
    2. SpireClimbEpoch AI Benchmarking Hub0.15137 on the scale
    3. SpireClimb (Slay the Spire 2, Ascension 10)Epoch AI Benchmarking Hub0.17136 on the scale
    4. EBR-benchEpoch AI Benchmarking Hub0.90123 on the scale
    5. Mystery Game PuzzlesEpoch AI Benchmarking Hub0.90121 on the scale
    6. Furniture AssemblyEpoch AI Benchmarking Hub0.90120 on the scale
    7. Chess PuzzlesEpoch AI Benchmarking Hub0.79119 on the scale
    8. FrontierMath-Tier-4-v2-PrivateEpoch AI Benchmarking Hub1116 on the scale
    9. SimpleQA VerifiedEpoch AI Benchmarking Hub0.94115 on the scale
    10. FrontierMath-Tiers-1-3-v2-PrivateEpoch AI Benchmarking Hub0.95109 on the scale
    11. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub1.0094 on the scale
    12. GPQA diamondEpoch AI Benchmarking Hub0.9483 on the scale
  5. 005google/gemini-4-carbonhigh131.68101

    10 columns on 1 board, hardest first are the whole evidence behind 131.68. Each is a door to the column and everything else scored on it.

    1. FrontierMath-ErdosEpoch AI Benchmarking Hub0.03153 on the scale
    2. EBR-benchEpoch AI Benchmarking Hub0.88123 on the scale
    3. Mystery Game PuzzlesEpoch AI Benchmarking Hub0.73121 on the scale
    4. Furniture AssemblyEpoch AI Benchmarking Hub0.78120 on the scale
    5. Chess PuzzlesEpoch AI Benchmarking Hub0.78119 on the scale
    6. FrontierMath-Tier-4-v2-PrivateEpoch AI Benchmarking Hub0.95116 on the scale
    7. SimpleQA VerifiedEpoch AI Benchmarking Hub0.78115 on the scale
    8. FrontierMath-Tiers-1-3-v2-PrivateEpoch AI Benchmarking Hub0.91109 on the scale
    9. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub194 on the scale
    10. GPQA diamondEpoch AI Benchmarking Hub0.9783 on the scale
  6. 006openai/gpt-6.1-terramax130.85121

    12 columns on 1 board, hardest first are the whole evidence behind 130.85. Each is a door to the column and everything else scored on it.

    1. SpireClimb (Slay the Spire 1, Ascension 20 Heart)Epoch AI Benchmarking Hub0.10139 on the scale
    2. SpireClimbEpoch AI Benchmarking Hub0.22137 on the scale
    3. SpireClimb (Slay the Spire 2, Ascension 10)Epoch AI Benchmarking Hub0.35136 on the scale
    4. EBR-benchEpoch AI Benchmarking Hub0.78123 on the scale
    5. Mystery Game PuzzlesEpoch AI Benchmarking Hub0.74121 on the scale
    6. Furniture AssemblyEpoch AI Benchmarking Hub0.79120 on the scale
    7. MirrorCodeEpoch AI Benchmarking Hub0.77119 on the scale
    8. FrontierMath-Tier-4-v2-PrivateEpoch AI Benchmarking Hub0.93116 on the scale
    9. SimpleQA VerifiedEpoch AI Benchmarking Hub0.57115 on the scale
    10. FrontierMath-Tiers-1-3-v2-PrivateEpoch AI Benchmarking Hub0.91109 on the scale
    11. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub194 on the scale
    12. GPQA diamondEpoch AI Benchmarking Hub0.9483 on the scale
  7. 007openai/gpt-6.1-solmax130.00372

    37 columns on 2 boards, hardest first are the whole evidence behind 130.00. Each is a door to the column and everything else scored on it.

    1. FrontierMath-ErdosEpoch AI Benchmarking Hub0.04153 on the scale
    2. SpireClimb (Slay the Spire 1, Ascension 20 Heart)Epoch AI Benchmarking Hub0.18139 on the scale
    3. SpireClimbEpoch AI Benchmarking Hub0.24137 on the scale
    4. SpireClimb (Slay the Spire 2, Ascension 10)Epoch AI Benchmarking Hub0.29136 on the scale
    5. EBR-benchEpoch AI Benchmarking Hub0.54123 on the scale
    6. typescriptLiveBench40122 on the scale
    7. Mystery Game PuzzlesEpoch AI Benchmarking Hub0.80121 on the scale
    8. Furniture AssemblyEpoch AI Benchmarking Hub0.80120 on the scale
    9. Chess PuzzlesEpoch AI Benchmarking Hub0.68119 on the scale
    10. MirrorCodeEpoch AI Benchmarking Hub0.61119 on the scale
    11. tablejoinLiveBench57.42117 on the scale
    12. FrontierMath-Tier-4-v2-PrivateEpoch AI Benchmarking Hub1116 on the scale
    13. SimpleQA VerifiedEpoch AI Benchmarking Hub0.74115 on the scale
    14. pythonLiveBench60109 on the scale
    15. FrontierMath-Tiers-1-3-v2-PrivateEpoch AI Benchmarking Hub0.94109 on the scale
    16. plot_unscramblingLiveBench84.38106 on the scale
    17. integrals_with_gameLiveBench100104 on the scale
    18. consecutive_eventsLiveBench90.56102 on the scale
    19. zebra_puzzleLiveBench100102 on the scale
    20. javascriptLiveBench63.6499 on the scale
    21. logic_with_navigationLiveBench8696 on the scale
    22. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub194 on the scale
    23. simplifyLiveBench71.9792 on the scale
    24. connectionsLiveBench10091 on the scale
    25. theory_of_mindLiveBench86.5488 on the scale
    26. code_completionLiveBench80.4487 on the scale
    27. paraphraseLiveBench72.5886 on the scale
    28. summarizeLiveBench81.2585 on the scale
    29. GPQA diamondEpoch AI Benchmarking Hub0.9583 on the scale
    30. typosLiveBench8677 on the scale
    31. code_generationLiveBench80.2876 on the scale
    32. story_generationLiveBench70.8274 on the scale
    33. olympiadLiveBench92.2772 on the scale
    34. spatialLiveBench9853 on the scale
    35. AMPS_HardLiveBench9847 on the scale
    36. math_compLiveBench97.0642 on the scale
    37. tablereformatLiveBench10041 on the scale
  8. 008claude-opus-5-5not in the catalogmax128.09372

    37 columns on 2 boards, hardest first are the whole evidence behind 128.09. Each is a door to the column and everything else scored on it.

    1. FrontierMath-ErdosEpoch AI Benchmarking Hub0.03153 on the scale
    2. SpireClimb (Slay the Spire 1, Ascension 20 Heart)Epoch AI Benchmarking Hub0.05139 on the scale
    3. SpireClimbEpoch AI Benchmarking Hub0.06137 on the scale
    4. SpireClimb (Slay the Spire 2, Ascension 10)Epoch AI Benchmarking Hub0.07136 on the scale
    5. EBR-benchEpoch AI Benchmarking Hub0.71123 on the scale
    6. typescriptLiveBench63.33122 on the scale
    7. Mystery Game PuzzlesEpoch AI Benchmarking Hub0.71121 on the scale
    8. Furniture AssemblyEpoch AI Benchmarking Hub0.83120 on the scale
    9. Chess PuzzlesEpoch AI Benchmarking Hub0.67119 on the scale
    10. MirrorCodeEpoch AI Benchmarking Hub0.96119 on the scale
    11. tablejoinLiveBench52.33117 on the scale
    12. FrontierMath-Tier-4-v2-PrivateEpoch AI Benchmarking Hub0.95116 on the scale
    13. SimpleQA VerifiedEpoch AI Benchmarking Hub0.72115 on the scale
    14. pythonLiveBench70109 on the scale
    15. FrontierMath-Tiers-1-3-v2-PrivateEpoch AI Benchmarking Hub0.91109 on the scale
    16. plot_unscramblingLiveBench77.48106 on the scale
    17. integrals_with_gameLiveBench100104 on the scale
    18. consecutive_eventsLiveBench90.56102 on the scale
    19. zebra_puzzleLiveBench100102 on the scale
    20. javascriptLiveBench81.8299 on the scale
    21. logic_with_navigationLiveBench8696 on the scale
    22. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub194 on the scale
    23. simplifyLiveBench58.6792 on the scale
    24. connectionsLiveBench99.3391 on the scale
    25. theory_of_mindLiveBench84.6188 on the scale
    26. code_completionLiveBench86.9687 on the scale
    27. paraphraseLiveBench64.2786 on the scale
    28. summarizeLiveBench69.1085 on the scale
    29. GPQA diamondEpoch AI Benchmarking Hub0.9183 on the scale
    30. typosLiveBench8277 on the scale
    31. code_generationLiveBench91.5576 on the scale
    32. story_generationLiveBench70.9274 on the scale
    33. olympiadLiveBench93.2572 on the scale
    34. spatialLiveBench9853 on the scale
    35. AMPS_HardLiveBench9847 on the scale
    36. math_compLiveBench97.0642 on the scale
    37. tablereformatLiveBench98.0441 on the scale
  9. 009google/gemini-4-hydrogenxhigh125.83121

    12 columns on 1 board, hardest first are the whole evidence behind 125.83. Each is a door to the column and everything else scored on it.

    1. SpireClimb (Slay the Spire 1, Ascension 20 Heart)Epoch AI Benchmarking Hub0.10139 on the scale
    2. SpireClimbEpoch AI Benchmarking Hub0.08137 on the scale
    3. SpireClimb (Slay the Spire 2, Ascension 10)Epoch AI Benchmarking Hub0.05136 on the scale
    4. EBR-benchEpoch AI Benchmarking Hub0.70123 on the scale
    5. Mystery Game PuzzlesEpoch AI Benchmarking Hub0.65121 on the scale
    6. Furniture AssemblyEpoch AI Benchmarking Hub0.57120 on the scale
    7. Chess PuzzlesEpoch AI Benchmarking Hub0.60119 on the scale
    8. FrontierMath-Tier-4-v2-PrivateEpoch AI Benchmarking Hub0.88116 on the scale
    9. SimpleQA VerifiedEpoch AI Benchmarking Hub0.71115 on the scale
    10. FrontierMath-Tiers-1-3-v2-PrivateEpoch AI Benchmarking Hub0.88109 on the scale
    11. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub194 on the scale
    12. GPQA diamondEpoch AI Benchmarking Hub0.9783 on the scale
  10. 010claude-opus-5-5not in the catalogxhigh125.14231

    23 columns on 1 board, hardest first are the whole evidence behind 125.14. Each is a door to the column and everything else scored on it.

    1. typescriptLiveBench53.33122 on the scale
    2. tablejoinLiveBench51117 on the scale
    3. pythonLiveBench70109 on the scale
    4. plot_unscramblingLiveBench77.16106 on the scale
    5. integrals_with_gameLiveBench99104 on the scale
    6. consecutive_eventsLiveBench90.37102 on the scale
    7. zebra_puzzleLiveBench100102 on the scale
    8. javascriptLiveBench72.7399 on the scale
    9. logic_with_navigationLiveBench8096 on the scale
    10. simplifyLiveBench6392 on the scale
    11. connectionsLiveBench99.3391 on the scale
    12. theory_of_mindLiveBench84.6188 on the scale
    13. code_completionLiveBench86.9687 on the scale
    14. paraphraseLiveBench64.6886 on the scale
    15. summarizeLiveBench69.3385 on the scale
    16. typosLiveBench8077 on the scale
    17. code_generationLiveBench91.5576 on the scale
    18. story_generationLiveBench71.1874 on the scale
    19. olympiadLiveBench92.1572 on the scale
    20. spatialLiveBench9853 on the scale
    21. AMPS_HardLiveBench9947 on the scale
    22. math_compLiveBench97.0642 on the scale
    23. tablereformatLiveBench98.0441 on the scale
  11. 011claude-fable-5-1not in the catalogmax125.12362

    36 columns on 2 boards, hardest first are the whole evidence behind 125.12. Each is a door to the column and everything else scored on it.

    1. FrontierMath-ErdosEpoch AI Benchmarking Hub0153 on the scale
    2. SpireClimb (Slay the Spire 1, Ascension 20 Heart)Epoch AI Benchmarking Hub0139 on the scale
    3. SpireClimbEpoch AI Benchmarking Hub0.02137 on the scale
    4. SpireClimb (Slay the Spire 2, Ascension 10)Epoch AI Benchmarking Hub0.04136 on the scale
    5. EBR-benchEpoch AI Benchmarking Hub0.57123 on the scale
    6. typescriptLiveBench60122 on the scale
    7. Mystery Game PuzzlesEpoch AI Benchmarking Hub0.58121 on the scale
    8. Furniture AssemblyEpoch AI Benchmarking Hub0.70120 on the scale
    9. Chess PuzzlesEpoch AI Benchmarking Hub0.48119 on the scale
    10. MirrorCodeEpoch AI Benchmarking Hub0.93119 on the scale
    11. tablejoinLiveBench56.15117 on the scale
    12. FrontierMath-Tier-4-v2-PrivateEpoch AI Benchmarking Hub0.88116 on the scale
    13. SimpleQA VerifiedEpoch AI Benchmarking Hub0.71115 on the scale
    14. pythonLiveBench70109 on the scale
    15. FrontierMath-Tiers-1-3-v2-PrivateEpoch AI Benchmarking Hub0.90109 on the scale
    16. plot_unscramblingLiveBench75.17106 on the scale
    17. integrals_with_gameLiveBench99104 on the scale
    18. consecutive_eventsLiveBench90.56102 on the scale
    19. zebra_puzzleLiveBench100102 on the scale
    20. javascriptLiveBench68.1899 on the scale
    21. logic_with_navigationLiveBench8696 on the scale
    22. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub194 on the scale
    23. simplifyLiveBench70.1792 on the scale
    24. connectionsLiveBench99.3391 on the scale
    25. theory_of_mindLiveBench80.7788 on the scale
    26. code_completionLiveBench82.6187 on the scale
    27. paraphraseLiveBench71.5286 on the scale
    28. summarizeLiveBench72.1785 on the scale
    29. typosLiveBench9477 on the scale
    30. code_generationLiveBench90.1476 on the scale
    31. story_generationLiveBench78.1074 on the scale
    32. olympiadLiveBench92.9772 on the scale
    33. spatialLiveBench10053 on the scale
    34. AMPS_HardLiveBench9947 on the scale
    35. math_compLiveBench97.0642 on the scale
    36. tablereformatLiveBench94.1241 on the scale
  12. 012google/gemini-4-argonhigh124.90111

    11 columns on 1 board, hardest first are the whole evidence behind 124.90. Each is a door to the column and everything else scored on it.

    1. FrontierMath-ErdosEpoch AI Benchmarking Hub0.01153 on the scale
    2. EBR-benchEpoch AI Benchmarking Hub0.65123 on the scale
    3. Mystery Game PuzzlesEpoch AI Benchmarking Hub0.64121 on the scale
    4. Furniture AssemblyEpoch AI Benchmarking Hub0.72120 on the scale
    5. Chess PuzzlesEpoch AI Benchmarking Hub0.59119 on the scale
    6. MirrorCodeEpoch AI Benchmarking Hub0.59119 on the scale
    7. FrontierMath-Tier-4-v2-PrivateEpoch AI Benchmarking Hub0.78116 on the scale
    8. SimpleQA VerifiedEpoch AI Benchmarking Hub0.76115 on the scale
    9. FrontierMath-Tiers-1-3-v2-PrivateEpoch AI Benchmarking Hub0.86109 on the scale
    10. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub194 on the scale
    11. GPQA diamondEpoch AI Benchmarking Hub0.9683 on the scale
  13. 013openai/gpt-6.1-solxhigh124.64231

    23 columns on 1 board, hardest first are the whole evidence behind 124.64. Each is a door to the column and everything else scored on it.

    1. typescriptLiveBench46.67122 on the scale
    2. tablejoinLiveBench55.25117 on the scale
    3. pythonLiveBench60109 on the scale
    4. plot_unscramblingLiveBench81.94106 on the scale
    5. integrals_with_gameLiveBench99104 on the scale
    6. consecutive_eventsLiveBench91.29102 on the scale
    7. zebra_puzzleLiveBench100102 on the scale
    8. javascriptLiveBench63.6499 on the scale
    9. logic_with_navigationLiveBench8296 on the scale
    10. simplifyLiveBench68.1792 on the scale
    11. connectionsLiveBench10091 on the scale
    12. theory_of_mindLiveBench86.5488 on the scale
    13. code_completionLiveBench82.6187 on the scale
    14. paraphraseLiveBench71.0386 on the scale
    15. summarizeLiveBench75.5385 on the scale
    16. typosLiveBench8477 on the scale
    17. code_generationLiveBench78.8776 on the scale
    18. story_generationLiveBench70.5774 on the scale
    19. olympiadLiveBench91.8672 on the scale
    20. spatialLiveBench9853 on the scale
    21. AMPS_HardLiveBench9847 on the scale
    22. math_compLiveBench97.0642 on the scale
    23. tablereformatLiveBench10041 on the scale
  14. 014openai/gpt-6-solmax124.00372

    37 columns on 2 boards, hardest first are the whole evidence behind 124.00. Each is a door to the column and everything else scored on it.

    1. FrontierMath-ErdosEpoch AI Benchmarking Hub0.01153 on the scale
    2. SpireClimb (Slay the Spire 1, Ascension 20 Heart)Epoch AI Benchmarking Hub0.05139 on the scale
    3. SpireClimbEpoch AI Benchmarking Hub0.09137 on the scale
    4. SpireClimb (Slay the Spire 2, Ascension 10)Epoch AI Benchmarking Hub0.13136 on the scale
    5. EBR-benchEpoch AI Benchmarking Hub0.53123 on the scale
    6. typescriptLiveBench40122 on the scale
    7. Mystery Game PuzzlesEpoch AI Benchmarking Hub0.56121 on the scale
    8. Furniture AssemblyEpoch AI Benchmarking Hub0.58120 on the scale
    9. Chess PuzzlesEpoch AI Benchmarking Hub0.56119 on the scale
    10. MirrorCodeEpoch AI Benchmarking Hub0.49119 on the scale
    11. tablejoinLiveBench54.02117 on the scale
    12. FrontierMath-Tier-4-v2-PrivateEpoch AI Benchmarking Hub0.90116 on the scale
    13. SimpleQA VerifiedEpoch AI Benchmarking Hub0.61115 on the scale
    14. pythonLiveBench55109 on the scale
    15. FrontierMath-Tiers-1-3-v2-PrivateEpoch AI Benchmarking Hub0.90109 on the scale
    16. plot_unscramblingLiveBench77.90106 on the scale
    17. integrals_with_gameLiveBench99104 on the scale
    18. consecutive_eventsLiveBench89.55102 on the scale
    19. zebra_puzzleLiveBench100102 on the scale
    20. javascriptLiveBench63.6499 on the scale
    21. logic_with_navigationLiveBench7496 on the scale
    22. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub194 on the scale
    23. simplifyLiveBench69.2892 on the scale
    24. connectionsLiveBench10091 on the scale
    25. theory_of_mindLiveBench84.6188 on the scale
    26. code_completionLiveBench80.4487 on the scale
    27. paraphraseLiveBench70.0886 on the scale
    28. summarizeLiveBench6885 on the scale
    29. GPQA diamondEpoch AI Benchmarking Hub0.9483 on the scale
    30. typosLiveBench7877 on the scale
    31. code_generationLiveBench83.1076 on the scale
    32. story_generationLiveBench66.9374 on the scale
    33. olympiadLiveBench91.3672 on the scale
    34. spatialLiveBench9653 on the scale
    35. AMPS_HardLiveBench9847 on the scale
    36. math_compLiveBench97.0642 on the scale
    37. tablereformatLiveBench10041 on the scale
  15. 015openai/gpt-5.6-solmax123.35332

    33 columns on 2 boards, hardest first are the whole evidence behind 123.35. Each is a door to the column and everything else scored on it.

    1. FrontierMath-ErdosEpoch AI Benchmarking Hub0153 on the scale
    2. EBR-benchEpoch AI Benchmarking Hub0.45123 on the scale
    3. typescriptLiveBench50122 on the scale
    4. Mystery Game PuzzlesEpoch AI Benchmarking Hub0.58121 on the scale
    5. Furniture AssemblyEpoch AI Benchmarking Hub0.57120 on the scale
    6. Chess PuzzlesEpoch AI Benchmarking Hub0.59119 on the scale
    7. tablejoinLiveBench49.31117 on the scale
    8. FrontierMath-Tier-4-v2-PrivateEpoch AI Benchmarking Hub0.83116 on the scale
    9. SimpleQA VerifiedEpoch AI Benchmarking Hub0.70115 on the scale
    10. pythonLiveBench55109 on the scale
    11. FrontierMath-Tiers-1-3-v2-PrivateEpoch AI Benchmarking Hub0.89109 on the scale
    12. plot_unscramblingLiveBench79.05106 on the scale
    13. integrals_with_gameLiveBench100104 on the scale
    14. consecutive_eventsLiveBench90.21102 on the scale
    15. zebra_puzzleLiveBench100102 on the scale
    16. javascriptLiveBench63.6499 on the scale
    17. logic_with_navigationLiveBench8296 on the scale
    18. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub194 on the scale
    19. simplifyLiveBench70.5292 on the scale
    20. connectionsLiveBench10091 on the scale
    21. theory_of_mindLiveBench84.6188 on the scale
    22. code_completionLiveBench84.7887 on the scale
    23. paraphraseLiveBench71.5286 on the scale
    24. summarizeLiveBench69.4385 on the scale
    25. GPQA diamondEpoch AI Benchmarking Hub0.9383 on the scale
    26. typosLiveBench8477 on the scale
    27. code_generationLiveBench83.1076 on the scale
    28. story_generationLiveBench75.9274 on the scale
    29. olympiadLiveBench91.6972 on the scale
    30. spatialLiveBench10053 on the scale
    31. AMPS_HardLiveBench9847 on the scale
    32. math_compLiveBench95.1042 on the scale
    33. tablereformatLiveBench10041 on the scale
  16. 016openai/gpt-5.5-proxhigh122.6631

    3 columns on 1 board, hardest first are the whole evidence behind 122.66. Each is a door to the column and everything else scored on it.

    1. Chess PuzzlesEpoch AI Benchmarking Hub0.62119 on the scale
    2. FrontierMath-Tier-4-v2-PrivateEpoch AI Benchmarking Hub0.78116 on the scale
    3. FrontierMath-Tiers-1-3-v2-PrivateEpoch AI Benchmarking Hub0.88109 on the scale
  17. 017anthropic/claude-fable-5max122.58352

    35 columns on 2 boards, hardest first are the whole evidence behind 122.58. Each is a door to the column and everything else scored on it.

    1. FrontierMath-ErdosEpoch AI Benchmarking Hub0153 on the scale
    2. EBR-benchEpoch AI Benchmarking Hub0.40123 on the scale
    3. typescriptLiveBench53.33122 on the scale
    4. Mystery Game PuzzlesEpoch AI Benchmarking Hub0.52121 on the scale
    5. Furniture AssemblyEpoch AI Benchmarking Hub0.36120 on the scale
    6. Chess PuzzlesEpoch AI Benchmarking Hub0.47119 on the scale
    7. MirrorCodeEpoch AI Benchmarking Hub0.70119 on the scale
    8. tablejoinLiveBench56.13117 on the scale
    9. FrontierMath-Tier-4-2025-07-01-PublicEpoch AI Benchmarking Hub1116 on the scale
    10. FrontierMath-Tier-4-v2-PrivateEpoch AI Benchmarking Hub0.90116 on the scale
    11. pythonLiveBench65109 on the scale
    12. FrontierMath-Tiers-1-3-v2-PrivateEpoch AI Benchmarking Hub0.87109 on the scale
    13. FrontierMath-2025-02-28-PublicEpoch AI Benchmarking Hub1106 on the scale
    14. plot_unscramblingLiveBench78.72106 on the scale
    15. integrals_with_gameLiveBench97104 on the scale
    16. consecutive_eventsLiveBench91.36102 on the scale
    17. zebra_puzzleLiveBench100102 on the scale
    18. javascriptLiveBench68.1899 on the scale
    19. logic_with_navigationLiveBench7896 on the scale
    20. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub1.0094 on the scale
    21. simplifyLiveBench72.0392 on the scale
    22. connectionsLiveBench99.3391 on the scale
    23. theory_of_mindLiveBench84.6188 on the scale
    24. code_completionLiveBench80.4487 on the scale
    25. paraphraseLiveBench77.6586 on the scale
    26. summarizeLiveBench81.7085 on the scale
    27. GPQA diamondEpoch AI Benchmarking Hub0.8683 on the scale
    28. typosLiveBench9477 on the scale
    29. code_generationLiveBench91.5576 on the scale
    30. story_generationLiveBench71.7074 on the scale
    31. olympiadLiveBench92.8472 on the scale
    32. spatialLiveBench9653 on the scale
    33. AMPS_HardLiveBench9947 on the scale
    34. math_compLiveBench95.1042 on the scale
    35. tablereformatLiveBench94.1241 on the scale
  18. 018anthropic/claude-opus-5max122.24342

    34 columns on 2 boards, hardest first are the whole evidence behind 122.24. Each is a door to the column and everything else scored on it.

    1. FrontierMath-ErdosEpoch AI Benchmarking Hub0153 on the scale
    2. EBR-benchEpoch AI Benchmarking Hub0.46123 on the scale
    3. typescriptLiveBench43.33122 on the scale
    4. Mystery Game PuzzlesEpoch AI Benchmarking Hub0.59121 on the scale
    5. Furniture AssemblyEpoch AI Benchmarking Hub0.61120 on the scale
    6. Chess PuzzlesEpoch AI Benchmarking Hub0.43119 on the scale
    7. MirrorCodeEpoch AI Benchmarking Hub0.88119 on the scale
    8. tablejoinLiveBench51.96117 on the scale
    9. FrontierMath-Tier-4-v2-PrivateEpoch AI Benchmarking Hub0.73116 on the scale
    10. SimpleQA VerifiedEpoch AI Benchmarking Hub0.60115 on the scale
    11. pythonLiveBench75109 on the scale
    12. FrontierMath-Tiers-1-3-v2-PrivateEpoch AI Benchmarking Hub0.86109 on the scale
    13. plot_unscramblingLiveBench74.73106 on the scale
    14. integrals_with_gameLiveBench97104 on the scale
    15. consecutive_eventsLiveBench77.57102 on the scale
    16. zebra_puzzleLiveBench100102 on the scale
    17. javascriptLiveBench77.2799 on the scale
    18. logic_with_navigationLiveBench8696 on the scale
    19. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.9994 on the scale
    20. simplifyLiveBench61.5892 on the scale
    21. connectionsLiveBench99.3391 on the scale
    22. theory_of_mindLiveBench78.8588 on the scale
    23. code_completionLiveBench82.6187 on the scale
    24. paraphraseLiveBench65.7386 on the scale
    25. summarizeLiveBench66.4385 on the scale
    26. GPQA diamondEpoch AI Benchmarking Hub0.9483 on the scale
    27. typosLiveBench9277 on the scale
    28. code_generationLiveBench80.2876 on the scale
    29. story_generationLiveBench61.3274 on the scale
    30. olympiadLiveBench92.8072 on the scale
    31. spatialLiveBench10053 on the scale
    32. AMPS_HardLiveBench99.0147 on the scale
    33. math_compLiveBench94.1242 on the scale
    34. tablereformatLiveBench94.1241 on the scale
  19. 019claude-sonnet-5-5not in the catalogmax122.13362

    36 columns on 2 boards, hardest first are the whole evidence behind 122.13. Each is a door to the column and everything else scored on it.

    1. FrontierMath-ErdosEpoch AI Benchmarking Hub0.03153 on the scale
    2. SpireClimb (Slay the Spire 1, Ascension 20 Heart)Epoch AI Benchmarking Hub0139 on the scale
    3. SpireClimbEpoch AI Benchmarking Hub0.01137 on the scale
    4. SpireClimb (Slay the Spire 2, Ascension 10)Epoch AI Benchmarking Hub0.03136 on the scale
    5. typescriptLiveBench56.67122 on the scale
    6. Mystery Game PuzzlesEpoch AI Benchmarking Hub0.65121 on the scale
    7. Furniture AssemblyEpoch AI Benchmarking Hub0.75120 on the scale
    8. Chess PuzzlesEpoch AI Benchmarking Hub0.59119 on the scale
    9. MirrorCodeEpoch AI Benchmarking Hub0.98119 on the scale
    10. tablejoinLiveBench39.81117 on the scale
    11. FrontierMath-Tier-4-v2-PrivateEpoch AI Benchmarking Hub0.80116 on the scale
    12. SimpleQA VerifiedEpoch AI Benchmarking Hub0.47115 on the scale
    13. pythonLiveBench35109 on the scale
    14. FrontierMath-Tiers-1-3-v2-PrivateEpoch AI Benchmarking Hub0.89109 on the scale
    15. plot_unscramblingLiveBench48.62106 on the scale
    16. integrals_with_gameLiveBench97104 on the scale
    17. consecutive_eventsLiveBench40.62102 on the scale
    18. zebra_puzzleLiveBench100102 on the scale
    19. javascriptLiveBench77.2799 on the scale
    20. logic_with_navigationLiveBench8296 on the scale
    21. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub194 on the scale
    22. simplifyLiveBench50.8592 on the scale
    23. connectionsLiveBench99.3391 on the scale
    24. theory_of_mindLiveBench86.5488 on the scale
    25. code_completionLiveBench86.9687 on the scale
    26. paraphraseLiveBench48.2286 on the scale
    27. summarizeLiveBench58.1785 on the scale
    28. GPQA diamondEpoch AI Benchmarking Hub0.9683 on the scale
    29. typosLiveBench8677 on the scale
    30. code_generationLiveBench95.7876 on the scale
    31. story_generationLiveBench69.9274 on the scale
    32. olympiadLiveBench92.4772 on the scale
    33. spatialLiveBench9853 on the scale
    34. AMPS_HardLiveBench9847 on the scale
    35. math_compLiveBench97.0642 on the scale
    36. tablereformatLiveBench98.0441 on the scale
  20. 020muse-wonder-1.0not in the catalogmax120.86302

    30 columns on 2 boards, hardest first are the whole evidence behind 120.86. Each is a door to the column and everything else scored on it.

    1. EBR-benchEpoch AI Benchmarking Hub0.31123 on the scale
    2. typescriptLiveBench60122 on the scale
    3. Mystery Game PuzzlesEpoch AI Benchmarking Hub0.51121 on the scale
    4. Furniture AssemblyEpoch AI Benchmarking Hub0.54120 on the scale
    5. MirrorCodeEpoch AI Benchmarking Hub0.46119 on the scale
    6. tablejoinLiveBench46.33117 on the scale
    7. FrontierMath-Tier-4-v2-PrivateEpoch AI Benchmarking Hub0.71116 on the scale
    8. pythonLiveBench60109 on the scale
    9. FrontierMath-Tiers-1-3-v2-PrivateEpoch AI Benchmarking Hub0.82109 on the scale
    10. plot_unscramblingLiveBench74.80106 on the scale
    11. integrals_with_gameLiveBench98104 on the scale
    12. consecutive_eventsLiveBench98.53102 on the scale
    13. zebra_puzzleLiveBench100102 on the scale
    14. javascriptLiveBench68.1899 on the scale
    15. logic_with_navigationLiveBench8096 on the scale
    16. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.9994 on the scale
    17. simplifyLiveBench67.0592 on the scale
    18. connectionsLiveBench9691 on the scale
    19. theory_of_mindLiveBench86.5488 on the scale
    20. code_completionLiveBench78.2687 on the scale
    21. paraphraseLiveBench74.0786 on the scale
    22. summarizeLiveBench76.8385 on the scale
    23. typosLiveBench7877 on the scale
    24. code_generationLiveBench83.1076 on the scale
    25. story_generationLiveBench74.1774 on the scale
    26. olympiadLiveBench91.8272 on the scale
    27. spatialLiveBench9653 on the scale
    28. AMPS_HardLiveBench9947 on the scale
    29. math_compLiveBench97.0642 on the scale
    30. tablereformatLiveBench10041 on the scale
  21. 021openai/gpt-5.5xhigh120.29322

    32 columns on 2 boards, hardest first are the whole evidence behind 120.29. Each is a door to the column and everything else scored on it.

    1. FrontierMath-ErdosEpoch AI Benchmarking Hub0153 on the scale
    2. EBR-benchEpoch AI Benchmarking Hub0.34123 on the scale
    3. typescriptLiveBench43.33122 on the scale
    4. Mystery Game PuzzlesEpoch AI Benchmarking Hub0.56121 on the scale
    5. Furniture AssemblyEpoch AI Benchmarking Hub0.44120 on the scale
    6. Chess PuzzlesEpoch AI Benchmarking Hub0.63119 on the scale
    7. MirrorCodeEpoch AI Benchmarking Hub0.23119 on the scale
    8. tablejoinLiveBench55.90117 on the scale
    9. FrontierMath-Tier-4-v2-PrivateEpoch AI Benchmarking Hub0.72116 on the scale
    10. SimpleQA VerifiedEpoch AI Benchmarking Hub0.63115 on the scale
    11. pythonLiveBench55109 on the scale
    12. FrontierMath-Tiers-1-3-v2-PrivateEpoch AI Benchmarking Hub0.85109 on the scale
    13. plot_unscramblingLiveBench74.09106 on the scale
    14. integrals_with_gameLiveBench99104 on the scale
    15. consecutive_eventsLiveBench88.82102 on the scale
    16. zebra_puzzleLiveBench100102 on the scale
    17. javascriptLiveBench63.6499 on the scale
    18. logic_with_navigationLiveBench7696 on the scale
    19. simplifyLiveBench66.3292 on the scale
    20. connectionsLiveBench10091 on the scale
    21. theory_of_mindLiveBench84.6188 on the scale
    22. code_completionLiveBench82.6187 on the scale
    23. paraphraseLiveBench71.7386 on the scale
    24. summarizeLiveBench72.3285 on the scale
    25. typosLiveBench8877 on the scale
    26. code_generationLiveBench81.6976 on the scale
    27. story_generationLiveBench72.5574 on the scale
    28. olympiadLiveBench91.3572 on the scale
    29. spatialLiveBench9853 on the scale
    30. AMPS_HardLiveBench9747 on the scale
    31. math_compLiveBench96.0842 on the scale
    32. tablereformatLiveBench10041 on the scale
  22. 022claude-sonnet-5-5not in the catalogxhigh119.88231

    23 columns on 1 board, hardest first are the whole evidence behind 119.88. Each is a door to the column and everything else scored on it.

    1. typescriptLiveBench46.67122 on the scale
    2. tablejoinLiveBench46.88117 on the scale
    3. pythonLiveBench35109 on the scale
    4. plot_unscramblingLiveBench67.79106 on the scale
    5. integrals_with_gameLiveBench100104 on the scale
    6. consecutive_eventsLiveBench90.94102 on the scale
    7. zebra_puzzleLiveBench100102 on the scale
    8. javascriptLiveBench36.3699 on the scale
    9. logic_with_navigationLiveBench8096 on the scale
    10. simplifyLiveBench72.3792 on the scale
    11. connectionsLiveBench98.5091 on the scale
    12. theory_of_mindLiveBench69.2388 on the scale
    13. code_completionLiveBench84.7887 on the scale
    14. paraphraseLiveBench62.2886 on the scale
    15. summarizeLiveBench70.3385 on the scale
    16. typosLiveBench8477 on the scale
    17. code_generationLiveBench92.9676 on the scale
    18. story_generationLiveBench77.0874 on the scale
    19. olympiadLiveBench91.7272 on the scale
    20. spatialLiveBench9853 on the scale
    21. AMPS_HardLiveBench9847 on the scale
    22. math_compLiveBench97.0642 on the scale
    23. tablereformatLiveBench98.0441 on the scale
  23. 023anthropic/claude-fable-5high119.2951

    5 columns on 1 board, hardest first are the whole evidence behind 119.29. Each is a door to the column and everything else scored on it.

    1. OEIS Open LiteEpoch AI Benchmarking Hub0.44122 on the scale
    2. Chess PuzzlesEpoch AI Benchmarking Hub0.45119 on the scale
    3. MirrorCodeEpoch AI Benchmarking Hub0.64119 on the scale
    4. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub194 on the scale
    5. GPQA diamondEpoch AI Benchmarking Hub0.8383 on the scale
  24. 024openai/gpt-5.6-terramax119.24322

    32 columns on 2 boards, hardest first are the whole evidence behind 119.24. Each is a door to the column and everything else scored on it.

    1. typescriptLiveBench46.67122 on the scale
    2. Mystery Game PuzzlesEpoch AI Benchmarking Hub0.35121 on the scale
    3. Furniture AssemblyEpoch AI Benchmarking Hub0.54120 on the scale
    4. Chess PuzzlesEpoch AI Benchmarking Hub0.47119 on the scale
    5. MirrorCodeEpoch AI Benchmarking Hub0.41119 on the scale
    6. tablejoinLiveBench50.25117 on the scale
    7. FrontierMath-Tier-4-v2-PrivateEpoch AI Benchmarking Hub0.71116 on the scale
    8. SimpleQA VerifiedEpoch AI Benchmarking Hub0.43115 on the scale
    9. pythonLiveBench50109 on the scale
    10. FrontierMath-Tiers-1-3-v2-PrivateEpoch AI Benchmarking Hub0.86109 on the scale
    11. plot_unscramblingLiveBench69.68106 on the scale
    12. integrals_with_gameLiveBench95104 on the scale
    13. consecutive_eventsLiveBench87.67102 on the scale
    14. zebra_puzzleLiveBench100102 on the scale
    15. javascriptLiveBench68.1899 on the scale
    16. logic_with_navigationLiveBench7696 on the scale
    17. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub1.0094 on the scale
    18. simplifyLiveBench61.4392 on the scale
    19. connectionsLiveBench9391 on the scale
    20. theory_of_mindLiveBench86.5488 on the scale
    21. code_completionLiveBench80.4487 on the scale
    22. paraphraseLiveBench57.0386 on the scale
    23. summarizeLiveBench73.1785 on the scale
    24. GPQA diamondEpoch AI Benchmarking Hub0.9383 on the scale
    25. typosLiveBench8677 on the scale
    26. code_generationLiveBench76.0676 on the scale
    27. story_generationLiveBench66.8374 on the scale
    28. olympiadLiveBench91.5372 on the scale
    29. spatialLiveBench10053 on the scale
    30. AMPS_HardLiveBench9847 on the scale
    31. math_compLiveBench95.1042 on the scale
    32. tablereformatLiveBench10041 on the scale
  25. 025openai/gpt-5.4xhigh119.02231

    23 columns on 1 board, hardest first are the whole evidence behind 119.02. Each is a door to the column and everything else scored on it.

    1. typescriptLiveBench43.33122 on the scale
    2. tablejoinLiveBench51.75117 on the scale
    3. pythonLiveBench50109 on the scale
    4. plot_unscramblingLiveBench65.90106 on the scale
    5. integrals_with_gameLiveBench93104 on the scale
    6. consecutive_eventsLiveBench86.19102 on the scale
    7. zebra_puzzleLiveBench98102 on the scale
    8. javascriptLiveBench68.1899 on the scale
    9. logic_with_navigationLiveBench6896 on the scale
    10. simplifyLiveBench7092 on the scale
    11. connectionsLiveBench10091 on the scale
    12. theory_of_mindLiveBench88.4688 on the scale
    13. code_completionLiveBench80.4487 on the scale
    14. paraphraseLiveBench63.4386 on the scale
    15. summarizeLiveBench68.4285 on the scale
    16. typosLiveBench8277 on the scale
    17. code_generationLiveBench74.6576 on the scale
    18. story_generationLiveBench79.0274 on the scale
    19. olympiadLiveBench91.4772 on the scale
    20. spatialLiveBench9853 on the scale
    21. AMPS_HardLiveBench9847 on the scale
    22. math_compLiveBench94.1242 on the scale
    23. tablereformatLiveBench10041 on the scale
  26. 026kimi-k3.1-pro-togethernot in the catalogmax118.88131

    13 columns on 1 board, hardest first are the whole evidence behind 118.88. Each is a door to the column and everything else scored on it.

    1. SpireClimb (Slay the Spire 1, Ascension 20 Heart)Epoch AI Benchmarking Hub0139 on the scale
    2. SpireClimbEpoch AI Benchmarking Hub0137 on the scale
    3. SpireClimb (Slay the Spire 2, Ascension 10)Epoch AI Benchmarking Hub0136 on the scale
    4. EBR-benchEpoch AI Benchmarking Hub0.37123 on the scale
    5. Mystery Game PuzzlesEpoch AI Benchmarking Hub0.42121 on the scale
    6. Furniture AssemblyEpoch AI Benchmarking Hub0.56120 on the scale
    7. Chess PuzzlesEpoch AI Benchmarking Hub0.45119 on the scale
    8. MirrorCodeEpoch AI Benchmarking Hub0.43119 on the scale
    9. FrontierMath-Tier-4-v2-PrivateEpoch AI Benchmarking Hub0.66116 on the scale
    10. SimpleQA VerifiedEpoch AI Benchmarking Hub0.62115 on the scale
    11. FrontierMath-Tiers-1-3-v2-PrivateEpoch AI Benchmarking Hub0.78109 on the scale
    12. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub194 on the scale
    13. GPQA diamondEpoch AI Benchmarking Hub0.9483 on the scale
  27. 027deepseek/deepseek-v4-pro-0813unstated118.60231

    23 columns on 1 board, hardest first are the whole evidence behind 118.60. Each is a door to the column and everything else scored on it.

    1. typescriptLiveBench46.67122 on the scale
    2. tablejoinLiveBench49.46117 on the scale
    3. pythonLiveBench50109 on the scale
    4. plot_unscramblingLiveBench64.22106 on the scale
    5. integrals_with_gameLiveBench94104 on the scale
    6. consecutive_eventsLiveBench90.23102 on the scale
    7. zebra_puzzleLiveBench96.75102 on the scale
    8. javascriptLiveBench68.1899 on the scale
    9. logic_with_navigationLiveBench6696 on the scale
    10. simplifyLiveBench61.5792 on the scale
    11. connectionsLiveBench10091 on the scale
    12. theory_of_mindLiveBench84.6188 on the scale
    13. code_completionLiveBench78.2687 on the scale
    14. paraphraseLiveBench68.6386 on the scale
    15. summarizeLiveBench65.6785 on the scale
    16. typosLiveBench8277 on the scale
    17. code_generationLiveBench76.0676 on the scale
    18. story_generationLiveBench74.9374 on the scale
    19. olympiadLiveBench91.2972 on the scale
    20. spatialLiveBench9653 on the scale
    21. AMPS_HardLiveBench9847 on the scale
    22. math_compLiveBench97.0642 on the scale
    23. tablereformatLiveBench98.0441 on the scale
  28. 028qwen3.8-maxnot in the catalogunstated118.08231

    23 columns on 1 board, hardest first are the whole evidence behind 118.08. Each is a door to the column and everything else scored on it.

    1. typescriptLiveBench56.67122 on the scale
    2. tablejoinLiveBench50.06117 on the scale
    3. pythonLiveBench60109 on the scale
    4. plot_unscramblingLiveBench58.56106 on the scale
    5. integrals_with_gameLiveBench81104 on the scale
    6. consecutive_eventsLiveBench87.14102 on the scale
    7. zebra_puzzleLiveBench100102 on the scale
    8. javascriptLiveBench77.2799 on the scale
    9. logic_with_navigationLiveBench7496 on the scale
    10. simplifyLiveBench67.3592 on the scale
    11. connectionsLiveBench94.5091 on the scale
    12. theory_of_mindLiveBench78.8588 on the scale
    13. code_completionLiveBench73.9187 on the scale
    14. paraphraseLiveBench73.3286 on the scale
    15. summarizeLiveBench79.1585 on the scale
    16. typosLiveBench8677 on the scale
    17. code_generationLiveBench71.8376 on the scale
    18. story_generationLiveBench76.5274 on the scale
    19. olympiadLiveBench91.1572 on the scale
    20. spatialLiveBench10053 on the scale
    21. AMPS_HardLiveBench9847 on the scale
    22. math_compLiveBench95.1042 on the scale
    23. tablereformatLiveBench98.0441 on the scale
  29. 029gpt-5.4-pro-2026-03-05not in the catalogxhigh117.9261

    6 columns on 1 board, hardest first are the whole evidence behind 117.92. Each is a door to the column and everything else scored on it.

    1. Chess PuzzlesEpoch AI Benchmarking Hub0.59119 on the scale
    2. FrontierMath-Tier-4-v2-PrivateEpoch AI Benchmarking Hub0.59116 on the scale
    3. SimpleQA VerifiedEpoch AI Benchmarking Hub0.46115 on the scale
    4. FrontierMath-2025-02-28-PrivateEpoch AI Benchmarking Hub0.50115 on the scale
    5. FrontierMath-Tiers-1-3-v2-PrivateEpoch AI Benchmarking Hub0.82109 on the scale
    6. GPQA diamondEpoch AI Benchmarking Hub0.9583 on the scale
  30. 030x-ai/grok-4.6unstated117.62231

    23 columns on 1 board, hardest first are the whole evidence behind 117.62. Each is a door to the column and everything else scored on it.

    1. typescriptLiveBench43.33122 on the scale
    2. tablejoinLiveBench43.42117 on the scale
    3. pythonLiveBench55109 on the scale
    4. plot_unscramblingLiveBench67.09106 on the scale
    5. integrals_with_gameLiveBench85104 on the scale
    6. consecutive_eventsLiveBench78.15102 on the scale
    7. zebra_puzzleLiveBench95.50102 on the scale
    8. javascriptLiveBench72.7399 on the scale
    9. logic_with_navigationLiveBench8296 on the scale
    10. simplifyLiveBench69.3392 on the scale
    11. connectionsLiveBench10091 on the scale
    12. theory_of_mindLiveBench86.5488 on the scale
    13. code_completionLiveBench76.0987 on the scale
    14. paraphraseLiveBench71.7886 on the scale
    15. summarizeLiveBench68.0885 on the scale
    16. typosLiveBench8477 on the scale
    17. code_generationLiveBench77.4776 on the scale
    18. story_generationLiveBench78.2774 on the scale
    19. olympiadLiveBench91.2172 on the scale
    20. spatialLiveBench9853 on the scale
    21. AMPS_HardLiveBench9747 on the scale
    22. math_compLiveBench97.0642 on the scale
    23. tablereformatLiveBench10041 on the scale
  31. 031gpt-5.5-pro-pre-releasenot in the catalogxhigh117.3841

    4 columns on 1 board, hardest first are the whole evidence behind 117.38. Each is a door to the column and everything else scored on it.

    1. FrontierMath-Tier-4-2025-07-01-PrivateEpoch AI Benchmarking Hub0.40120 on the scale
    2. FrontierMath-2025-02-28-PrivateEpoch AI Benchmarking Hub0.51115 on the scale
    3. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub194 on the scale
    4. GPQA diamondEpoch AI Benchmarking Hub0.9483 on the scale
  32. 032meta/muse-spark-1.2xhigh117.04252

    25 columns on 2 boards, hardest first are the whole evidence behind 117.04. Each is a door to the column and everything else scored on it.

    1. typescriptLiveBench50122 on the scale
    2. Chess PuzzlesEpoch AI Benchmarking Hub0.27119 on the scale
    3. tablejoinLiveBench46.83117 on the scale
    4. SimpleQA VerifiedEpoch AI Benchmarking Hub0.60115 on the scale
    5. pythonLiveBench50109 on the scale
    6. plot_unscramblingLiveBench61.72106 on the scale
    7. integrals_with_gameLiveBench91104 on the scale
    8. consecutive_eventsLiveBench82.55102 on the scale
    9. zebra_puzzleLiveBench95.25102 on the scale
    10. javascriptLiveBench72.7399 on the scale
    11. logic_with_navigationLiveBench8896 on the scale
    12. simplifyLiveBench68.7392 on the scale
    13. connectionsLiveBench10091 on the scale
    14. theory_of_mindLiveBench80.7788 on the scale
    15. code_completionLiveBench80.4487 on the scale
    16. paraphraseLiveBench74.3086 on the scale
    17. summarizeLiveBench80.6285 on the scale
    18. typosLiveBench7477 on the scale
    19. code_generationLiveBench74.6576 on the scale
    20. story_generationLiveBench73.6574 on the scale
    21. olympiadLiveBench87.7572 on the scale
    22. spatialLiveBench9653 on the scale
    23. AMPS_HardLiveBench8947 on the scale
    24. math_compLiveBench97.0642 on the scale
    25. tablereformatLiveBench10041 on the scale
  33. 033claude-opus-4-8not in the catalogmax116.89352

    35 columns on 2 boards, hardest first are the whole evidence behind 116.89. Each is a door to the column and everything else scored on it.

    1. EBR-benchEpoch AI Benchmarking Hub0.29123 on the scale
    2. typescriptLiveBench33.33122 on the scale
    3. Mystery Game PuzzlesEpoch AI Benchmarking Hub0.36121 on the scale
    4. FrontierMath-Tier-4-2025-07-01-PrivateEpoch AI Benchmarking Hub0.31120 on the scale
    5. Furniture AssemblyEpoch AI Benchmarking Hub0.42120 on the scale
    6. Chess PuzzlesEpoch AI Benchmarking Hub0.52119 on the scale
    7. MirrorCodeEpoch AI Benchmarking Hub0.66119 on the scale
    8. tablejoinLiveBench51.08117 on the scale
    9. FrontierMath-Tier-4-v2-PrivateEpoch AI Benchmarking Hub0.56116 on the scale
    10. SimpleQA VerifiedEpoch AI Benchmarking Hub0.53115 on the scale
    11. FrontierMath-2025-02-28-PrivateEpoch AI Benchmarking Hub0.47115 on the scale
    12. pythonLiveBench50109 on the scale
    13. FrontierMath-Tiers-1-3-v2-PrivateEpoch AI Benchmarking Hub0.80109 on the scale
    14. plot_unscramblingLiveBench61.65106 on the scale
    15. integrals_with_gameLiveBench89104 on the scale
    16. consecutive_eventsLiveBench52.91102 on the scale
    17. zebra_puzzleLiveBench100102 on the scale
    18. javascriptLiveBench68.1899 on the scale
    19. logic_with_navigationLiveBench7896 on the scale
    20. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.9894 on the scale
    21. simplifyLiveBench6292 on the scale
    22. connectionsLiveBench99.3391 on the scale
    23. theory_of_mindLiveBench80.7788 on the scale
    24. code_completionLiveBench84.7887 on the scale
    25. paraphraseLiveBench67.8786 on the scale
    26. summarizeLiveBench77.6785 on the scale
    27. GPQA diamondEpoch AI Benchmarking Hub0.9183 on the scale
    28. typosLiveBench7877 on the scale
    29. code_generationLiveBench78.8776 on the scale
    30. story_generationLiveBench80.6074 on the scale
    31. olympiadLiveBench92.2372 on the scale
    32. spatialLiveBench9853 on the scale
    33. AMPS_HardLiveBench9847 on the scale
    34. math_compLiveBench98.0442 on the scale
    35. tablereformatLiveBench94.1241 on the scale
  34. 034gpt-5.5-pre-releasenot in the catalogxhigh116.8651

    5 columns on 1 board, hardest first are the whole evidence behind 116.86. Each is a door to the column and everything else scored on it.

    1. FrontierMath-Tier-4-2025-07-01-PrivateEpoch AI Benchmarking Hub0.35120 on the scale
    2. FrontierMath-2025-02-28-PrivateEpoch AI Benchmarking Hub0.52115 on the scale
    3. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub194 on the scale
    4. SWE-Bench verifiedEpoch AI Benchmarking Hub0.8184 on the scale
    5. GPQA diamondEpoch AI Benchmarking Hub0.9483 on the scale
  35. 035meta/muse-spark-1.3xhigh116.79282

    28 columns on 2 boards, hardest first are the whole evidence behind 116.79. Each is a door to the column and everything else scored on it.

    1. typescriptLiveBench60122 on the scale
    2. Mystery Game PuzzlesEpoch AI Benchmarking Hub0.14121 on the scale
    3. Chess PuzzlesEpoch AI Benchmarking Hub0.34119 on the scale
    4. tablejoinLiveBench48.19117 on the scale
    5. FrontierMath-Tier-4-v2-PrivateEpoch AI Benchmarking Hub0.41116 on the scale
    6. pythonLiveBench55109 on the scale
    7. FrontierMath-Tiers-1-3-v2-PrivateEpoch AI Benchmarking Hub0.74109 on the scale
    8. plot_unscramblingLiveBench68.38106 on the scale
    9. integrals_with_gameLiveBench96104 on the scale
    10. consecutive_eventsLiveBench90.50102 on the scale
    11. zebra_puzzleLiveBench98102 on the scale
    12. javascriptLiveBench77.2799 on the scale
    13. logic_with_navigationLiveBench7696 on the scale
    14. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.9994 on the scale
    15. simplifyLiveBench72.5292 on the scale
    16. connectionsLiveBench9491 on the scale
    17. theory_of_mindLiveBench84.6188 on the scale
    18. code_completionLiveBench80.4487 on the scale
    19. paraphraseLiveBench78.6286 on the scale
    20. summarizeLiveBench83.4085 on the scale
    21. typosLiveBench8677 on the scale
    22. code_generationLiveBench81.6976 on the scale
    23. story_generationLiveBench77.4874 on the scale
    24. olympiadLiveBench91.7472 on the scale
    25. spatialLiveBench10053 on the scale
    26. AMPS_HardLiveBench9947 on the scale
    27. math_compLiveBench97.0642 on the scale
    28. tablereformatLiveBench10041 on the scale
  36. 036gpt-5.2-pro-2025-12-11not in the catalogxhigh116.7431

    3 columns on 1 board, hardest first are the whole evidence behind 116.74. Each is a door to the column and everything else scored on it.

    1. Chess PuzzlesEpoch AI Benchmarking Hub0.60119 on the scale
    2. FrontierMath-Tier-4-v2-PrivateEpoch AI Benchmarking Hub0.46116 on the scale
    3. FrontierMath-Tiers-1-3-v2-PrivateEpoch AI Benchmarking Hub0.74109 on the scale
  37. 037smaug-flashnot in the catalogunstated116.63231

    23 columns on 1 board, hardest first are the whole evidence behind 116.63. Each is a door to the column and everything else scored on it.

    1. typescriptLiveBench50122 on the scale
    2. tablejoinLiveBench50.71117 on the scale
    3. pythonLiveBench65109 on the scale
    4. plot_unscramblingLiveBench60.31106 on the scale
    5. integrals_with_gameLiveBench76104 on the scale
    6. consecutive_eventsLiveBench88.61102 on the scale
    7. zebra_puzzleLiveBench98102 on the scale
    8. javascriptLiveBench68.1899 on the scale
    9. logic_with_navigationLiveBench7296 on the scale
    10. simplifyLiveBench63.1392 on the scale
    11. connectionsLiveBench99.3391 on the scale
    12. theory_of_mindLiveBench76.9288 on the scale
    13. code_completionLiveBench73.9187 on the scale
    14. paraphraseLiveBench65.5786 on the scale
    15. summarizeLiveBench78.3585 on the scale
    16. typosLiveBench7877 on the scale
    17. code_generationLiveBench80.2876 on the scale
    18. story_generationLiveBench69.9874 on the scale
    19. olympiadLiveBench90.2072 on the scale
    20. spatialLiveBench9853 on the scale
    21. AMPS_HardLiveBench9747 on the scale
    22. math_compLiveBench97.0642 on the scale
    23. tablereformatLiveBench98.0441 on the scale
  38. 038moonshotai/kimi-k3unstated116.54231

    23 columns on 1 board, hardest first are the whole evidence behind 116.54. Each is a door to the column and everything else scored on it.

    1. typescriptLiveBench53.33122 on the scale
    2. tablejoinLiveBench48.40117 on the scale
    3. pythonLiveBench65109 on the scale
    4. plot_unscramblingLiveBench72.58106 on the scale
    5. integrals_with_gameLiveBench54104 on the scale
    6. consecutive_eventsLiveBench89.76102 on the scale
    7. zebra_puzzleLiveBench100102 on the scale
    8. javascriptLiveBench68.1899 on the scale
    9. logic_with_navigationLiveBench8096 on the scale
    10. simplifyLiveBench66.3792 on the scale
    11. connectionsLiveBench10091 on the scale
    12. theory_of_mindLiveBench82.6988 on the scale
    13. code_completionLiveBench82.6187 on the scale
    14. paraphraseLiveBench74.3786 on the scale
    15. summarizeLiveBench69.3585 on the scale
    16. typosLiveBench8477 on the scale
    17. code_generationLiveBench80.2876 on the scale
    18. story_generationLiveBench75.3774 on the scale
    19. olympiadLiveBench91.6572 on the scale
    20. spatialLiveBench10053 on the scale
    21. AMPS_HardLiveBench9747 on the scale
    22. math_compLiveBench95.1042 on the scale
    23. tablereformatLiveBench98.0441 on the scale
  39. 039deepseek/deepseek-v4.1-flashmax116.49322

    32 columns on 2 boards, hardest first are the whole evidence behind 116.49. Each is a door to the column and everything else scored on it.

    1. typescriptLiveBench60122 on the scale
    2. Mystery Game PuzzlesEpoch AI Benchmarking Hub0.43121 on the scale
    3. Furniture AssemblyEpoch AI Benchmarking Hub0.34120 on the scale
    4. Chess PuzzlesEpoch AI Benchmarking Hub0.48119 on the scale
    5. MirrorCodeEpoch AI Benchmarking Hub0.64119 on the scale
    6. tablejoinLiveBench49.04117 on the scale
    7. FrontierMath-Tier-4-v2-PrivateEpoch AI Benchmarking Hub0.27116 on the scale
    8. SimpleQA VerifiedEpoch AI Benchmarking Hub0.43115 on the scale
    9. pythonLiveBench90109 on the scale
    10. FrontierMath-Tiers-1-3-v2-PrivateEpoch AI Benchmarking Hub0.67109 on the scale
    11. plot_unscramblingLiveBench61.57106 on the scale
    12. integrals_with_gameLiveBench90104 on the scale
    13. consecutive_eventsLiveBench88.72102 on the scale
    14. zebra_puzzleLiveBench100102 on the scale
    15. javascriptLiveBench81.8299 on the scale
    16. logic_with_navigationLiveBench6896 on the scale
    17. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.9894 on the scale
    18. simplifyLiveBench67.0792 on the scale
    19. connectionsLiveBench10091 on the scale
    20. theory_of_mindLiveBench80.7788 on the scale
    21. code_completionLiveBench82.6187 on the scale
    22. paraphraseLiveBench70.7386 on the scale
    23. summarizeLiveBench69.6585 on the scale
    24. GPQA diamondEpoch AI Benchmarking Hub0.9083 on the scale
    25. typosLiveBench8277 on the scale
    26. code_generationLiveBench77.4776 on the scale
    27. story_generationLiveBench72.6874 on the scale
    28. olympiadLiveBench89.0872 on the scale
    29. spatialLiveBench9853 on the scale
    30. AMPS_HardLiveBench9847 on the scale
    31. math_compLiveBench96.0842 on the scale
    32. tablereformatLiveBench10041 on the scale
  40. 040qwen3.8-maxnot in the catalogxhigh116.3981

    8 columns on 1 board, hardest first are the whole evidence behind 116.39. Each is a door to the column and everything else scored on it.

    1. Mystery Game PuzzlesEpoch AI Benchmarking Hub0.38121 on the scale
    2. Chess PuzzlesEpoch AI Benchmarking Hub0.46119 on the scale
    3. MirrorCodeEpoch AI Benchmarking Hub0.52119 on the scale
    4. FrontierMath-Tier-4-v2-PrivateEpoch AI Benchmarking Hub0.46116 on the scale
    5. SimpleQA VerifiedEpoch AI Benchmarking Hub0.46115 on the scale
    6. FrontierMath-Tiers-1-3-v2-PrivateEpoch AI Benchmarking Hub0.75109 on the scale
    7. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.9994 on the scale
    8. GPQA diamondEpoch AI Benchmarking Hub0.9383 on the scale
  41. 041deepseek/deepseek-v4-flash-vision-expunstated116.36231

    23 columns on 1 board, hardest first are the whole evidence behind 116.36. Each is a door to the column and everything else scored on it.

    1. typescriptLiveBench56.67122 on the scale
    2. tablejoinLiveBench50.35117 on the scale
    3. pythonLiveBench75109 on the scale
    4. plot_unscramblingLiveBench57.75106 on the scale
    5. integrals_with_gameLiveBench76104 on the scale
    6. consecutive_eventsLiveBench90.05102 on the scale
    7. zebra_puzzleLiveBench98.75102 on the scale
    8. javascriptLiveBench63.6499 on the scale
    9. logic_with_navigationLiveBench6896 on the scale
    10. simplifyLiveBench65.0792 on the scale
    11. connectionsLiveBench99.3391 on the scale
    12. theory_of_mindLiveBench78.8588 on the scale
    13. code_completionLiveBench67.3987 on the scale
    14. paraphraseLiveBench72.8386 on the scale
    15. summarizeLiveBench72.1085 on the scale
    16. typosLiveBench8477 on the scale
    17. code_generationLiveBench69.0176 on the scale
    18. story_generationLiveBench73.8374 on the scale
    19. olympiadLiveBench90.1772 on the scale
    20. spatialLiveBench9653 on the scale
    21. AMPS_HardLiveBench8847 on the scale
    22. math_compLiveBench97.0642 on the scale
    23. tablereformatLiveBench98.0441 on the scale
  42. 042smaug-agenticnot in the catalogunstated116.30231

    23 columns on 1 board, hardest first are the whole evidence behind 116.30. Each is a door to the column and everything else scored on it.

    1. typescriptLiveBench56.67122 on the scale
    2. tablejoinLiveBench51.23117 on the scale
    3. pythonLiveBench60109 on the scale
    4. plot_unscramblingLiveBench71.07106 on the scale
    5. integrals_with_gameLiveBench52104 on the scale
    6. consecutive_eventsLiveBench90.42102 on the scale
    7. zebra_puzzleLiveBench98.25102 on the scale
    8. javascriptLiveBench77.2799 on the scale
    9. logic_with_navigationLiveBench8496 on the scale
    10. simplifyLiveBench66.6292 on the scale
    11. connectionsLiveBench10091 on the scale
    12. theory_of_mindLiveBench78.8588 on the scale
    13. code_completionLiveBench80.4487 on the scale
    14. paraphraseLiveBench68.6386 on the scale
    15. summarizeLiveBench72.0585 on the scale
    16. typosLiveBench8277 on the scale
    17. code_generationLiveBench84.5176 on the scale
    18. story_generationLiveBench76.6774 on the scale
    19. olympiadLiveBench91.5672 on the scale
    20. spatialLiveBench10053 on the scale
    21. AMPS_HardLiveBench9847 on the scale
    22. math_compLiveBench94.1242 on the scale
    23. tablereformatLiveBench98.0441 on the scale
  43. 043deepseek/deepseek-v4.1-flash-1017max116.2571

    7 columns on 1 board, hardest first are the whole evidence behind 116.25. Each is a door to the column and everything else scored on it.

    1. Mystery Game PuzzlesEpoch AI Benchmarking Hub0.49121 on the scale
    2. Chess PuzzlesEpoch AI Benchmarking Hub0.46119 on the scale
    3. FrontierMath-Tier-4-v2-PrivateEpoch AI Benchmarking Hub0.46116 on the scale
    4. SimpleQA VerifiedEpoch AI Benchmarking Hub0.42115 on the scale
    5. FrontierMath-Tiers-1-3-v2-PrivateEpoch AI Benchmarking Hub0.71109 on the scale
    6. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.9994 on the scale
    7. GPQA diamondEpoch AI Benchmarking Hub0.9383 on the scale
  44. 044gpt-5.4-2026-03-05not in the catalogxhigh116.23131

    13 columns on 1 board, hardest first are the whole evidence behind 116.23. Each is a door to the column and everything else scored on it.

    1. EBR-benchEpoch AI Benchmarking Hub0.25123 on the scale
    2. Mystery Game PuzzlesEpoch AI Benchmarking Hub0.37121 on the scale
    3. FrontierMath-Tier-4-2025-07-01-PrivateEpoch AI Benchmarking Hub0.27120 on the scale
    4. Furniture AssemblyEpoch AI Benchmarking Hub0.38120 on the scale
    5. Chess PuzzlesEpoch AI Benchmarking Hub0.48119 on the scale
    6. MirrorCodeEpoch AI Benchmarking Hub0.23119 on the scale
    7. FrontierMath-Tier-4-2025-07-01-PublicEpoch AI Benchmarking Hub0.50116 on the scale
    8. FrontierMath-Tier-4-v2-PrivateEpoch AI Benchmarking Hub0.49116 on the scale
    9. SimpleQA VerifiedEpoch AI Benchmarking Hub0.45115 on the scale
    10. FrontierMath-2025-02-28-PrivateEpoch AI Benchmarking Hub0.48115 on the scale
    11. FrontierMath-Tiers-1-3-v2-PrivateEpoch AI Benchmarking Hub0.79109 on the scale
    12. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.9594 on the scale
    13. GPQA diamondEpoch AI Benchmarking Hub0.9383 on the scale
  45. 045google/gemini-3.7-flashhigh116.01322

    32 columns on 2 boards, hardest first are the whole evidence behind 116.01. Each is a door to the column and everything else scored on it.

    1. typescriptLiveBench46.67122 on the scale
    2. Mystery Game PuzzlesEpoch AI Benchmarking Hub0.37121 on the scale
    3. Furniture AssemblyEpoch AI Benchmarking Hub0.27120 on the scale
    4. Chess PuzzlesEpoch AI Benchmarking Hub0.66119 on the scale
    5. MirrorCodeEpoch AI Benchmarking Hub0.41119 on the scale
    6. tablejoinLiveBench45.48117 on the scale
    7. FrontierMath-Tier-4-v2-PrivateEpoch AI Benchmarking Hub0.37116 on the scale
    8. SimpleQA VerifiedEpoch AI Benchmarking Hub0.69115 on the scale
    9. pythonLiveBench60109 on the scale
    10. FrontierMath-Tiers-1-3-v2-PrivateEpoch AI Benchmarking Hub0.72109 on the scale
    11. plot_unscramblingLiveBench66.36106 on the scale
    12. integrals_with_gameLiveBench88104 on the scale
    13. consecutive_eventsLiveBench60.37102 on the scale
    14. zebra_puzzleLiveBench94.50102 on the scale
    15. javascriptLiveBench68.1899 on the scale
    16. logic_with_navigationLiveBench7496 on the scale
    17. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.9794 on the scale
    18. simplifyLiveBench74.6292 on the scale
    19. connectionsLiveBench10091 on the scale
    20. theory_of_mindLiveBench82.6988 on the scale
    21. code_completionLiveBench76.0987 on the scale
    22. paraphraseLiveBench78.0786 on the scale
    23. summarizeLiveBench84.7785 on the scale
    24. GPQA diamondEpoch AI Benchmarking Hub0.9583 on the scale
    25. typosLiveBench9077 on the scale
    26. code_generationLiveBench81.6976 on the scale
    27. story_generationLiveBench82.2574 on the scale
    28. olympiadLiveBench91.7972 on the scale
    29. spatialLiveBench10053 on the scale
    30. AMPS_HardLiveBench9847 on the scale
    31. math_compLiveBench96.0842 on the scale
    32. tablereformatLiveBench98.0441 on the scale
  46. 046gpt-5.4-2026-03-05not in the cataloghigh115.9871

    7 columns on 1 board, hardest first are the whole evidence behind 115.98. Each is a door to the column and everything else scored on it.

    1. Chess PuzzlesEpoch AI Benchmarking Hub0.42119 on the scale
    2. MirrorCodeEpoch AI Benchmarking Hub0.16119 on the scale
    3. FrontierMath-Tier-4-2025-07-01-PublicEpoch AI Benchmarking Hub0.50116 on the scale
    4. FrontierMath-2025-02-28-PublicEpoch AI Benchmarking Hub0.80106 on the scale
    5. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.9894 on the scale
    6. SWE-Bench verifiedEpoch AI Benchmarking Hub0.7784 on the scale
    7. GPQA diamondEpoch AI Benchmarking Hub0.9083 on the scale
  47. 047anthropic/claude-opus-5unstated115.9431

    3 columns on 1 board, hardest first are the whole evidence behind 115.94. Each is a door to the column and everything else scored on it.

    1. Mystery Game PuzzlesEpoch AI Benchmarking Hub0.37121 on the scale
    2. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.9894 on the scale
    3. GPQA diamondEpoch AI Benchmarking Hub0.9383 on the scale
  48. 048meta/muse-spark-1.3max115.5551

    5 columns on 1 board, hardest first are the whole evidence behind 115.55. Each is a door to the column and everything else scored on it.

    1. Mystery Game PuzzlesEpoch AI Benchmarking Hub0.25121 on the scale
    2. Chess PuzzlesEpoch AI Benchmarking Hub0.37119 on the scale
    3. MirrorCodeEpoch AI Benchmarking Hub0.54119 on the scale
    4. FrontierMath-Tier-4-v2-PrivateEpoch AI Benchmarking Hub0.46116 on the scale
    5. FrontierMath-Tiers-1-3-v2-PrivateEpoch AI Benchmarking Hub0.74109 on the scale
  49. 049openai/gpt-5.6-lunamax114.95322

    32 columns on 2 boards, hardest first are the whole evidence behind 114.95. Each is a door to the column and everything else scored on it.

    1. typescriptLiveBench36.67122 on the scale
    2. Mystery Game PuzzlesEpoch AI Benchmarking Hub0.21121 on the scale
    3. Furniture AssemblyEpoch AI Benchmarking Hub0.42120 on the scale
    4. Chess PuzzlesEpoch AI Benchmarking Hub0.43119 on the scale
    5. MirrorCodeEpoch AI Benchmarking Hub0.21119 on the scale
    6. tablejoinLiveBench47.60117 on the scale
    7. FrontierMath-Tier-4-v2-PrivateEpoch AI Benchmarking Hub0.61116 on the scale
    8. SimpleQA VerifiedEpoch AI Benchmarking Hub0.41115 on the scale
    9. pythonLiveBench45109 on the scale
    10. FrontierMath-Tiers-1-3-v2-PrivateEpoch AI Benchmarking Hub0.82109 on the scale
    11. plot_unscramblingLiveBench51.20106 on the scale
    12. integrals_with_gameLiveBench70104 on the scale
    13. consecutive_eventsLiveBench86.50102 on the scale
    14. zebra_puzzleLiveBench93.50102 on the scale
    15. javascriptLiveBench63.6499 on the scale
    16. logic_with_navigationLiveBench8096 on the scale
    17. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.9894 on the scale
    18. simplifyLiveBench58.6792 on the scale
    19. connectionsLiveBench96.5091 on the scale
    20. theory_of_mindLiveBench73.0888 on the scale
    21. code_completionLiveBench86.9687 on the scale
    22. paraphraseLiveBench47.8286 on the scale
    23. summarizeLiveBench64.9385 on the scale
    24. GPQA diamondEpoch AI Benchmarking Hub0.9283 on the scale
    25. typosLiveBench7077 on the scale
    26. code_generationLiveBench78.8776 on the scale
    27. story_generationLiveBench69.0774 on the scale
    28. olympiadLiveBench88.6572 on the scale
    29. spatialLiveBench9653 on the scale
    30. AMPS_HardLiveBench9847 on the scale
    31. math_compLiveBench92.1642 on the scale
    32. tablereformatLiveBench10041 on the scale
  50. 050doubao-seed-evolvingnot in the cataloghigh114.7641

    4 columns on 1 board, hardest first are the whole evidence behind 114.76. Each is a door to the column and everything else scored on it.

    1. Chess PuzzlesEpoch AI Benchmarking Hub0.40119 on the scale
    2. SimpleQA VerifiedEpoch AI Benchmarking Hub0.42115 on the scale
    3. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.9994 on the scale
    4. GPQA diamondEpoch AI Benchmarking Hub0.9383 on the scale
  51. 051moonshotai/kimi-k3max114.75101

    10 columns on 1 board, hardest first are the whole evidence behind 114.75. Each is a door to the column and everything else scored on it.

    1. FrontierMath-ErdosEpoch AI Benchmarking Hub0153 on the scale
    2. Mystery Game PuzzlesEpoch AI Benchmarking Hub0.26121 on the scale
    3. Furniture AssemblyEpoch AI Benchmarking Hub0.34120 on the scale
    4. Chess PuzzlesEpoch AI Benchmarking Hub0.36119 on the scale
    5. MirrorCodeEpoch AI Benchmarking Hub0.54119 on the scale
    6. FrontierMath-Tier-4-v2-PrivateEpoch AI Benchmarking Hub0.39116 on the scale
    7. SimpleQA VerifiedEpoch AI Benchmarking Hub0.51115 on the scale
    8. FrontierMath-Tiers-1-3-v2-PrivateEpoch AI Benchmarking Hub0.72109 on the scale
    9. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.9794 on the scale
    10. GPQA diamondEpoch AI Benchmarking Hub0.9383 on the scale
  52. 052x-ai/grok-4.5unstated114.74231

    23 columns on 1 board, hardest first are the whole evidence behind 114.74. Each is a door to the column and everything else scored on it.

    1. typescriptLiveBench36.67122 on the scale
    2. tablejoinLiveBench43.58117 on the scale
    3. pythonLiveBench60109 on the scale
    4. plot_unscramblingLiveBench66.39106 on the scale
    5. integrals_with_gameLiveBench78104 on the scale
    6. consecutive_eventsLiveBench75.54102 on the scale
    7. zebra_puzzleLiveBench94102 on the scale
    8. javascriptLiveBench72.7399 on the scale
    9. logic_with_navigationLiveBench7296 on the scale
    10. simplifyLiveBench70.1792 on the scale
    11. connectionsLiveBench9891 on the scale
    12. theory_of_mindLiveBench82.6988 on the scale
    13. code_completionLiveBench69.5687 on the scale
    14. paraphraseLiveBench69.2286 on the scale
    15. summarizeLiveBench73.1585 on the scale
    16. typosLiveBench8477 on the scale
    17. code_generationLiveBench67.6176 on the scale
    18. story_generationLiveBench73.5874 on the scale
    19. olympiadLiveBench89.2472 on the scale
    20. spatialLiveBench10053 on the scale
    21. AMPS_HardLiveBench9947 on the scale
    22. math_compLiveBench97.0642 on the scale
    23. tablereformatLiveBench10041 on the scale
  53. 053smaug-mininot in the catalogunstated114.73231

    23 columns on 1 board, hardest first are the whole evidence behind 114.73. Each is a door to the column and everything else scored on it.

    1. typescriptLiveBench53.33122 on the scale
    2. tablejoinLiveBench51.87117 on the scale
    3. pythonLiveBench70109 on the scale
    4. plot_unscramblingLiveBench55.33106 on the scale
    5. integrals_with_gameLiveBench76104 on the scale
    6. consecutive_eventsLiveBench88.50102 on the scale
    7. zebra_puzzleLiveBench94102 on the scale
    8. javascriptLiveBench59.0999 on the scale
    9. logic_with_navigationLiveBench7096 on the scale
    10. simplifyLiveBench65.3892 on the scale
    11. connectionsLiveBench91.6791 on the scale
    12. theory_of_mindLiveBench69.2388 on the scale
    13. code_completionLiveBench80.4487 on the scale
    14. paraphraseLiveBench76.1886 on the scale
    15. summarizeLiveBench76.1085 on the scale
    16. typosLiveBench8477 on the scale
    17. code_generationLiveBench70.4276 on the scale
    18. story_generationLiveBench7874 on the scale
    19. olympiadLiveBench90.8572 on the scale
    20. spatialLiveBench9853 on the scale
    21. AMPS_HardLiveBench9847 on the scale
    22. math_compLiveBench94.1242 on the scale
    23. tablereformatLiveBench96.0841 on the scale
  54. 054x-ai/grok-4.6xhigh114.39101

    10 columns on 1 board, hardest first are the whole evidence behind 114.39. Each is a door to the column and everything else scored on it.

    1. EBR-benchEpoch AI Benchmarking Hub0.30123 on the scale
    2. Mystery Game PuzzlesEpoch AI Benchmarking Hub0.34121 on the scale
    3. Furniture AssemblyEpoch AI Benchmarking Hub0.40120 on the scale
    4. Chess PuzzlesEpoch AI Benchmarking Hub0.33119 on the scale
    5. MirrorCodeEpoch AI Benchmarking Hub0.41119 on the scale
    6. FrontierMath-Tier-4-v2-PrivateEpoch AI Benchmarking Hub0.32116 on the scale
    7. SimpleQA VerifiedEpoch AI Benchmarking Hub0.49115 on the scale
    8. FrontierMath-Tiers-1-3-v2-PrivateEpoch AI Benchmarking Hub0.66109 on the scale
    9. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.9994 on the scale
    10. GPQA diamondEpoch AI Benchmarking Hub0.9383 on the scale
  55. 056google/gemini-3.8-flashhigh114.21332

    33 columns on 2 boards, hardest first are the whole evidence behind 114.21. Each is a door to the column and everything else scored on it.

    1. FrontierMath-ErdosEpoch AI Benchmarking Hub0153 on the scale
    2. typescriptLiveBench40122 on the scale
    3. Mystery Game PuzzlesEpoch AI Benchmarking Hub0.47121 on the scale
    4. Furniture AssemblyEpoch AI Benchmarking Hub0.32120 on the scale
    5. Chess PuzzlesEpoch AI Benchmarking Hub0.58119 on the scale
    6. MirrorCodeEpoch AI Benchmarking Hub0.39119 on the scale
    7. tablejoinLiveBench45.33117 on the scale
    8. FrontierMath-Tier-4-v2-PrivateEpoch AI Benchmarking Hub0.22116 on the scale
    9. SimpleQA VerifiedEpoch AI Benchmarking Hub0.70115 on the scale
    10. pythonLiveBench50109 on the scale
    11. FrontierMath-Tiers-1-3-v2-PrivateEpoch AI Benchmarking Hub0.68109 on the scale
    12. plot_unscramblingLiveBench73.38106 on the scale
    13. integrals_with_gameLiveBench80104 on the scale
    14. consecutive_eventsLiveBench20.61102 on the scale
    15. zebra_puzzleLiveBench98.25102 on the scale
    16. javascriptLiveBench72.7399 on the scale
    17. logic_with_navigationLiveBench8296 on the scale
    18. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.9994 on the scale
    19. simplifyLiveBench75.4092 on the scale
    20. connectionsLiveBench10091 on the scale
    21. theory_of_mindLiveBench76.9288 on the scale
    22. code_completionLiveBench71.7487 on the scale
    23. paraphraseLiveBench8086 on the scale
    24. summarizeLiveBench87.5085 on the scale
    25. GPQA diamondEpoch AI Benchmarking Hub0.9583 on the scale
    26. typosLiveBench9077 on the scale
    27. code_generationLiveBench73.2476 on the scale
    28. story_generationLiveBench82.7574 on the scale
    29. olympiadLiveBench92.1672 on the scale
    30. spatialLiveBench10053 on the scale
    31. AMPS_HardLiveBench9947 on the scale
    32. math_compLiveBench95.1042 on the scale
    33. tablereformatLiveBench96.0841 on the scale
  56. 055meta/muse-spark-1.1xhigh114.21242

    24 columns on 2 boards, hardest first are the whole evidence behind 114.21. Each is a door to the column and everything else scored on it.

    1. typescriptLiveBench43.33122 on the scale
    2. Chess PuzzlesEpoch AI Benchmarking Hub0.34119 on the scale
    3. tablejoinLiveBench46.56117 on the scale
    4. pythonLiveBench55109 on the scale
    5. plot_unscramblingLiveBench63.03106 on the scale
    6. integrals_with_gameLiveBench83104 on the scale
    7. consecutive_eventsLiveBench71.09102 on the scale
    8. zebra_puzzleLiveBench96102 on the scale
    9. javascriptLiveBench77.2799 on the scale
    10. logic_with_navigationLiveBench7896 on the scale
    11. simplifyLiveBench65.7092 on the scale
    12. connectionsLiveBench9891 on the scale
    13. theory_of_mindLiveBench76.9288 on the scale
    14. code_completionLiveBench78.2687 on the scale
    15. paraphraseLiveBench69.4086 on the scale
    16. summarizeLiveBench74.3085 on the scale
    17. typosLiveBench6277 on the scale
    18. code_generationLiveBench76.0676 on the scale
    19. story_generationLiveBench69.1574 on the scale
    20. olympiadLiveBench87.5072 on the scale
    21. spatialLiveBench10053 on the scale
    22. AMPS_HardLiveBench8247 on the scale
    23. math_compLiveBench96.0842 on the scale
    24. tablereformatLiveBench10041 on the scale
  57. 057claude-sonnet-4-6-thinking-autonot in the catalogmedium114.06231

    23 columns on 1 board, hardest first are the whole evidence behind 114.06. Each is a door to the column and everything else scored on it.

    1. typescriptLiveBench23.33122 on the scale
    2. tablejoinLiveBench45.08117 on the scale
    3. pythonLiveBench50109 on the scale
    4. plot_unscramblingLiveBench56.98106 on the scale
    5. integrals_with_gameLiveBench90104 on the scale
    6. consecutive_eventsLiveBench92.68102 on the scale
    7. zebra_puzzleLiveBench96102 on the scale
    8. javascriptLiveBench54.5599 on the scale
    9. logic_with_navigationLiveBench7096 on the scale
    10. simplifyLiveBench62.9392 on the scale
    11. connectionsLiveBench99.3391 on the scale
    12. theory_of_mindLiveBench73.0888 on the scale
    13. code_completionLiveBench78.2687 on the scale
    14. paraphraseLiveBench59.4086 on the scale
    15. summarizeLiveBench61.6585 on the scale
    16. typosLiveBench7277 on the scale
    17. code_generationLiveBench80.2876 on the scale
    18. story_generationLiveBench68.9074 on the scale
    19. olympiadLiveBench87.8672 on the scale
    20. spatialLiveBench10053 on the scale
    21. AMPS_HardLiveBench7647 on the scale
    22. math_compLiveBench94.1242 on the scale
    23. tablereformatLiveBench96.0841 on the scale
  58. 058x-ai/grok-4.6high114.0241

    4 columns on 1 board, hardest first are the whole evidence behind 114.02. Each is a door to the column and everything else scored on it.

    1. Chess PuzzlesEpoch AI Benchmarking Hub0.33119 on the scale
    2. SimpleQA VerifiedEpoch AI Benchmarking Hub0.49115 on the scale
    3. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.9894 on the scale
    4. GPQA diamondEpoch AI Benchmarking Hub0.9483 on the scale
  59. 059openai/gpt-6-lunamax113.99352

    35 columns on 2 boards, hardest first are the whole evidence behind 113.99. Each is a door to the column and everything else scored on it.

    1. SpireClimb (Slay the Spire 1, Ascension 20 Heart)Epoch AI Benchmarking Hub0139 on the scale
    2. SpireClimbEpoch AI Benchmarking Hub0137 on the scale
    3. SpireClimb (Slay the Spire 2, Ascension 10)Epoch AI Benchmarking Hub0136 on the scale
    4. typescriptLiveBench40122 on the scale
    5. Mystery Game PuzzlesEpoch AI Benchmarking Hub0.07121 on the scale
    6. Furniture AssemblyEpoch AI Benchmarking Hub0.44120 on the scale
    7. Chess PuzzlesEpoch AI Benchmarking Hub0.36119 on the scale
    8. MirrorCodeEpoch AI Benchmarking Hub0.27119 on the scale
    9. tablejoinLiveBench49.62117 on the scale
    10. FrontierMath-Tier-4-v2-PrivateEpoch AI Benchmarking Hub0.56116 on the scale
    11. SimpleQA VerifiedEpoch AI Benchmarking Hub0.41115 on the scale
    12. pythonLiveBench50109 on the scale
    13. FrontierMath-Tiers-1-3-v2-PrivateEpoch AI Benchmarking Hub0.79109 on the scale
    14. plot_unscramblingLiveBench57.48106 on the scale
    15. integrals_with_gameLiveBench74104 on the scale
    16. consecutive_eventsLiveBench70.49102 on the scale
    17. zebra_puzzleLiveBench96102 on the scale
    18. javascriptLiveBench63.6499 on the scale
    19. logic_with_navigationLiveBench6296 on the scale
    20. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.9994 on the scale
    21. simplifyLiveBench55.4392 on the scale
    22. connectionsLiveBench10091 on the scale
    23. theory_of_mindLiveBench73.0888 on the scale
    24. code_completionLiveBench80.4487 on the scale
    25. paraphraseLiveBench49.7086 on the scale
    26. summarizeLiveBench55.3285 on the scale
    27. GPQA diamondEpoch AI Benchmarking Hub0.9083 on the scale
    28. typosLiveBench6477 on the scale
    29. code_generationLiveBench77.4776 on the scale
    30. story_generationLiveBench63.2874 on the scale
    31. olympiadLiveBench90.3872 on the scale
    32. spatialLiveBench9653 on the scale
    33. AMPS_HardLiveBench9847 on the scale
    34. math_compLiveBench94.1242 on the scale
    35. tablereformatLiveBench10041 on the scale
  60. 060muse-spark-open-816b-a42bnot in the catalogxhigh113.9251

    5 columns on 1 board, hardest first are the whole evidence behind 113.92. Each is a door to the column and everything else scored on it.

    1. FrontierMath-Tier-4-v2-PrivateEpoch AI Benchmarking Hub0.32116 on the scale
    2. SimpleQA VerifiedEpoch AI Benchmarking Hub0.57115 on the scale
    3. FrontierMath-Tiers-1-3-v2-PrivateEpoch AI Benchmarking Hub0.70109 on the scale
    4. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.9894 on the scale
    5. GPQA diamondEpoch AI Benchmarking Hub0.8983 on the scale
  61. 061google/gemini-3.1-pro-previewhigh113.89302

    30 columns on 2 boards, hardest first are the whole evidence behind 113.89. Each is a door to the column and everything else scored on it.

    1. typescriptLiveBench23.33122 on the scale
    2. Mystery Game PuzzlesEpoch AI Benchmarking Hub0.34121 on the scale
    3. Furniture AssemblyEpoch AI Benchmarking Hub0.27120 on the scale
    4. Chess PuzzlesEpoch AI Benchmarking Hub0.51119 on the scale
    5. MirrorCodeEpoch AI Benchmarking Hub0.09119 on the scale
    6. tablejoinLiveBench52.35117 on the scale
    7. SimpleQA VerifiedEpoch AI Benchmarking Hub0.73115 on the scale
    8. pythonLiveBench50109 on the scale
    9. plot_unscramblingLiveBench74.13106 on the scale
    10. integrals_with_gameLiveBench78104 on the scale
    11. consecutive_eventsLiveBench85.24102 on the scale
    12. zebra_puzzleLiveBench85.25102 on the scale
    13. javascriptLiveBench59.0999 on the scale
    14. logic_with_navigationLiveBench7296 on the scale
    15. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.9694 on the scale
    16. simplifyLiveBench71.0592 on the scale
    17. connectionsLiveBench10091 on the scale
    18. theory_of_mindLiveBench80.7788 on the scale
    19. code_completionLiveBench78.2687 on the scale
    20. paraphraseLiveBench79.8786 on the scale
    21. summarizeLiveBench88.2385 on the scale
    22. GPQA diamondEpoch AI Benchmarking Hub0.9483 on the scale
    23. typosLiveBench8277 on the scale
    24. code_generationLiveBench74.6576 on the scale
    25. story_generationLiveBench77.2574 on the scale
    26. olympiadLiveBench92.1072 on the scale
    27. spatialLiveBench9853 on the scale
    28. AMPS_HardLiveBench9847 on the scale
    29. math_compLiveBench96.0842 on the scale
    30. tablereformatLiveBench98.0441 on the scale
  62. 062claude-haiku-5-5not in the catalogmax113.88322

    32 columns on 2 boards, hardest first are the whole evidence behind 113.88. Each is a door to the column and everything else scored on it.

    1. EBR-benchEpoch AI Benchmarking Hub0.44123 on the scale
    2. typescriptLiveBench43.33122 on the scale
    3. Mystery Game PuzzlesEpoch AI Benchmarking Hub0.30121 on the scale
    4. Furniture AssemblyEpoch AI Benchmarking Hub0.47120 on the scale
    5. Chess PuzzlesEpoch AI Benchmarking Hub0.55119 on the scale
    6. MirrorCodeEpoch AI Benchmarking Hub0.79119 on the scale
    7. tablejoinLiveBench46.67117 on the scale
    8. FrontierMath-Tier-4-v2-PrivateEpoch AI Benchmarking Hub0.46116 on the scale
    9. SimpleQA VerifiedEpoch AI Benchmarking Hub0.24115 on the scale
    10. pythonLiveBench60109 on the scale
    11. FrontierMath-Tiers-1-3-v2-PrivateEpoch AI Benchmarking Hub0.75109 on the scale
    12. plot_unscramblingLiveBench27.88106 on the scale
    13. integrals_with_gameLiveBench67104 on the scale
    14. consecutive_eventsLiveBench10.64102 on the scale
    15. zebra_puzzleLiveBench94102 on the scale
    16. javascriptLiveBench68.1899 on the scale
    17. logic_with_navigationLiveBench6696 on the scale
    18. simplifyLiveBench50.2592 on the scale
    19. connectionsLiveBench9691 on the scale
    20. theory_of_mindLiveBench86.5488 on the scale
    21. code_completionLiveBench78.2687 on the scale
    22. paraphraseLiveBench50.2286 on the scale
    23. summarizeLiveBench53.6385 on the scale
    24. GPQA diamondEpoch AI Benchmarking Hub0.9083 on the scale
    25. typosLiveBench6477 on the scale
    26. code_generationLiveBench77.4776 on the scale
    27. story_generationLiveBench64.5374 on the scale
    28. olympiadLiveBench83.7072 on the scale
    29. spatialLiveBench9253 on the scale
    30. AMPS_HardLiveBench9747 on the scale
    31. math_compLiveBench98.0442 on the scale
    32. tablereformatLiveBench98.0441 on the scale
  63. 063google/gemini-3-flash-previewhigh113.7051

    5 columns on 1 board, hardest first are the whole evidence behind 113.70. Each is a door to the column and everything else scored on it.

    1. Mystery Game PuzzlesEpoch AI Benchmarking Hub0.20121 on the scale
    2. Chess PuzzlesEpoch AI Benchmarking Hub0.40119 on the scale
    3. SimpleQA VerifiedEpoch AI Benchmarking Hub0.67115 on the scale
    4. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.9694 on the scale
    5. GPQA diamondEpoch AI Benchmarking Hub0.8983 on the scale
  64. 064deepseek/deepseek-v4-pro-0813max113.6081

    8 columns on 1 board, hardest first are the whole evidence behind 113.60. Each is a door to the column and everything else scored on it.

    1. Mystery Game PuzzlesEpoch AI Benchmarking Hub0.43121 on the scale
    2. Chess PuzzlesEpoch AI Benchmarking Hub0.46119 on the scale
    3. MirrorCodeEpoch AI Benchmarking Hub0.33119 on the scale
    4. FrontierMath-Tier-4-v2-PrivateEpoch AI Benchmarking Hub0.27116 on the scale
    5. SimpleQA VerifiedEpoch AI Benchmarking Hub0.53115 on the scale
    6. FrontierMath-Tiers-1-3-v2-PrivateEpoch AI Benchmarking Hub0.65109 on the scale
    7. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.9994 on the scale
    8. GPQA diamondEpoch AI Benchmarking Hub0.9283 on the scale
  65. 065qwen/qwen3.8-max-0902xhigh113.5181

    8 columns on 1 board, hardest first are the whole evidence behind 113.51. Each is a door to the column and everything else scored on it.

    1. Furniture AssemblyEpoch AI Benchmarking Hub0.20120 on the scale
    2. Chess PuzzlesEpoch AI Benchmarking Hub0.37119 on the scale
    3. MirrorCodeEpoch AI Benchmarking Hub0.48119 on the scale
    4. FrontierMath-Tier-4-v2-PrivateEpoch AI Benchmarking Hub0.34116 on the scale
    5. SimpleQA VerifiedEpoch AI Benchmarking Hub0.47115 on the scale
    6. FrontierMath-Tiers-1-3-v2-PrivateEpoch AI Benchmarking Hub0.66109 on the scale
    7. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub194 on the scale
    8. GPQA diamondEpoch AI Benchmarking Hub0.9283 on the scale
  66. 066anthropic/claude-sonnet-5xhigh113.50272

    27 columns on 2 boards, hardest first are the whole evidence behind 113.50. Each is a door to the column and everything else scored on it.

    1. typescriptLiveBench50122 on the scale
    2. Chess PuzzlesEpoch AI Benchmarking Hub0.34119 on the scale
    3. tablejoinLiveBench42.44117 on the scale
    4. SimpleQA VerifiedEpoch AI Benchmarking Hub0.33115 on the scale
    5. pythonLiveBench60109 on the scale
    6. plot_unscramblingLiveBench53.41106 on the scale
    7. integrals_with_gameLiveBench88104 on the scale
    8. consecutive_eventsLiveBench74.74102 on the scale
    9. zebra_puzzleLiveBench88102 on the scale
    10. javascriptLiveBench68.1899 on the scale
    11. logic_with_navigationLiveBench8696 on the scale
    12. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.9594 on the scale
    13. simplifyLiveBench60.6592 on the scale
    14. connectionsLiveBench95.5091 on the scale
    15. theory_of_mindLiveBench80.7788 on the scale
    16. code_completionLiveBench78.2687 on the scale
    17. paraphraseLiveBench61.2586 on the scale
    18. summarizeLiveBench71.2285 on the scale
    19. GPQA diamondEpoch AI Benchmarking Hub0.9183 on the scale
    20. typosLiveBench7677 on the scale
    21. code_generationLiveBench83.1076 on the scale
    22. story_generationLiveBench62.3274 on the scale
    23. olympiadLiveBench90.6772 on the scale
    24. spatialLiveBench10053 on the scale
    25. AMPS_HardLiveBench9847 on the scale
    26. math_compLiveBench95.1042 on the scale
    27. tablereformatLiveBench98.0441 on the scale
  67. 067deepseek/deepseek-v4-flash-0731unstated113.47231

    23 columns on 1 board, hardest first are the whole evidence behind 113.47. Each is a door to the column and everything else scored on it.

    1. typescriptLiveBench26.67122 on the scale
    2. tablejoinLiveBench48.54117 on the scale
    3. pythonLiveBench50109 on the scale
    4. plot_unscramblingLiveBench58.19106 on the scale
    5. integrals_with_gameLiveBench65104 on the scale
    6. consecutive_eventsLiveBench89.44102 on the scale
    7. zebra_puzzleLiveBench100102 on the scale
    8. javascriptLiveBench63.6499 on the scale
    9. logic_with_navigationLiveBench7096 on the scale
    10. simplifyLiveBench58.3792 on the scale
    11. connectionsLiveBench97.3391 on the scale
    12. theory_of_mindLiveBench86.5488 on the scale
    13. code_completionLiveBench73.9187 on the scale
    14. paraphraseLiveBench61.7086 on the scale
    15. summarizeLiveBench71.5085 on the scale
    16. typosLiveBench8277 on the scale
    17. code_generationLiveBench76.0676 on the scale
    18. story_generationLiveBench70.5074 on the scale
    19. olympiadLiveBench89.0872 on the scale
    20. spatialLiveBench9053 on the scale
    21. AMPS_HardLiveBench9747 on the scale
    22. math_compLiveBench96.0842 on the scale
    23. tablereformatLiveBench10041 on the scale
  68. 068gpt-5.2-2025-12-11not in the catalogxhigh113.39111

    11 columns on 1 board, hardest first are the whole evidence behind 113.39. Each is a door to the column and everything else scored on it.

    1. EBR-benchEpoch AI Benchmarking Hub0.23123 on the scale
    2. FrontierMath-Tier-4-2025-07-01-PrivateEpoch AI Benchmarking Hub0.19120 on the scale
    3. Furniture AssemblyEpoch AI Benchmarking Hub0.38120 on the scale
    4. Chess PuzzlesEpoch AI Benchmarking Hub0.48119 on the scale
    5. MirrorCodeEpoch AI Benchmarking Hub0.32119 on the scale
    6. FrontierMath-Tier-4-v2-PrivateEpoch AI Benchmarking Hub0.32116 on the scale
    7. SimpleQA VerifiedEpoch AI Benchmarking Hub0.37115 on the scale
    8. FrontierMath-2025-02-28-PrivateEpoch AI Benchmarking Hub0.41115 on the scale
    9. FrontierMath-Tiers-1-3-v2-PrivateEpoch AI Benchmarking Hub0.67109 on the scale
    10. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.9694 on the scale
    11. GPQA diamondEpoch AI Benchmarking Hub0.9183 on the scale
  69. 069x-ai/grok-4.7xhigh113.32332

    33 columns on 2 boards, hardest first are the whole evidence behind 113.32. Each is a door to the column and everything else scored on it.

    1. FrontierMath-ErdosEpoch AI Benchmarking Hub0153 on the scale
    2. typescriptLiveBench43.33122 on the scale
    3. Mystery Game PuzzlesEpoch AI Benchmarking Hub0.29121 on the scale
    4. Furniture AssemblyEpoch AI Benchmarking Hub0.21120 on the scale
    5. Chess PuzzlesEpoch AI Benchmarking Hub0.41119 on the scale
    6. MirrorCodeEpoch AI Benchmarking Hub0.54119 on the scale
    7. tablejoinLiveBench44.92117 on the scale
    8. FrontierMath-Tier-4-v2-PrivateEpoch AI Benchmarking Hub0.17116 on the scale
    9. SimpleQA VerifiedEpoch AI Benchmarking Hub0.56115 on the scale
    10. pythonLiveBench55109 on the scale
    11. FrontierMath-Tiers-1-3-v2-PrivateEpoch AI Benchmarking Hub0.53109 on the scale
    12. plot_unscramblingLiveBench72.42106 on the scale
    13. integrals_with_gameLiveBench96104 on the scale
    14. consecutive_eventsLiveBench85.73102 on the scale
    15. zebra_puzzleLiveBench86102 on the scale
    16. javascriptLiveBench63.6499 on the scale
    17. logic_with_navigationLiveBench6696 on the scale
    18. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.9894 on the scale
    19. simplifyLiveBench69.9792 on the scale
    20. connectionsLiveBench9891 on the scale
    21. theory_of_mindLiveBench84.6188 on the scale
    22. code_completionLiveBench78.2687 on the scale
    23. paraphraseLiveBench78.0586 on the scale
    24. summarizeLiveBench78.1785 on the scale
    25. GPQA diamondEpoch AI Benchmarking Hub0.9383 on the scale
    26. typosLiveBench7077 on the scale
    27. code_generationLiveBench76.0676 on the scale
    28. story_generationLiveBench74.9274 on the scale
    29. olympiadLiveBench91.6572 on the scale
    30. spatialLiveBench9453 on the scale
    31. AMPS_HardLiveBench9847 on the scale
    32. math_compLiveBench97.0642 on the scale
    33. tablereformatLiveBench10041 on the scale
  70. 070claude-opus-4-7not in the catalogxhigh113.14312

    31 columns on 2 boards, hardest first are the whole evidence behind 113.14. Each is a door to the column and everything else scored on it.

    1. typescriptLiveBench43.33122 on the scale
    2. FrontierMath-Tier-4-2025-07-01-PrivateEpoch AI Benchmarking Hub0.23120 on the scale
    3. Chess PuzzlesEpoch AI Benchmarking Hub0.36119 on the scale
    4. tablejoinLiveBench47.23117 on the scale
    5. FrontierMath-Tier-4-2025-07-01-PublicEpoch AI Benchmarking Hub0116 on the scale
    6. SimpleQA VerifiedEpoch AI Benchmarking Hub0.52115 on the scale
    7. FrontierMath-2025-02-28-PrivateEpoch AI Benchmarking Hub0.44115 on the scale
    8. pythonLiveBench45109 on the scale
    9. FrontierMath-2025-02-28-PublicEpoch AI Benchmarking Hub0.90106 on the scale
    10. plot_unscramblingLiveBench61.41106 on the scale
    11. integrals_with_gameLiveBench84104 on the scale
    12. consecutive_eventsLiveBench89.52102 on the scale
    13. zebra_puzzleLiveBench98102 on the scale
    14. javascriptLiveBench63.6499 on the scale
    15. logic_with_navigationLiveBench7096 on the scale
    16. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.9894 on the scale
    17. simplifyLiveBench65.5092 on the scale
    18. connectionsLiveBench92.3391 on the scale
    19. theory_of_mindLiveBench80.7788 on the scale
    20. code_completionLiveBench78.2687 on the scale
    21. paraphraseLiveBench65.7786 on the scale
    22. summarizeLiveBench66.2885 on the scale
    23. GPQA diamondEpoch AI Benchmarking Hub0.9083 on the scale
    24. typosLiveBench8077 on the scale
    25. code_generationLiveBench85.9276 on the scale
    26. story_generationLiveBench69.4074 on the scale
    27. olympiadLiveBench91.3872 on the scale
    28. spatialLiveBench10053 on the scale
    29. AMPS_HardLiveBench9847 on the scale
    30. math_compLiveBench98.0442 on the scale
    31. tablereformatLiveBench98.0441 on the scale
  71. 071qwen3.8-flash-nextnot in the catalogunstated113.12231

    23 columns on 1 board, hardest first are the whole evidence behind 113.12. Each is a door to the column and everything else scored on it.

    1. typescriptLiveBench46.67122 on the scale
    2. tablejoinLiveBench51.02117 on the scale
    3. pythonLiveBench70109 on the scale
    4. plot_unscramblingLiveBench55.76106 on the scale
    5. integrals_with_gameLiveBench59104 on the scale
    6. consecutive_eventsLiveBench75.62102 on the scale
    7. zebra_puzzleLiveBench98.75102 on the scale
    8. javascriptLiveBench68.1899 on the scale
    9. logic_with_navigationLiveBench7096 on the scale
    10. simplifyLiveBench70.2592 on the scale
    11. connectionsLiveBench90.1791 on the scale
    12. theory_of_mindLiveBench80.7788 on the scale
    13. code_completionLiveBench76.0987 on the scale
    14. paraphraseLiveBench79.4786 on the scale
    15. summarizeLiveBench77.3585 on the scale
    16. typosLiveBench7877 on the scale
    17. code_generationLiveBench69.0176 on the scale
    18. story_generationLiveBench81.3774 on the scale
    19. olympiadLiveBench91.1772 on the scale
    20. spatialLiveBench10053 on the scale
    21. AMPS_HardLiveBench9947 on the scale
    22. math_compLiveBench94.1242 on the scale
    23. tablereformatLiveBench96.0841 on the scale
  72. 072claude-opus-4-6-thinking-autonot in the cataloghigh113.04231

    23 columns on 1 board, hardest first are the whole evidence behind 113.04. Each is a door to the column and everything else scored on it.

    1. typescriptLiveBench33.33122 on the scale
    2. tablejoinLiveBench48.17117 on the scale
    3. pythonLiveBench50109 on the scale
    4. plot_unscramblingLiveBench66.48106 on the scale
    5. integrals_with_gameLiveBench73104 on the scale
    6. consecutive_eventsLiveBench63.47102 on the scale
    7. zebra_puzzleLiveBench94102 on the scale
    8. javascriptLiveBench63.6499 on the scale
    9. logic_with_navigationLiveBench8096 on the scale
    10. simplifyLiveBench59.1592 on the scale
    11. connectionsLiveBench99.3391 on the scale
    12. theory_of_mindLiveBench82.6988 on the scale
    13. code_completionLiveBench76.0987 on the scale
    14. paraphraseLiveBench62.8286 on the scale
    15. summarizeLiveBench65.1585 on the scale
    16. typosLiveBench8477 on the scale
    17. code_generationLiveBench80.2876 on the scale
    18. story_generationLiveBench66.1374 on the scale
    19. olympiadLiveBench92.1772 on the scale
    20. spatialLiveBench9853 on the scale
    21. AMPS_HardLiveBench9747 on the scale
    22. math_compLiveBench95.1042 on the scale
    23. tablereformatLiveBench98.0441 on the scale
  73. 073claude-opus-4-7not in the catalogmax113.03101

    10 columns on 1 board, hardest first are the whole evidence behind 113.03. Each is a door to the column and everything else scored on it.

    1. EBR-benchEpoch AI Benchmarking Hub0.19123 on the scale
    2. Mystery Game PuzzlesEpoch AI Benchmarking Hub0.28121 on the scale
    3. Furniture AssemblyEpoch AI Benchmarking Hub0.33120 on the scale
    4. Chess PuzzlesEpoch AI Benchmarking Hub0.41119 on the scale
    5. MirrorCodeEpoch AI Benchmarking Hub0.43119 on the scale
    6. FrontierMath-Tier-4-v2-PrivateEpoch AI Benchmarking Hub0.32116 on the scale
    7. FrontierMath-Tiers-1-3-v2-PrivateEpoch AI Benchmarking Hub0.70109 on the scale
    8. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.8794 on the scale
    9. SWE-Bench verifiedEpoch AI Benchmarking Hub0.8384 on the scale
    10. GPQA diamondEpoch AI Benchmarking Hub0.8683 on the scale
  74. 074z-ai/glm-5.3unstated112.92231

    23 columns on 1 board, hardest first are the whole evidence behind 112.92. Each is a door to the column and everything else scored on it.

    1. typescriptLiveBench50122 on the scale
    2. tablejoinLiveBench42.35117 on the scale
    3. pythonLiveBench60109 on the scale
    4. plot_unscramblingLiveBench60.24106 on the scale
    5. integrals_with_gameLiveBench69104 on the scale
    6. consecutive_eventsLiveBench72.31102 on the scale
    7. zebra_puzzleLiveBench88.75102 on the scale
    8. javascriptLiveBench72.7399 on the scale
    9. logic_with_navigationLiveBench7096 on the scale
    10. simplifyLiveBench65.8592 on the scale
    11. connectionsLiveBench95.3391 on the scale
    12. theory_of_mindLiveBench88.4688 on the scale
    13. code_completionLiveBench80.4487 on the scale
    14. paraphraseLiveBench64.6886 on the scale
    15. summarizeLiveBench74.5585 on the scale
    16. typosLiveBench8477 on the scale
    17. code_generationLiveBench77.4776 on the scale
    18. story_generationLiveBench72.1374 on the scale
    19. olympiadLiveBench87.5172 on the scale
    20. spatialLiveBench9653 on the scale
    21. AMPS_HardLiveBench9947 on the scale
    22. math_compLiveBench96.0842 on the scale
    23. tablereformatLiveBench96.0841 on the scale
  75. 075claude-haiku-5-5not in the catalogxhigh112.88242

    24 columns on 2 boards, hardest first are the whole evidence behind 112.88. Each is a door to the column and everything else scored on it.

    1. typescriptLiveBench40122 on the scale
    2. tablejoinLiveBench49.17117 on the scale
    3. pythonLiveBench55109 on the scale
    4. plot_unscramblingLiveBench42.72106 on the scale
    5. integrals_with_gameLiveBench89104 on the scale
    6. consecutive_eventsLiveBench71.05102 on the scale
    7. zebra_puzzleLiveBench98102 on the scale
    8. javascriptLiveBench59.0999 on the scale
    9. logic_with_navigationLiveBench5696 on the scale
    10. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.9994 on the scale
    11. simplifyLiveBench62.7892 on the scale
    12. connectionsLiveBench93.8391 on the scale
    13. theory_of_mindLiveBench76.9288 on the scale
    14. code_completionLiveBench73.9187 on the scale
    15. paraphraseLiveBench62.5086 on the scale
    16. summarizeLiveBench66.9885 on the scale
    17. typosLiveBench5477 on the scale
    18. code_generationLiveBench78.8776 on the scale
    19. story_generationLiveBench73.6074 on the scale
    20. olympiadLiveBench86.9572 on the scale
    21. spatialLiveBench9453 on the scale
    22. AMPS_HardLiveBench9847 on the scale
    23. math_compLiveBench97.0642 on the scale
    24. tablereformatLiveBench98.0441 on the scale
  76. 076qwen/qwen3.8-27bunstated112.72231

    23 columns on 1 board, hardest first are the whole evidence behind 112.72. Each is a door to the column and everything else scored on it.

    1. typescriptLiveBench50122 on the scale
    2. tablejoinLiveBench48.75117 on the scale
    3. pythonLiveBench75109 on the scale
    4. plot_unscramblingLiveBench56.54106 on the scale
    5. integrals_with_gameLiveBench65104 on the scale
    6. consecutive_eventsLiveBench84.93102 on the scale
    7. zebra_puzzleLiveBench96.50102 on the scale
    8. javascriptLiveBench59.0999 on the scale
    9. logic_with_navigationLiveBench6896 on the scale
    10. simplifyLiveBench66.7092 on the scale
    11. connectionsLiveBench90.5091 on the scale
    12. theory_of_mindLiveBench59.6288 on the scale
    13. code_completionLiveBench73.9187 on the scale
    14. paraphraseLiveBench74.9086 on the scale
    15. summarizeLiveBench75.9385 on the scale
    16. typosLiveBench7677 on the scale
    17. code_generationLiveBench77.4776 on the scale
    18. story_generationLiveBench73.1074 on the scale
    19. olympiadLiveBench87.7372 on the scale
    20. spatialLiveBench9653 on the scale
    21. AMPS_HardLiveBench9847 on the scale
    22. math_compLiveBench94.1242 on the scale
    23. tablereformatLiveBench96.0841 on the scale
  77. 077z-ai/glm-5.3max112.5471

    7 columns on 1 board, hardest first are the whole evidence behind 112.54. Each is a door to the column and everything else scored on it.

    1. Mystery Game PuzzlesEpoch AI Benchmarking Hub0.33121 on the scale
    2. Chess PuzzlesEpoch AI Benchmarking Hub0.37119 on the scale
    3. FrontierMath-Tier-4-v2-PrivateEpoch AI Benchmarking Hub0.29116 on the scale
    4. SimpleQA VerifiedEpoch AI Benchmarking Hub0.41115 on the scale
    5. FrontierMath-Tiers-1-3-v2-PrivateEpoch AI Benchmarking Hub0.69109 on the scale
    6. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.9194 on the scale
    7. GPQA diamondEpoch AI Benchmarking Hub0.9183 on the scale
  78. 078anthropic/claude-sonnet-5max112.4381

    8 columns on 1 board, hardest first are the whole evidence behind 112.43. Each is a door to the column and everything else scored on it.

    1. Mystery Game PuzzlesEpoch AI Benchmarking Hub0.35121 on the scale
    2. Chess PuzzlesEpoch AI Benchmarking Hub0.45119 on the scale
    3. MirrorCodeEpoch AI Benchmarking Hub0.63119 on the scale
    4. FrontierMath-Tier-4-v2-PrivateEpoch AI Benchmarking Hub0.29116 on the scale
    5. SimpleQA VerifiedEpoch AI Benchmarking Hub0.34115 on the scale
    6. FrontierMath-Tiers-1-3-v2-PrivateEpoch AI Benchmarking Hub0.66109 on the scale
    7. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.8094 on the scale
    8. GPQA diamondEpoch AI Benchmarking Hub0.8083 on the scale
  79. 079moonshotai/kimi-k3high112.2031

    3 columns on 1 board, hardest first are the whole evidence behind 112.20. Each is a door to the column and everything else scored on it.

    1. Chess PuzzlesEpoch AI Benchmarking Hub0.37119 on the scale
    2. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.9394 on the scale
    3. GPQA diamondEpoch AI Benchmarking Hub0.9283 on the scale
  80. 080gpt-5.4-2026-03-05not in the catalogmedium112.0441

    4 columns on 1 board, hardest first are the whole evidence behind 112.04. Each is a door to the column and everything else scored on it.

    1. Mystery Game PuzzlesEpoch AI Benchmarking Hub0.28121 on the scale
    2. Chess PuzzlesEpoch AI Benchmarking Hub0.37119 on the scale
    3. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.9694 on the scale
    4. GPQA diamondEpoch AI Benchmarking Hub0.8983 on the scale
  81. 081claude-opus-4-6-64knot in the catalogunstated111.9261

    6 columns on 1 board, hardest first are the whole evidence behind 111.92. Each is a door to the column and everything else scored on it.

    1. FrontierMath-Tier-4-2025-07-01-PrivateEpoch AI Benchmarking Hub0.21120 on the scale
    2. FrontierMath-Tier-4-2025-07-01-PublicEpoch AI Benchmarking Hub0116 on the scale
    3. FrontierMath-2025-02-28-PrivateEpoch AI Benchmarking Hub0.40115 on the scale
    4. FrontierMath-2025-02-28-PublicEpoch AI Benchmarking Hub0.90106 on the scale
    5. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.9494 on the scale
    6. GPQA diamondEpoch AI Benchmarking Hub0.8983 on the scale
  82. 082claude-opus-4-6not in the catalogmax111.69141

    14 columns on 1 board, hardest first are the whole evidence behind 111.69. Each is a door to the column and everything else scored on it.

    1. EBR-benchEpoch AI Benchmarking Hub0.13123 on the scale
    2. Mystery Game PuzzlesEpoch AI Benchmarking Hub0.25121 on the scale
    3. FrontierMath-Tier-4-2025-07-01-PrivateEpoch AI Benchmarking Hub0.23120 on the scale
    4. Furniture AssemblyEpoch AI Benchmarking Hub0.28120 on the scale
    5. Chess PuzzlesEpoch AI Benchmarking Hub0.21119 on the scale
    6. MirrorCodeEpoch AI Benchmarking Hub0.33119 on the scale
    7. FrontierMath-Tier-4-2025-07-01-PublicEpoch AI Benchmarking Hub0116 on the scale
    8. FrontierMath-Tier-4-v2-PrivateEpoch AI Benchmarking Hub0.27116 on the scale
    9. SimpleQA VerifiedEpoch AI Benchmarking Hub0.47115 on the scale
    10. FrontierMath-2025-02-28-PrivateEpoch AI Benchmarking Hub0.41115 on the scale
    11. FrontierMath-Tiers-1-3-v2-PrivateEpoch AI Benchmarking Hub0.66109 on the scale
    12. FrontierMath-2025-02-28-PublicEpoch AI Benchmarking Hub0.90106 on the scale
    13. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.9194 on the scale
    14. GPQA diamondEpoch AI Benchmarking Hub0.8883 on the scale
  83. 083google/gemini-3.1-pro-previewunstated111.6691

    9 columns on 1 board, hardest first are the whole evidence behind 111.66. Each is a door to the column and everything else scored on it.

    1. EBR-benchEpoch AI Benchmarking Hub0.14123 on the scale
    2. FrontierMath-Tier-4-2025-07-01-PrivateEpoch AI Benchmarking Hub0.17120 on the scale
    3. FrontierMath-Tier-4-2025-07-01-PublicEpoch AI Benchmarking Hub0116 on the scale
    4. FrontierMath-Tier-4-v2-PrivateEpoch AI Benchmarking Hub0.27116 on the scale
    5. FrontierMath-2025-02-28-PrivateEpoch AI Benchmarking Hub0.37115 on the scale
    6. FrontierMath-Tiers-1-3-v2-PrivateEpoch AI Benchmarking Hub0.60109 on the scale
    7. FrontierMath-2025-02-28-PublicEpoch AI Benchmarking Hub0.89106 on the scale
    8. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.9694 on the scale
    9. GPQA diamondEpoch AI Benchmarking Hub0.9483 on the scale
  84. 084deepseek/deepseek-v4-prounstated111.64231

    23 columns on 1 board, hardest first are the whole evidence behind 111.64. Each is a door to the column and everything else scored on it.

    1. typescriptLiveBench23.33122 on the scale
    2. tablejoinLiveBench48.19117 on the scale
    3. pythonLiveBench50109 on the scale
    4. plot_unscramblingLiveBench56.39106 on the scale
    5. integrals_with_gameLiveBench78104 on the scale
    6. consecutive_eventsLiveBench75.42102 on the scale
    7. zebra_puzzleLiveBench92102 on the scale
    8. javascriptLiveBench54.5599 on the scale
    9. logic_with_navigationLiveBench6496 on the scale
    10. simplifyLiveBench55.9392 on the scale
    11. connectionsLiveBench9891 on the scale
    12. theory_of_mindLiveBench80.7788 on the scale
    13. code_completionLiveBench69.5687 on the scale
    14. paraphraseLiveBench56.2286 on the scale
    15. summarizeLiveBench69.5085 on the scale
    16. typosLiveBench8077 on the scale
    17. code_generationLiveBench70.4276 on the scale
    18. story_generationLiveBench67.7574 on the scale
    19. olympiadLiveBench90.6272 on the scale
    20. spatialLiveBench9453 on the scale
    21. AMPS_HardLiveBench9847 on the scale
    22. math_compLiveBench96.0842 on the scale
    23. tablereformatLiveBench10041 on the scale
  85. 085x-ai/grok-4.5high111.5581

    8 columns on 1 board, hardest first are the whole evidence behind 111.55. Each is a door to the column and everything else scored on it.

    1. Furniture AssemblyEpoch AI Benchmarking Hub0.23120 on the scale
    2. Chess PuzzlesEpoch AI Benchmarking Hub0.35119 on the scale
    3. MirrorCodeEpoch AI Benchmarking Hub0.32119 on the scale
    4. FrontierMath-Tier-4-v2-PrivateEpoch AI Benchmarking Hub0.24116 on the scale
    5. SimpleQA VerifiedEpoch AI Benchmarking Hub0.48115 on the scale
    6. FrontierMath-Tiers-1-3-v2-PrivateEpoch AI Benchmarking Hub0.57109 on the scale
    7. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.9894 on the scale
    8. GPQA diamondEpoch AI Benchmarking Hub0.9383 on the scale
  86. 086claude-opus-4-8not in the cataloglow111.5431

    3 columns on 1 board, hardest first are the whole evidence behind 111.54. Each is a door to the column and everything else scored on it.

    1. Chess PuzzlesEpoch AI Benchmarking Hub0.29119 on the scale
    2. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.9894 on the scale
    3. GPQA diamondEpoch AI Benchmarking Hub0.8883 on the scale
  87. 087deepseek/deepseek-v4-flash-0731max111.1471

    7 columns on 1 board, hardest first are the whole evidence behind 111.14. Each is a door to the column and everything else scored on it.

    1. Mystery Game PuzzlesEpoch AI Benchmarking Hub0.34121 on the scale
    2. Chess PuzzlesEpoch AI Benchmarking Hub0.32119 on the scale
    3. FrontierMath-Tier-4-v2-PrivateEpoch AI Benchmarking Hub0.24116 on the scale
    4. SimpleQA VerifiedEpoch AI Benchmarking Hub0.34115 on the scale
    5. FrontierMath-Tiers-1-3-v2-PrivateEpoch AI Benchmarking Hub0.58109 on the scale
    6. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.9494 on the scale
    7. GPQA diamondEpoch AI Benchmarking Hub0.9183 on the scale
  88. 088google/gemini-3.5-flashhigh111.12382

    38 columns on 2 boards, hardest first are the whole evidence behind 111.12. Each is a door to the column and everything else scored on it.

    1. OEIS OpenEpoch AI Benchmarking Hub0.22127 on the scale
    2. EBR-benchEpoch AI Benchmarking Hub0.05123 on the scale
    3. OEIS Open LiteEpoch AI Benchmarking Hub0.29122 on the scale
    4. typescriptLiveBench33.33122 on the scale
    5. Mystery Game PuzzlesEpoch AI Benchmarking Hub0.32121 on the scale
    6. FrontierMath-Tier-4-2025-07-01-PrivateEpoch AI Benchmarking Hub0.15120 on the scale
    7. Chess PuzzlesEpoch AI Benchmarking Hub0.45119 on the scale
    8. tablejoinLiveBench50.50117 on the scale
    9. FrontierMath-Tier-4-2025-07-01-PublicEpoch AI Benchmarking Hub0116 on the scale
    10. FrontierMath-Tier-4-v2-PrivateEpoch AI Benchmarking Hub0.27116 on the scale
    11. SimpleQA VerifiedEpoch AI Benchmarking Hub0.66115 on the scale
    12. FrontierMath-2025-02-28-PrivateEpoch AI Benchmarking Hub0.39115 on the scale
    13. pythonLiveBench50109 on the scale
    14. FrontierMath-Tiers-1-3-v2-PrivateEpoch AI Benchmarking Hub0.63109 on the scale
    15. FrontierMath-2025-02-28-PublicEpoch AI Benchmarking Hub0.80106 on the scale
    16. plot_unscramblingLiveBench67.75106 on the scale
    17. integrals_with_gameLiveBench68104 on the scale
    18. consecutive_eventsLiveBench47.99102 on the scale
    19. zebra_puzzleLiveBench77.25102 on the scale
    20. javascriptLiveBench63.6499 on the scale
    21. logic_with_navigationLiveBench7496 on the scale
    22. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.9694 on the scale
    23. simplifyLiveBench69.1092 on the scale
    24. connectionsLiveBench10091 on the scale
    25. theory_of_mindLiveBench80.7788 on the scale
    26. code_completionLiveBench76.0987 on the scale
    27. paraphraseLiveBench75.5286 on the scale
    28. summarizeLiveBench82.5885 on the scale
    29. SWE-Bench verifiedEpoch AI Benchmarking Hub0.7984 on the scale
    30. GPQA diamondEpoch AI Benchmarking Hub0.9383 on the scale
    31. typosLiveBench8677 on the scale
    32. code_generationLiveBench80.2876 on the scale
    33. story_generationLiveBench75.2074 on the scale
    34. olympiadLiveBench91.8872 on the scale
    35. spatialLiveBench9653 on the scale
    36. AMPS_HardLiveBench9847 on the scale
    37. math_compLiveBench95.1042 on the scale
    38. tablereformatLiveBench96.0841 on the scale
  89. 089qwen/qwen3.7-maxunstated111.06322

    32 columns on 2 boards, hardest first are the whole evidence behind 111.06. Each is a door to the column and everything else scored on it.

    1. EBR-benchEpoch AI Benchmarking Hub0.10123 on the scale
    2. typescriptLiveBench26.67122 on the scale
    3. Mystery Game PuzzlesEpoch AI Benchmarking Hub0.32121 on the scale
    4. Chess PuzzlesEpoch AI Benchmarking Hub0.27119 on the scale
    5. tablejoinLiveBench45.52117 on the scale
    6. FrontierMath-Tier-4-v2-PrivateEpoch AI Benchmarking Hub0.34116 on the scale
    7. SimpleQA VerifiedEpoch AI Benchmarking Hub0.56115 on the scale
    8. pythonLiveBench45109 on the scale
    9. FrontierMath-Tiers-1-3-v2-PrivateEpoch AI Benchmarking Hub0.65109 on the scale
    10. plot_unscramblingLiveBench58.72106 on the scale
    11. integrals_with_gameLiveBench59104 on the scale
    12. consecutive_eventsLiveBench71.80102 on the scale
    13. zebra_puzzleLiveBench74.50102 on the scale
    14. javascriptLiveBench59.0999 on the scale
    15. logic_with_navigationLiveBench8496 on the scale
    16. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.9694 on the scale
    17. simplifyLiveBench64.0892 on the scale
    18. connectionsLiveBench96.5091 on the scale
    19. theory_of_mindLiveBench78.8588 on the scale
    20. code_completionLiveBench69.5687 on the scale
    21. paraphraseLiveBench7286 on the scale
    22. summarizeLiveBench83.8085 on the scale
    23. SWE-Bench verifiedEpoch AI Benchmarking Hub0.7784 on the scale
    24. GPQA diamondEpoch AI Benchmarking Hub0.9183 on the scale
    25. typosLiveBench8477 on the scale
    26. code_generationLiveBench78.8776 on the scale
    27. story_generationLiveBench76.2874 on the scale
    28. olympiadLiveBench86.9372 on the scale
    29. spatialLiveBench9653 on the scale
    30. AMPS_HardLiveBench9847 on the scale
    31. math_compLiveBench97.0642 on the scale
    32. tablereformatLiveBench98.0441 on the scale
  90. 090claude-opus-4-6-32knot in the catalogunstated111.0361

    6 columns on 1 board, hardest first are the whole evidence behind 111.03. Each is a door to the column and everything else scored on it.

    1. FrontierMath-Tier-4-2025-07-01-PrivateEpoch AI Benchmarking Hub0.21120 on the scale
    2. FrontierMath-Tier-4-2025-07-01-PublicEpoch AI Benchmarking Hub0116 on the scale
    3. FrontierMath-2025-02-28-PrivateEpoch AI Benchmarking Hub0.40115 on the scale
    4. FrontierMath-2025-02-28-PublicEpoch AI Benchmarking Hub0.80106 on the scale
    5. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.9394 on the scale
    6. GPQA diamondEpoch AI Benchmarking Hub0.9183 on the scale
  91. 091google/gemini-3.6-flashhigh110.95322

    32 columns on 2 boards, hardest first are the whole evidence behind 110.95. Each is a door to the column and everything else scored on it.

    1. typescriptLiveBench26.67122 on the scale
    2. Mystery Game PuzzlesEpoch AI Benchmarking Hub0.30121 on the scale
    3. Furniture AssemblyEpoch AI Benchmarking Hub0.23120 on the scale
    4. Chess PuzzlesEpoch AI Benchmarking Hub0.40119 on the scale
    5. MirrorCodeEpoch AI Benchmarking Hub0.23119 on the scale
    6. tablejoinLiveBench47.13117 on the scale
    7. FrontierMath-Tier-4-v2-PrivateEpoch AI Benchmarking Hub0.22116 on the scale
    8. SimpleQA VerifiedEpoch AI Benchmarking Hub0.66115 on the scale
    9. pythonLiveBench40109 on the scale
    10. FrontierMath-Tiers-1-3-v2-PrivateEpoch AI Benchmarking Hub0.59109 on the scale
    11. plot_unscramblingLiveBench63.69106 on the scale
    12. integrals_with_gameLiveBench63104 on the scale
    13. consecutive_eventsLiveBench43.82102 on the scale
    14. zebra_puzzleLiveBench85.75102 on the scale
    15. javascriptLiveBench63.6499 on the scale
    16. logic_with_navigationLiveBench7696 on the scale
    17. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.9494 on the scale
    18. simplifyLiveBench75.7092 on the scale
    19. connectionsLiveBench10091 on the scale
    20. theory_of_mindLiveBench78.8588 on the scale
    21. code_completionLiveBench78.2687 on the scale
    22. paraphraseLiveBench74.3286 on the scale
    23. summarizeLiveBench75.8585 on the scale
    24. GPQA diamondEpoch AI Benchmarking Hub0.9483 on the scale
    25. typosLiveBench8877 on the scale
    26. code_generationLiveBench77.4776 on the scale
    27. story_generationLiveBench75.6074 on the scale
    28. olympiadLiveBench90.4972 on the scale
    29. spatialLiveBench10053 on the scale
    30. AMPS_HardLiveBench9847 on the scale
    31. math_compLiveBench94.1242 on the scale
    32. tablereformatLiveBench98.0441 on the scale
  92. 092openai/gpt-5.6-sollow110.8541

    4 columns on 1 board, hardest first are the whole evidence behind 110.85. Each is a door to the column and everything else scored on it.

    1. Mystery Game PuzzlesEpoch AI Benchmarking Hub0.26121 on the scale
    2. Chess PuzzlesEpoch AI Benchmarking Hub0.31119 on the scale
    3. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.9694 on the scale
    4. GPQA diamondEpoch AI Benchmarking Hub0.9083 on the scale
  93. 093google/gemini-3.5-flashlow110.8341

    4 columns on 1 board, hardest first are the whole evidence behind 110.83. Each is a door to the column and everything else scored on it.

    1. Mystery Game PuzzlesEpoch AI Benchmarking Hub0.28121 on the scale
    2. Chess PuzzlesEpoch AI Benchmarking Hub0.42119 on the scale
    3. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.8994 on the scale
    4. GPQA diamondEpoch AI Benchmarking Hub0.8983 on the scale
  94. 094moonshotai/kimi-k2.6unstated110.82131

    13 columns on 1 board, hardest first are the whole evidence behind 110.82. Each is a door to the column and everything else scored on it.

    1. EBR-benchEpoch AI Benchmarking Hub0.02123 on the scale
    2. Mystery Game PuzzlesEpoch AI Benchmarking Hub0.18121 on the scale
    3. FrontierMath-Tier-4-2025-07-01-PrivateEpoch AI Benchmarking Hub0.15120 on the scale
    4. Furniture AssemblyEpoch AI Benchmarking Hub0.22120 on the scale
    5. Chess PuzzlesEpoch AI Benchmarking Hub0.20119 on the scale
    6. FrontierMath-Tier-4-v2-PrivateEpoch AI Benchmarking Hub0.26116 on the scale
    7. SimpleQA VerifiedEpoch AI Benchmarking Hub0.35115 on the scale
    8. FrontierMath-2025-02-28-PrivateEpoch AI Benchmarking Hub0.39115 on the scale
    9. FrontierMath-Tiers-1-3-v2-PrivateEpoch AI Benchmarking Hub0.57109 on the scale
    10. FrontierMath-2025-02-28-PublicEpoch AI Benchmarking Hub0.90106 on the scale
    11. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.9694 on the scale
    12. SWE-Bench verifiedEpoch AI Benchmarking Hub0.7784 on the scale
    13. GPQA diamondEpoch AI Benchmarking Hub0.9183 on the scale
  95. 095mistral-large-4-0-ossnot in the cataloghigh110.7871

    7 columns on 1 board, hardest first are the whole evidence behind 110.78. Each is a door to the column and everything else scored on it.

    1. EBR-benchEpoch AI Benchmarking Hub0.18123 on the scale
    2. Mystery Game PuzzlesEpoch AI Benchmarking Hub0.20121 on the scale
    3. Furniture AssemblyEpoch AI Benchmarking Hub0.31120 on the scale
    4. Chess PuzzlesEpoch AI Benchmarking Hub0.29119 on the scale
    5. SimpleQA VerifiedEpoch AI Benchmarking Hub0.22115 on the scale
    6. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.9994 on the scale
    7. GPQA diamondEpoch AI Benchmarking Hub0.9083 on the scale
  96. 097gemini-3-pro-previewnot in the catalogunstated110.7471

    7 columns on 1 board, hardest first are the whole evidence behind 110.74. Each is a door to the column and everything else scored on it.

    1. FrontierMath-Tier-4-2025-07-01-PrivateEpoch AI Benchmarking Hub0.19120 on the scale
    2. FrontierMath-Tier-4-2025-07-01-PublicEpoch AI Benchmarking Hub0116 on the scale
    3. FrontierMath-2025-02-28-PrivateEpoch AI Benchmarking Hub0.38115 on the scale
    4. FrontierMath-2025-02-28-PublicEpoch AI Benchmarking Hub0.80106 on the scale
    5. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.9194 on the scale
    6. SWE-Bench verifiedEpoch AI Benchmarking Hub0.7384 on the scale
    7. GPQA diamondEpoch AI Benchmarking Hub0.9383 on the scale
  97. 096gpt-5.2-2025-12-11not in the cataloghigh110.74332

    33 columns on 2 boards, hardest first are the whole evidence behind 110.74. Each is a door to the column and everything else scored on it.

    1. typescriptLiveBench36.67122 on the scale
    2. Mystery Game PuzzlesEpoch AI Benchmarking Hub0.23121 on the scale
    3. FrontierMath-Tier-4-2025-07-01-PrivateEpoch AI Benchmarking Hub0.19120 on the scale
    4. Chess PuzzlesEpoch AI Benchmarking Hub0.45119 on the scale
    5. tablejoinLiveBench45.58117 on the scale
    6. FrontierMath-Tier-4-2025-07-01-PublicEpoch AI Benchmarking Hub0116 on the scale
    7. SimpleQA VerifiedEpoch AI Benchmarking Hub0.34115 on the scale
    8. FrontierMath-2025-02-28-PrivateEpoch AI Benchmarking Hub0.40115 on the scale
    9. pythonLiveBench55109 on the scale
    10. FrontierMath-2025-02-28-PublicEpoch AI Benchmarking Hub0.60106 on the scale
    11. plot_unscramblingLiveBench58.43106 on the scale
    12. integrals_with_gameLiveBench92104 on the scale
    13. consecutive_eventsLiveBench88.91102 on the scale
    14. zebra_puzzleLiveBench84102 on the scale
    15. javascriptLiveBench59.0999 on the scale
    16. logic_with_navigationLiveBench7496 on the scale
    17. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.9694 on the scale
    18. simplifyLiveBench54.0892 on the scale
    19. connectionsLiveBench9991 on the scale
    20. theory_of_mindLiveBench78.8588 on the scale
    21. code_completionLiveBench76.0987 on the scale
    22. paraphraseLiveBench64.1086 on the scale
    23. summarizeLiveBench63.2085 on the scale
    24. SWE-Bench verifiedEpoch AI Benchmarking Hub0.7484 on the scale
    25. GPQA diamondEpoch AI Benchmarking Hub0.8883 on the scale
    26. typosLiveBench8277 on the scale
    27. code_generationLiveBench76.0676 on the scale
    28. story_generationLiveBench65.7074 on the scale
    29. olympiadLiveBench88.5772 on the scale
    30. spatialLiveBench9653 on the scale
    31. AMPS_HardLiveBench9747 on the scale
    32. math_compLiveBench95.1042 on the scale
    33. tablereformatLiveBench10041 on the scale
  98. 098claude-opus-4-5-20251101-thinking-64knot in the cataloghigh110.65231

    23 columns on 1 board, hardest first are the whole evidence behind 110.65. Each is a door to the column and everything else scored on it.

    1. typescriptLiveBench20122 on the scale
    2. tablejoinLiveBench45.92117 on the scale
    3. pythonLiveBench40109 on the scale
    4. plot_unscramblingLiveBench66.45106 on the scale
    5. integrals_with_gameLiveBench78104 on the scale
    6. consecutive_eventsLiveBench79.36102 on the scale
    7. zebra_puzzleLiveBench77.50102 on the scale
    8. javascriptLiveBench59.0999 on the scale
    9. logic_with_navigationLiveBench6896 on the scale
    10. simplifyLiveBench54.9592 on the scale
    11. connectionsLiveBench99.3391 on the scale
    12. theory_of_mindLiveBench78.8588 on the scale
    13. code_completionLiveBench80.4487 on the scale
    14. paraphraseLiveBench65.6786 on the scale
    15. summarizeLiveBench63.7285 on the scale
    16. typosLiveBench7877 on the scale
    17. code_generationLiveBench78.8776 on the scale
    18. story_generationLiveBench65.8574 on the scale
    19. olympiadLiveBench89.4672 on the scale
    20. spatialLiveBench9653 on the scale
    21. AMPS_HardLiveBench9947 on the scale
    22. math_compLiveBench95.1042 on the scale
    23. tablereformatLiveBench98.0441 on the scale
  99. 099mistralai/mistral-large-4-0high110.6391

    9 columns on 1 board, hardest first are the whole evidence behind 110.63. Each is a door to the column and everything else scored on it.

    1. Mystery Game PuzzlesEpoch AI Benchmarking Hub0.17121 on the scale
    2. Furniture AssemblyEpoch AI Benchmarking Hub0.21120 on the scale
    3. Chess PuzzlesEpoch AI Benchmarking Hub0.33119 on the scale
    4. MirrorCodeEpoch AI Benchmarking Hub0.40119 on the scale
    5. FrontierMath-Tier-4-v2-PrivateEpoch AI Benchmarking Hub0.27116 on the scale
    6. SimpleQA VerifiedEpoch AI Benchmarking Hub0.20115 on the scale
    7. FrontierMath-Tiers-1-3-v2-PrivateEpoch AI Benchmarking Hub0.59109 on the scale
    8. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.9894 on the scale
    9. GPQA diamondEpoch AI Benchmarking Hub0.8883 on the scale
  100. 100muse-sparknot in the catalogunstated110.4141

    4 columns on 1 board, hardest first are the whole evidence behind 110.41. Each is a door to the column and everything else scored on it.

    1. FrontierMath-Tier-4-2025-07-01-PrivateEpoch AI Benchmarking Hub0.15120 on the scale
    2. FrontierMath-2025-02-28-PrivateEpoch AI Benchmarking Hub0.39115 on the scale
    3. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.8994 on the scale
    4. GPQA diamondEpoch AI Benchmarking Hub0.9083 on the scale
  101. 101z-ai/glm-5.2max110.3391

    9 columns on 1 board, hardest first are the whole evidence behind 110.33. Each is a door to the column and everything else scored on it.

    1. EBR-benchEpoch AI Benchmarking Hub0.10123 on the scale
    2. Chess PuzzlesEpoch AI Benchmarking Hub0.22119 on the scale
    3. MirrorCodeEpoch AI Benchmarking Hub0.37119 on the scale
    4. FrontierMath-Tier-4-v2-PrivateEpoch AI Benchmarking Hub0.29116 on the scale
    5. SimpleQA VerifiedEpoch AI Benchmarking Hub0.34115 on the scale
    6. FrontierMath-Tiers-1-3-v2-PrivateEpoch AI Benchmarking Hub0.59109 on the scale
    7. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.8694 on the scale
    8. SWE-Bench verifiedEpoch AI Benchmarking Hub0.7984 on the scale
    9. GPQA diamondEpoch AI Benchmarking Hub0.9283 on the scale
  102. 102openai/gpt-5.4-nanoxhigh110.30231

    23 columns on 1 board, hardest first are the whole evidence behind 110.30. Each is a door to the column and everything else scored on it.

    1. typescriptLiveBench26.67122 on the scale
    2. tablejoinLiveBench50.59117 on the scale
    3. pythonLiveBench50109 on the scale
    4. plot_unscramblingLiveBench39.13106 on the scale
    5. integrals_with_gameLiveBench82.83104 on the scale
    6. consecutive_eventsLiveBench54.30102 on the scale
    7. zebra_puzzleLiveBench97.62102 on the scale
    8. javascriptLiveBench63.6499 on the scale
    9. logic_with_navigationLiveBench6496 on the scale
    10. simplifyLiveBench62.7592 on the scale
    11. connectionsLiveBench94.3991 on the scale
    12. theory_of_mindLiveBench80.7788 on the scale
    13. code_completionLiveBench67.3987 on the scale
    14. paraphraseLiveBench66.6586 on the scale
    15. summarizeLiveBench71.7785 on the scale
    16. typosLiveBench5477 on the scale
    17. code_generationLiveBench74.2976 on the scale
    18. story_generationLiveBench67.6574 on the scale
    19. olympiadLiveBench87.9872 on the scale
    20. spatialLiveBench8253 on the scale
    21. AMPS_HardLiveBench9847 on the scale
    22. math_compLiveBench95.1042 on the scale
    23. tablereformatLiveBench98.0441 on the scale
  103. 103anthropic/claude-fable-5low110.2031

    3 columns on 1 board, hardest first are the whole evidence behind 110.20. Each is a door to the column and everything else scored on it.

    1. Chess PuzzlesEpoch AI Benchmarking Hub0.31119 on the scale
    2. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.9894 on the scale
    3. GPQA diamondEpoch AI Benchmarking Hub0.7983 on the scale
  104. 104claude-opus-4-6not in the catalogunstated110.0841

    4 columns on 1 board, hardest first are the whole evidence behind 110.08. Each is a door to the column and everything else scored on it.

    1. Mystery Game PuzzlesEpoch AI Benchmarking Hub0.15121 on the scale
    2. FrontierMath-Tier-4-2025-07-01-PrivateEpoch AI Benchmarking Hub0.15120 on the scale
    3. FrontierMath-2025-02-28-PrivateEpoch AI Benchmarking Hub0.38115 on the scale
    4. SWE-Bench verifiedEpoch AI Benchmarking Hub0.7984 on the scale
  105. 105openai/gpt-5.2-codexunstated110.02231

    23 columns on 1 board, hardest first are the whole evidence behind 110.02. Each is a door to the column and everything else scored on it.

    1. typescriptLiveBench20122 on the scale
    2. tablejoinLiveBench45.60117 on the scale
    3. pythonLiveBench60109 on the scale
    4. plot_unscramblingLiveBench56.03106 on the scale
    5. integrals_with_gameLiveBench75104 on the scale
    6. consecutive_eventsLiveBench89.02102 on the scale
    7. zebra_puzzleLiveBench70102 on the scale
    8. javascriptLiveBench68.1899 on the scale
    9. logic_with_navigationLiveBench6896 on the scale
    10. simplifyLiveBench60.5792 on the scale
    11. connectionsLiveBench9591 on the scale
    12. theory_of_mindLiveBench78.8588 on the scale
    13. code_completionLiveBench86.9687 on the scale
    14. paraphraseLiveBench67.0586 on the scale
    15. summarizeLiveBench63.3885 on the scale
    16. typosLiveBench7077 on the scale
    17. code_generationLiveBench80.2876 on the scale
    18. story_generationLiveBench74.7874 on the scale
    19. olympiadLiveBench87.0072 on the scale
    20. spatialLiveBench9453 on the scale
    21. AMPS_HardLiveBench9847 on the scale
    22. math_compLiveBench95.1042 on the scale
    23. tablereformatLiveBench10041 on the scale
  106. 106claude-sonnet-4-6-16knot in the catalogunstated109.9841

    4 columns on 1 board, hardest first are the whole evidence behind 109.98. Each is a door to the column and everything else scored on it.

    1. FrontierMath-Tier-4-2025-07-01-PrivateEpoch AI Benchmarking Hub0.08120 on the scale
    2. FrontierMath-Tier-4-2025-07-01-PublicEpoch AI Benchmarking Hub0116 on the scale
    3. FrontierMath-2025-02-28-PrivateEpoch AI Benchmarking Hub0.32115 on the scale
    4. FrontierMath-2025-02-28-PublicEpoch AI Benchmarking Hub0.80106 on the scale
  107. 107gpt-5.1-2025-11-13not in the cataloghigh109.9471

    7 columns on 1 board, hardest first are the whole evidence behind 109.94. Each is a door to the column and everything else scored on it.

    1. FrontierMath-Tier-4-2025-07-01-PrivateEpoch AI Benchmarking Hub0.13120 on the scale
    2. Chess PuzzlesEpoch AI Benchmarking Hub0.42119 on the scale
    3. SimpleQA VerifiedEpoch AI Benchmarking Hub0.48115 on the scale
    4. FrontierMath-2025-02-28-PrivateEpoch AI Benchmarking Hub0.31115 on the scale
    5. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.8994 on the scale
    6. SWE-Bench verifiedEpoch AI Benchmarking Hub0.6884 on the scale
    7. GPQA diamondEpoch AI Benchmarking Hub0.8883 on the scale
  108. 108mistral-large-4not in the cataloghigh109.81231

    23 columns on 1 board, hardest first are the whole evidence behind 109.81. Each is a door to the column and everything else scored on it.

    1. typescriptLiveBench43.33122 on the scale
    2. tablejoinLiveBench49.10117 on the scale
    3. pythonLiveBench60109 on the scale
    4. plot_unscramblingLiveBench40.93106 on the scale
    5. integrals_with_gameLiveBench90104 on the scale
    6. consecutive_eventsLiveBench80.53102 on the scale
    7. zebra_puzzleLiveBench93102 on the scale
    8. javascriptLiveBench68.1899 on the scale
    9. logic_with_navigationLiveBench6896 on the scale
    10. simplifyLiveBench66.1892 on the scale
    11. connectionsLiveBench4891 on the scale
    12. theory_of_mindLiveBench80.7788 on the scale
    13. code_completionLiveBench78.2687 on the scale
    14. paraphraseLiveBench63.9786 on the scale
    15. summarizeLiveBench61.6385 on the scale
    16. typosLiveBench6077 on the scale
    17. code_generationLiveBench76.0676 on the scale
    18. story_generationLiveBench67.5074 on the scale
    19. olympiadLiveBench89.2872 on the scale
    20. spatialLiveBench9453 on the scale
    21. AMPS_HardLiveBench9847 on the scale
    22. math_compLiveBench97.0642 on the scale
    23. tablereformatLiveBench10041 on the scale
  109. 109doubao-seed-2.1-pro-260628not in the cataloghigh109.6141

    4 columns on 1 board, hardest first are the whole evidence behind 109.61. Each is a door to the column and everything else scored on it.

    1. Chess PuzzlesEpoch AI Benchmarking Hub0.21119 on the scale
    2. SimpleQA VerifiedEpoch AI Benchmarking Hub0.45115 on the scale
    3. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.9694 on the scale
    4. GPQA diamondEpoch AI Benchmarking Hub0.8983 on the scale
  110. 110z-ai/glm-5.2unstated109.40231

    23 columns on 1 board, hardest first are the whole evidence behind 109.40. Each is a door to the column and everything else scored on it.

    1. typescriptLiveBench36.67122 on the scale
    2. tablejoinLiveBench45.87117 on the scale
    3. pythonLiveBench55109 on the scale
    4. plot_unscramblingLiveBench60.73106 on the scale
    5. integrals_with_gameLiveBench76104 on the scale
    6. consecutive_eventsLiveBench79.28102 on the scale
    7. zebra_puzzleLiveBench65.50102 on the scale
    8. javascriptLiveBench63.6499 on the scale
    9. logic_with_navigationLiveBench8096 on the scale
    10. simplifyLiveBench55.6792 on the scale
    11. connectionsLiveBench9491 on the scale
    12. theory_of_mindLiveBench7588 on the scale
    13. code_completionLiveBench80.4487 on the scale
    14. paraphraseLiveBench62.2586 on the scale
    15. summarizeLiveBench68.3785 on the scale
    16. typosLiveBench7477 on the scale
    17. code_generationLiveBench78.8776 on the scale
    18. story_generationLiveBench62.8874 on the scale
    19. olympiadLiveBench89.0572 on the scale
    20. spatialLiveBench9453 on the scale
    21. AMPS_HardLiveBench9847 on the scale
    22. math_compLiveBench96.0842 on the scale
    23. tablereformatLiveBench96.0841 on the scale
  111. 111z-ai/glm-5.1unstated109.27101

    10 columns on 1 board, hardest first are the whole evidence behind 109.27. Each is a door to the column and everything else scored on it.

    1. FrontierMath-Tier-4-2025-07-01-PrivateEpoch AI Benchmarking Hub0.13120 on the scale
    2. Chess PuzzlesEpoch AI Benchmarking Hub0.20119 on the scale
    3. FrontierMath-Tier-4-2025-07-01-PublicEpoch AI Benchmarking Hub0116 on the scale
    4. SimpleQA VerifiedEpoch AI Benchmarking Hub0.34115 on the scale
    5. FrontierMath-2025-02-28-PrivateEpoch AI Benchmarking Hub0.33115 on the scale
    6. FrontierMath-Tiers-1-3-v2-PrivateEpoch AI Benchmarking Hub0.37109 on the scale
    7. FrontierMath-2025-02-28-PublicEpoch AI Benchmarking Hub0.80106 on the scale
    8. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.9394 on the scale
    9. SWE-Bench verifiedEpoch AI Benchmarking Hub0.7484 on the scale
    10. GPQA diamondEpoch AI Benchmarking Hub0.9083 on the scale
  112. 112gpt-5-pro-2025-10-06not in the cataloghigh109.2351

    5 columns on 1 board, hardest first are the whole evidence behind 109.23. Each is a door to the column and everything else scored on it.

    1. FrontierMath-Tier-4-2025-07-01-PrivateEpoch AI Benchmarking Hub0.15120 on the scale
    2. Chess PuzzlesEpoch AI Benchmarking Hub0.48119 on the scale
    3. FrontierMath-Tier-4-v2-PrivateEpoch AI Benchmarking Hub0.20116 on the scale
    4. FrontierMath-Tiers-1-3-v2-PrivateEpoch AI Benchmarking Hub0.56109 on the scale
    5. FrontierMath-2025-02-28-PublicEpoch AI Benchmarking Hub0.60106 on the scale
  113. 113anthropic/claude-opus-5low109.1331

    3 columns on 1 board, hardest first are the whole evidence behind 109.13. Each is a door to the column and everything else scored on it.

    1. Chess PuzzlesEpoch AI Benchmarking Hub0.27119 on the scale
    2. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.9394 on the scale
    3. GPQA diamondEpoch AI Benchmarking Hub0.8883 on the scale
  114. 114doubao-seed-2.1-turbo-260628not in the cataloghigh108.8441

    4 columns on 1 board, hardest first are the whole evidence behind 108.84. Each is a door to the column and everything else scored on it.

    1. Chess PuzzlesEpoch AI Benchmarking Hub0.26119 on the scale
    2. SimpleQA VerifiedEpoch AI Benchmarking Hub0.30115 on the scale
    3. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.9694 on the scale
    4. GPQA diamondEpoch AI Benchmarking Hub0.9083 on the scale
  115. 115gpt-5.2-2025-12-11not in the catalogmedium108.7591

    9 columns on 1 board, hardest first are the whole evidence behind 108.75. Each is a door to the column and everything else scored on it.

    1. Mystery Game PuzzlesEpoch AI Benchmarking Hub0.22121 on the scale
    2. FrontierMath-Tier-4-2025-07-01-PrivateEpoch AI Benchmarking Hub0.17120 on the scale
    3. Chess PuzzlesEpoch AI Benchmarking Hub0.36119 on the scale
    4. FrontierMath-Tier-4-2025-07-01-PublicEpoch AI Benchmarking Hub0116 on the scale
    5. SimpleQA VerifiedEpoch AI Benchmarking Hub0.33115 on the scale
    6. FrontierMath-2025-02-28-PrivateEpoch AI Benchmarking Hub0.37115 on the scale
    7. FrontierMath-2025-02-28-PublicEpoch AI Benchmarking Hub0.60106 on the scale
    8. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.9494 on the scale
    9. GPQA diamondEpoch AI Benchmarking Hub0.8883 on the scale
  116. 116gpt-5-2025-08-07not in the cataloghigh108.61151

    15 columns on 1 board, hardest first are the whole evidence behind 108.61. Each is a door to the column and everything else scored on it.

    1. EBR-benchEpoch AI Benchmarking Hub0.13123 on the scale
    2. Mystery Game PuzzlesEpoch AI Benchmarking Hub0.23121 on the scale
    3. FrontierMath-Tier-4-2025-07-01-PrivateEpoch AI Benchmarking Hub0.13120 on the scale
    4. Chess PuzzlesEpoch AI Benchmarking Hub0.36119 on the scale
    5. MirrorCodeEpoch AI Benchmarking Hub0.04119 on the scale
    6. FrontierMath-Tier-4-2025-07-01-PublicEpoch AI Benchmarking Hub0116 on the scale
    7. FrontierMath-Tier-4-v2-PrivateEpoch AI Benchmarking Hub0.22116 on the scale
    8. SimpleQA VerifiedEpoch AI Benchmarking Hub0.50115 on the scale
    9. FrontierMath-2025-02-28-PrivateEpoch AI Benchmarking Hub0.32115 on the scale
    10. FrontierMath-Tiers-1-3-v2-PrivateEpoch AI Benchmarking Hub0.55109 on the scale
    11. FrontierMath-2025-02-28-PublicEpoch AI Benchmarking Hub0.60106 on the scale
    12. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.9194 on the scale
    13. SWE-Bench verifiedEpoch AI Benchmarking Hub0.7484 on the scale
    14. GPQA diamondEpoch AI Benchmarking Hub0.8683 on the scale
    15. MATH level 5Epoch AI Benchmarking Hub0.9881 on the scale
  117. 117z-ai/glm-5.3-flashmax108.4561

    6 columns on 1 board, hardest first are the whole evidence behind 108.45. Each is a door to the column and everything else scored on it.

    1. Mystery Game PuzzlesEpoch AI Benchmarking Hub0.08121 on the scale
    2. Chess PuzzlesEpoch AI Benchmarking Hub0.21119 on the scale
    3. FrontierMath-Tier-4-v2-PrivateEpoch AI Benchmarking Hub0.17116 on the scale
    4. FrontierMath-Tiers-1-3-v2-PrivateEpoch AI Benchmarking Hub0.56109 on the scale
    5. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.9494 on the scale
    6. GPQA diamondEpoch AI Benchmarking Hub0.9083 on the scale
  118. 118z-ai/glm-5.3-flashunstated108.42231

    23 columns on 1 board, hardest first are the whole evidence behind 108.42. Each is a door to the column and everything else scored on it.

    1. typescriptLiveBench46.67122 on the scale
    2. tablejoinLiveBench48.83117 on the scale
    3. pythonLiveBench60109 on the scale
    4. plot_unscramblingLiveBench60.26106 on the scale
    5. integrals_with_gameLiveBench45104 on the scale
    6. consecutive_eventsLiveBench84.30102 on the scale
    7. zebra_puzzleLiveBench79.50102 on the scale
    8. javascriptLiveBench63.6499 on the scale
    9. logic_with_navigationLiveBench6296 on the scale
    10. simplifyLiveBench46.9592 on the scale
    11. connectionsLiveBench93.6791 on the scale
    12. theory_of_mindLiveBench73.0888 on the scale
    13. code_completionLiveBench80.4487 on the scale
    14. paraphraseLiveBench47.9886 on the scale
    15. summarizeLiveBench56.4785 on the scale
    16. typosLiveBench7877 on the scale
    17. code_generationLiveBench77.4776 on the scale
    18. story_generationLiveBench59.8874 on the scale
    19. olympiadLiveBench89.8472 on the scale
    20. spatialLiveBench9653 on the scale
    21. AMPS_HardLiveBench9747 on the scale
    22. math_compLiveBench93.1442 on the scale
    23. tablereformatLiveBench96.0841 on the scale
  119. 119grok-4.20-0309-reasoningnot in the catalogunstated108.3361

    6 columns on 1 board, hardest first are the whole evidence behind 108.33. Each is a door to the column and everything else scored on it.

    1. Chess PuzzlesEpoch AI Benchmarking Hub0.29119 on the scale
    2. FrontierMath-Tier-4-v2-PrivateEpoch AI Benchmarking Hub0.17116 on the scale
    3. SimpleQA VerifiedEpoch AI Benchmarking Hub0.30115 on the scale
    4. FrontierMath-Tiers-1-3-v2-PrivateEpoch AI Benchmarking Hub0.45109 on the scale
    5. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.9294 on the scale
    6. GPQA diamondEpoch AI Benchmarking Hub0.8983 on the scale
  120. 120deepseek/deepseek-v4-prohigh108.2031

    3 columns on 1 board, hardest first are the whole evidence behind 108.20. Each is a door to the column and everything else scored on it.

    1. Chess PuzzlesEpoch AI Benchmarking Hub0.16119 on the scale
    2. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.9694 on the scale
    3. GPQA diamondEpoch AI Benchmarking Hub0.9183 on the scale
  121. 121google/gemini-3-flash-previewunstated108.1691

    9 columns on 1 board, hardest first are the whole evidence behind 108.16. Each is a door to the column and everything else scored on it.

    1. FrontierMath-Tier-4-2025-07-01-PrivateEpoch AI Benchmarking Hub0.04120 on the scale
    2. FrontierMath-Tier-4-2025-07-01-PublicEpoch AI Benchmarking Hub0116 on the scale
    3. FrontierMath-Tier-4-v2-PrivateEpoch AI Benchmarking Hub0.17116 on the scale
    4. FrontierMath-2025-02-28-PrivateEpoch AI Benchmarking Hub0.36115 on the scale
    5. FrontierMath-Tiers-1-3-v2-PrivateEpoch AI Benchmarking Hub0.51109 on the scale
    6. FrontierMath-2025-02-28-PublicEpoch AI Benchmarking Hub0.60106 on the scale
    7. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.9394 on the scale
    8. SWE-Bench verifiedEpoch AI Benchmarking Hub0.7584 on the scale
    9. GPQA diamondEpoch AI Benchmarking Hub0.8383 on the scale
  122. 123doubao-seed-2.0-pro-260215not in the cataloghigh108.1241

    4 columns on 1 board, hardest first are the whole evidence behind 108.12. Each is a door to the column and everything else scored on it.

    1. Chess PuzzlesEpoch AI Benchmarking Hub0.20119 on the scale
    2. SimpleQA VerifiedEpoch AI Benchmarking Hub0.39115 on the scale
    3. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.9494 on the scale
    4. GPQA diamondEpoch AI Benchmarking Hub0.8883 on the scale
  123. 122gpt-5-2025-08-07not in the catalogmedium108.12101

    10 columns on 1 board, hardest first are the whole evidence behind 108.12. Each is a door to the column and everything else scored on it.

    1. Mystery Game PuzzlesEpoch AI Benchmarking Hub0.15121 on the scale
    2. FrontierMath-Tier-4-2025-07-01-PrivateEpoch AI Benchmarking Hub0.06120 on the scale
    3. Chess PuzzlesEpoch AI Benchmarking Hub0.32119 on the scale
    4. FrontierMath-Tier-4-2025-07-01-PublicEpoch AI Benchmarking Hub0116 on the scale
    5. FrontierMath-2025-02-28-PrivateEpoch AI Benchmarking Hub0.27115 on the scale
    6. FrontierMath-2025-02-28-PublicEpoch AI Benchmarking Hub0.70106 on the scale
    7. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.8794 on the scale
    8. SWE-Bench verifiedEpoch AI Benchmarking Hub0.7184 on the scale
    9. GPQA diamondEpoch AI Benchmarking Hub0.8583 on the scale
    10. MATH level 5Epoch AI Benchmarking Hub0.9881 on the scale
  124. 124thinkingmachines/inklingxhigh107.98292

    29 columns on 2 boards, hardest first are the whole evidence behind 107.98. Each is a door to the column and everything else scored on it.

    1. typescriptLiveBench30122 on the scale
    2. Chess PuzzlesEpoch AI Benchmarking Hub0.21119 on the scale
    3. tablejoinLiveBench48.48117 on the scale
    4. FrontierMath-Tier-4-v2-PrivateEpoch AI Benchmarking Hub0.05116 on the scale
    5. SimpleQA VerifiedEpoch AI Benchmarking Hub0.40115 on the scale
    6. pythonLiveBench50109 on the scale
    7. FrontierMath-Tiers-1-3-v2-PrivateEpoch AI Benchmarking Hub0.33109 on the scale
    8. plot_unscramblingLiveBench53.21106 on the scale
    9. integrals_with_gameLiveBench72104 on the scale
    10. consecutive_eventsLiveBench69.85102 on the scale
    11. zebra_puzzleLiveBench88102 on the scale
    12. javascriptLiveBench68.1899 on the scale
    13. logic_with_navigationLiveBench6696 on the scale
    14. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.8994 on the scale
    15. simplifyLiveBench60.5092 on the scale
    16. connectionsLiveBench91.1791 on the scale
    17. theory_of_mindLiveBench65.3988 on the scale
    18. code_completionLiveBench67.3987 on the scale
    19. paraphraseLiveBench70.8586 on the scale
    20. summarizeLiveBench74.8585 on the scale
    21. GPQA diamondEpoch AI Benchmarking Hub0.8883 on the scale
    22. typosLiveBench7677 on the scale
    23. code_generationLiveBench74.6576 on the scale
    24. story_generationLiveBench74.1874 on the scale
    25. olympiadLiveBench85.4072 on the scale
    26. spatialLiveBench9453 on the scale
    27. AMPS_HardLiveBench9947 on the scale
    28. math_compLiveBench97.0642 on the scale
    29. tablereformatLiveBench10041 on the scale
  125. 125openai/gpt-5.5low107.8641

    4 columns on 1 board, hardest first are the whole evidence behind 107.86. Each is a door to the column and everything else scored on it.

    1. Mystery Game PuzzlesEpoch AI Benchmarking Hub0.28121 on the scale
    2. Chess PuzzlesEpoch AI Benchmarking Hub0.30119 on the scale
    3. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.8494 on the scale
    4. GPQA diamondEpoch AI Benchmarking Hub0.9183 on the scale
  126. 127google/gemini-3.6-flashlow107.8041

    4 columns on 1 board, hardest first are the whole evidence behind 107.80. Each is a door to the column and everything else scored on it.

    1. Mystery Game PuzzlesEpoch AI Benchmarking Hub0.23121 on the scale
    2. Chess PuzzlesEpoch AI Benchmarking Hub0.42119 on the scale
    3. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.8294 on the scale
    4. GPQA diamondEpoch AI Benchmarking Hub0.8683 on the scale
  127. 126qwen/qwen3.7-plusunstated107.8031

    3 columns on 1 board, hardest first are the whole evidence behind 107.80. Each is a door to the column and everything else scored on it.

    1. Mystery Game PuzzlesEpoch AI Benchmarking Hub0.17121 on the scale
    2. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.9394 on the scale
    3. GPQA diamondEpoch AI Benchmarking Hub0.8883 on the scale
  128. 128moonshotai/kimi-k2.7-codeunstated107.73292

    29 columns on 2 boards, hardest first are the whole evidence behind 107.73. Each is a door to the column and everything else scored on it.

    1. typescriptLiveBench23.33122 on the scale
    2. Chess PuzzlesEpoch AI Benchmarking Hub0.14119 on the scale
    3. tablejoinLiveBench47.54117 on the scale
    4. FrontierMath-Tier-4-v2-PrivateEpoch AI Benchmarking Hub0.12116 on the scale
    5. SimpleQA VerifiedEpoch AI Benchmarking Hub0.36115 on the scale
    6. pythonLiveBench50109 on the scale
    7. FrontierMath-Tiers-1-3-v2-PrivateEpoch AI Benchmarking Hub0.54109 on the scale
    8. plot_unscramblingLiveBench55.72106 on the scale
    9. integrals_with_gameLiveBench37104 on the scale
    10. consecutive_eventsLiveBench48.28102 on the scale
    11. zebra_puzzleLiveBench96102 on the scale
    12. javascriptLiveBench63.6499 on the scale
    13. logic_with_navigationLiveBench7496 on the scale
    14. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.9694 on the scale
    15. simplifyLiveBench49.7592 on the scale
    16. connectionsLiveBench9891 on the scale
    17. theory_of_mindLiveBench69.2388 on the scale
    18. code_completionLiveBench76.0987 on the scale
    19. paraphraseLiveBench48.5386 on the scale
    20. summarizeLiveBench58.3285 on the scale
    21. GPQA diamondEpoch AI Benchmarking Hub0.8883 on the scale
    22. typosLiveBench8077 on the scale
    23. code_generationLiveBench71.8376 on the scale
    24. story_generationLiveBench68.5774 on the scale
    25. olympiadLiveBench90.3072 on the scale
    26. spatialLiveBench9253 on the scale
    27. AMPS_HardLiveBench9747 on the scale
    28. math_compLiveBench94.1242 on the scale
    29. tablereformatLiveBench92.1641 on the scale
  129. 129x-ai/grok-4.3high107.3961

    6 columns on 1 board, hardest first are the whole evidence behind 107.39. Each is a door to the column and everything else scored on it.

    1. Chess PuzzlesEpoch AI Benchmarking Hub0.18119 on the scale
    2. FrontierMath-Tier-4-v2-PrivateEpoch AI Benchmarking Hub0.15116 on the scale
    3. SimpleQA VerifiedEpoch AI Benchmarking Hub0.33115 on the scale
    4. FrontierMath-Tiers-1-3-v2-PrivateEpoch AI Benchmarking Hub0.43109 on the scale
    5. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.9394 on the scale
    6. GPQA diamondEpoch AI Benchmarking Hub0.8983 on the scale
  130. 130fireworks/kimi-k2p5not in the catalogunstated107.3241

    4 columns on 1 board, hardest first are the whole evidence behind 107.32. Each is a door to the column and everything else scored on it.

    1. FrontierMath-Tier-4-2025-07-01-PrivateEpoch AI Benchmarking Hub0.04120 on the scale
    2. FrontierMath-2025-02-28-PrivateEpoch AI Benchmarking Hub0.28115 on the scale
    3. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.9294 on the scale
    4. GPQA diamondEpoch AI Benchmarking Hub0.8883 on the scale
  131. 131kimi-k2.6-thinkingnot in the catalogunstated107.26231

    23 columns on 1 board, hardest first are the whole evidence behind 107.26. Each is a door to the column and everything else scored on it.

    1. typescriptLiveBench26.67122 on the scale
    2. tablejoinLiveBench46.10117 on the scale
    3. pythonLiveBench55109 on the scale
    4. plot_unscramblingLiveBench58.09106 on the scale
    5. integrals_with_gameLiveBench54104 on the scale
    6. consecutive_eventsLiveBench51.27102 on the scale
    7. zebra_puzzleLiveBench78.50102 on the scale
    8. javascriptLiveBench59.0999 on the scale
    9. logic_with_navigationLiveBench7096 on the scale
    10. simplifyLiveBench61.4292 on the scale
    11. connectionsLiveBench89.3391 on the scale
    12. theory_of_mindLiveBench7588 on the scale
    13. code_completionLiveBench78.2687 on the scale
    14. paraphraseLiveBench61.6386 on the scale
    15. summarizeLiveBench67.5085 on the scale
    16. typosLiveBench7877 on the scale
    17. code_generationLiveBench78.8776 on the scale
    18. story_generationLiveBench66.8874 on the scale
    19. olympiadLiveBench90.0372 on the scale
    20. spatialLiveBench9453 on the scale
    21. AMPS_HardLiveBench9747 on the scale
    22. math_compLiveBench96.0842 on the scale
    23. tablereformatLiveBench98.0441 on the scale
  132. 132deepseek/deepseek-v4-promax107.0271

    7 columns on 1 board, hardest first are the whole evidence behind 107.02. Each is a door to the column and everything else scored on it.

    1. Chess PuzzlesEpoch AI Benchmarking Hub0.19119 on the scale
    2. FrontierMath-Tier-4-v2-PrivateEpoch AI Benchmarking Hub0.02116 on the scale
    3. SimpleQA VerifiedEpoch AI Benchmarking Hub0.47115 on the scale
    4. FrontierMath-Tiers-1-3-v2-PrivateEpoch AI Benchmarking Hub0.45109 on the scale
    5. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.9794 on the scale
    6. SWE-Bench verifiedEpoch AI Benchmarking Hub0.7884 on the scale
    7. GPQA diamondEpoch AI Benchmarking Hub0.9083 on the scale
  133. 133openai/gpt-5.6-terralow106.9341

    4 columns on 1 board, hardest first are the whole evidence behind 106.93. Each is a door to the column and everything else scored on it.

    1. Mystery Game PuzzlesEpoch AI Benchmarking Hub0.19121 on the scale
    2. Chess PuzzlesEpoch AI Benchmarking Hub0.27119 on the scale
    3. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.8994 on the scale
    4. GPQA diamondEpoch AI Benchmarking Hub0.8783 on the scale
  134. 134gpt-5.4-mini-2026-03-17not in the catalogxhigh106.9151

    5 columns on 1 board, hardest first are the whole evidence behind 106.91. Each is a door to the column and everything else scored on it.

    1. Chess PuzzlesEpoch AI Benchmarking Hub0.17119 on the scale
    2. FrontierMath-Tier-4-v2-PrivateEpoch AI Benchmarking Hub0.10116 on the scale
    3. FrontierMath-Tiers-1-3-v2-PrivateEpoch AI Benchmarking Hub0.51109 on the scale
    4. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.8994 on the scale
    5. GPQA diamondEpoch AI Benchmarking Hub0.8783 on the scale
  135. 135gpt-5.4-nano-2026-03-17not in the cataloghigh106.76101

    10 columns on 1 board, hardest first are the whole evidence behind 106.76. Each is a door to the column and everything else scored on it.

    1. Mystery Game PuzzlesEpoch AI Benchmarking Hub0.05121 on the scale
    2. FrontierMath-Tier-4-2025-07-01-PrivateEpoch AI Benchmarking Hub0.06120 on the scale
    3. Chess PuzzlesEpoch AI Benchmarking Hub0.36119 on the scale
    4. FrontierMath-Tier-4-v2-PrivateEpoch AI Benchmarking Hub0.12116 on the scale
    5. SimpleQA VerifiedEpoch AI Benchmarking Hub0.12115 on the scale
    6. FrontierMath-2025-02-28-PrivateEpoch AI Benchmarking Hub0.26115 on the scale
    7. FrontierMath-Tiers-1-3-v2-PrivateEpoch AI Benchmarking Hub0.45109 on the scale
    8. FrontierMath-2025-02-28-PublicEpoch AI Benchmarking Hub0.60106 on the scale
    9. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.8894 on the scale
    10. GPQA diamondEpoch AI Benchmarking Hub0.7883 on the scale
  136. 136qwen3.6-max-previewnot in the catalogunstated106.7581

    8 columns on 1 board, hardest first are the whole evidence behind 106.75. Each is a door to the column and everything else scored on it.

    1. FrontierMath-Tier-4-2025-07-01-PrivateEpoch AI Benchmarking Hub0.04120 on the scale
    2. FrontierMath-Tier-4-2025-07-01-PublicEpoch AI Benchmarking Hub0116 on the scale
    3. SimpleQA VerifiedEpoch AI Benchmarking Hub0.52115 on the scale
    4. FrontierMath-2025-02-28-PrivateEpoch AI Benchmarking Hub0.23115 on the scale
    5. FrontierMath-2025-02-28-PublicEpoch AI Benchmarking Hub0.50106 on the scale
    6. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.9194 on the scale
    7. SWE-Bench verifiedEpoch AI Benchmarking Hub0.7784 on the scale
    8. GPQA diamondEpoch AI Benchmarking Hub0.8783 on the scale
  137. 137thinkingmachines/inkling-smallxhigh106.5461

    6 columns on 1 board, hardest first are the whole evidence behind 106.54. Each is a door to the column and everything else scored on it.

    1. Mystery Game PuzzlesEpoch AI Benchmarking Hub0.06121 on the scale
    2. FrontierMath-Tier-4-v2-PrivateEpoch AI Benchmarking Hub0.17116 on the scale
    3. SimpleQA VerifiedEpoch AI Benchmarking Hub0.19115 on the scale
    4. FrontierMath-Tiers-1-3-v2-PrivateEpoch AI Benchmarking Hub0.46109 on the scale
    5. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.9094 on the scale
    6. GPQA diamondEpoch AI Benchmarking Hub0.8983 on the scale
  138. 138qwen/qwen3.6-plusunstated106.49332

    33 columns on 2 boards, hardest first are the whole evidence behind 106.49. Each is a door to the column and everything else scored on it.

    1. typescriptLiveBench20122 on the scale
    2. FrontierMath-Tier-4-2025-07-01-PrivateEpoch AI Benchmarking Hub0.08120 on the scale
    3. Chess PuzzlesEpoch AI Benchmarking Hub0.16119 on the scale
    4. tablejoinLiveBench44.65117 on the scale
    5. FrontierMath-Tier-4-2025-07-01-PublicEpoch AI Benchmarking Hub0116 on the scale
    6. SimpleQA VerifiedEpoch AI Benchmarking Hub0.44115 on the scale
    7. FrontierMath-2025-02-28-PrivateEpoch AI Benchmarking Hub0.26115 on the scale
    8. pythonLiveBench45109 on the scale
    9. FrontierMath-Tiers-1-3-v2-PrivateEpoch AI Benchmarking Hub0.38109 on the scale
    10. FrontierMath-2025-02-28-PublicEpoch AI Benchmarking Hub0.50106 on the scale
    11. plot_unscramblingLiveBench52.47106 on the scale
    12. integrals_with_gameLiveBench62104 on the scale
    13. consecutive_eventsLiveBench67.04102 on the scale
    14. zebra_puzzleLiveBench68102 on the scale
    15. javascriptLiveBench59.0999 on the scale
    16. logic_with_navigationLiveBench7096 on the scale
    17. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.9394 on the scale
    18. simplifyLiveBench51.5792 on the scale
    19. connectionsLiveBench90.5091 on the scale
    20. theory_of_mindLiveBench67.3188 on the scale
    21. code_completionLiveBench76.0987 on the scale
    22. paraphraseLiveBench60.6286 on the scale
    23. summarizeLiveBench64.3285 on the scale
    24. SWE-Bench verifiedEpoch AI Benchmarking Hub0.5884 on the scale
    25. GPQA diamondEpoch AI Benchmarking Hub0.8883 on the scale
    26. typosLiveBench8277 on the scale
    27. code_generationLiveBench80.2876 on the scale
    28. story_generationLiveBench56.8774 on the scale
    29. olympiadLiveBench82.7672 on the scale
    30. spatialLiveBench9853 on the scale
    31. AMPS_HardLiveBench9747 on the scale
    32. math_compLiveBench93.1442 on the scale
    33. tablereformatLiveBench98.0441 on the scale
  139. 139doubao-seed-2.0-lite-260428not in the cataloghigh106.4241

    4 columns on 1 board, hardest first are the whole evidence behind 106.42. Each is a door to the column and everything else scored on it.

    1. Chess PuzzlesEpoch AI Benchmarking Hub0.20119 on the scale
    2. SimpleQA VerifiedEpoch AI Benchmarking Hub0.32115 on the scale
    3. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.9194 on the scale
    4. GPQA diamondEpoch AI Benchmarking Hub0.8883 on the scale
  140. 140x-ai/grok-build-0.1unstated106.25231

    23 columns on 1 board, hardest first are the whole evidence behind 106.25. Each is a door to the column and everything else scored on it.

    1. typescriptLiveBench33.33122 on the scale
    2. tablejoinLiveBench42.65117 on the scale
    3. pythonLiveBench45109 on the scale
    4. plot_unscramblingLiveBench53.38106 on the scale
    5. integrals_with_gameLiveBench66104 on the scale
    6. consecutive_eventsLiveBench69.73102 on the scale
    7. zebra_puzzleLiveBench68.25102 on the scale
    8. javascriptLiveBench59.0999 on the scale
    9. logic_with_navigationLiveBench7096 on the scale
    10. simplifyLiveBench62.6092 on the scale
    11. connectionsLiveBench8491 on the scale
    12. theory_of_mindLiveBench69.2388 on the scale
    13. code_completionLiveBench67.3987 on the scale
    14. paraphraseLiveBench58.3886 on the scale
    15. summarizeLiveBench67.3785 on the scale
    16. typosLiveBench8077 on the scale
    17. code_generationLiveBench63.3876 on the scale
    18. story_generationLiveBench72.5374 on the scale
    19. olympiadLiveBench86.6272 on the scale
    20. spatialLiveBench9853 on the scale
    21. AMPS_HardLiveBench6647 on the scale
    22. math_compLiveBench95.1042 on the scale
    23. tablereformatLiveBench10041 on the scale
  141. 141gpt-5.4-mini-2026-03-17not in the cataloghigh106.0971

    7 columns on 1 board, hardest first are the whole evidence behind 106.09. Each is a door to the column and everything else scored on it.

    1. FrontierMath-Tier-4-2025-07-01-PrivateEpoch AI Benchmarking Hub0.02120 on the scale
    2. Chess PuzzlesEpoch AI Benchmarking Hub0.23119 on the scale
    3. SimpleQA VerifiedEpoch AI Benchmarking Hub0.29115 on the scale
    4. FrontierMath-2025-02-28-PrivateEpoch AI Benchmarking Hub0.28115 on the scale
    5. FrontierMath-2025-02-28-PublicEpoch AI Benchmarking Hub0.50106 on the scale
    6. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.8794 on the scale
    7. GPQA diamondEpoch AI Benchmarking Hub0.8483 on the scale
  142. 142ox-alphanot in the catalogmax106.05231

    23 columns on 1 board, hardest first are the whole evidence behind 106.05. Each is a door to the column and everything else scored on it.

    1. typescriptLiveBench43.33122 on the scale
    2. tablejoinLiveBench46.94117 on the scale
    3. pythonLiveBench60109 on the scale
    4. plot_unscramblingLiveBench53.08106 on the scale
    5. integrals_with_gameLiveBench39104 on the scale
    6. consecutive_eventsLiveBench80.35102 on the scale
    7. zebra_puzzleLiveBench79.50102 on the scale
    8. javascriptLiveBench54.5599 on the scale
    9. logic_with_navigationLiveBench5296 on the scale
    10. simplifyLiveBench54.4892 on the scale
    11. connectionsLiveBench71.3391 on the scale
    12. theory_of_mindLiveBench78.8588 on the scale
    13. code_completionLiveBench78.2687 on the scale
    14. paraphraseLiveBench57.4786 on the scale
    15. summarizeLiveBench58.1885 on the scale
    16. typosLiveBench7477 on the scale
    17. code_generationLiveBench73.2476 on the scale
    18. story_generationLiveBench70.8774 on the scale
    19. olympiadLiveBench81.9572 on the scale
    20. spatialLiveBench9653 on the scale
    21. AMPS_HardLiveBench9847 on the scale
    22. math_compLiveBench91.1842 on the scale
    23. tablereformatLiveBench10041 on the scale
  143. 143nvidia/nemotron-3-ultra-550b-a55bunstated105.72231

    23 columns on 1 board, hardest first are the whole evidence behind 105.72. Each is a door to the column and everything else scored on it.

    1. typescriptLiveBench16.67122 on the scale
    2. tablejoinLiveBench46.56117 on the scale
    3. pythonLiveBench45109 on the scale
    4. plot_unscramblingLiveBench47.77106 on the scale
    5. integrals_with_gameLiveBench80104 on the scale
    6. consecutive_eventsLiveBench18.77102 on the scale
    7. zebra_puzzleLiveBench71.25102 on the scale
    8. javascriptLiveBench54.5599 on the scale
    9. logic_with_navigationLiveBench6896 on the scale
    10. simplifyLiveBench72.2892 on the scale
    11. connectionsLiveBench86.6791 on the scale
    12. theory_of_mindLiveBench61.5488 on the scale
    13. code_completionLiveBench69.5687 on the scale
    14. paraphraseLiveBench77.3886 on the scale
    15. summarizeLiveBench74.8885 on the scale
    16. typosLiveBench7877 on the scale
    17. code_generationLiveBench71.8376 on the scale
    18. story_generationLiveBench69.2374 on the scale
    19. olympiadLiveBench82.5872 on the scale
    20. spatialLiveBench9853 on the scale
    21. AMPS_HardLiveBench9647 on the scale
    22. math_compLiveBench96.0842 on the scale
    23. tablereformatLiveBench98.0441 on the scale
  144. 144nemotron-3-ultranot in the catalogunstated105.6231

    3 columns on 1 board, hardest first are the whole evidence behind 105.62. Each is a door to the column and everything else scored on it.

    1. Mystery Game PuzzlesEpoch AI Benchmarking Hub0.20121 on the scale
    2. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.8794 on the scale
    3. GPQA diamondEpoch AI Benchmarking Hub0.8583 on the scale
  145. 145google/gemini-3.6-flashminimal105.5541

    4 columns on 1 board, hardest first are the whole evidence behind 105.55. Each is a door to the column and everything else scored on it.

    1. Mystery Game PuzzlesEpoch AI Benchmarking Hub0.25121 on the scale
    2. Chess PuzzlesEpoch AI Benchmarking Hub0.29119 on the scale
    3. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.8094 on the scale
    4. GPQA diamondEpoch AI Benchmarking Hub0.8683 on the scale
  146. 146z-ai/glm-5.2low105.4251

    5 columns on 1 board, hardest first are the whole evidence behind 105.42. Each is a door to the column and everything else scored on it.

    1. Mystery Game PuzzlesEpoch AI Benchmarking Hub0.19121 on the scale
    2. Chess PuzzlesEpoch AI Benchmarking Hub0.18119 on the scale
    3. FrontierMath-Tiers-1-3-v2-PrivateEpoch AI Benchmarking Hub0.55109 on the scale
    4. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.7694 on the scale
    5. GPQA diamondEpoch AI Benchmarking Hub0.8883 on the scale
  147. 147gpt-5.1-2025-11-13not in the catalogmedium105.4151

    5 columns on 1 board, hardest first are the whole evidence behind 105.41. Each is a door to the column and everything else scored on it.

    1. Mystery Game PuzzlesEpoch AI Benchmarking Hub0.16121 on the scale
    2. FrontierMath-Tier-4-2025-07-01-PrivateEpoch AI Benchmarking Hub0.04120 on the scale
    3. FrontierMath-2025-02-28-PrivateEpoch AI Benchmarking Hub0.27115 on the scale
    4. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.8694 on the scale
    5. GPQA diamondEpoch AI Benchmarking Hub0.8583 on the scale
  148. 148qwen3.5-plusnot in the catalogunstated105.3181

    8 columns on 1 board, hardest first are the whole evidence behind 105.31. Each is a door to the column and everything else scored on it.

    1. Mystery Game PuzzlesEpoch AI Benchmarking Hub0.16121 on the scale
    2. FrontierMath-Tier-4-2025-07-01-PrivateEpoch AI Benchmarking Hub0.02120 on the scale
    3. Chess PuzzlesEpoch AI Benchmarking Hub0.09119 on the scale
    4. SimpleQA VerifiedEpoch AI Benchmarking Hub0.25115 on the scale
    5. FrontierMath-2025-02-28-PrivateEpoch AI Benchmarking Hub0.21115 on the scale
    6. FrontierMath-2025-02-28-PublicEpoch AI Benchmarking Hub0.50106 on the scale
    7. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.8794 on the scale
    8. GPQA diamondEpoch AI Benchmarking Hub0.8583 on the scale
  149. 149gpt-5-2025-08-07not in the cataloglow105.2231

    3 columns on 1 board, hardest first are the whole evidence behind 105.22. Each is a door to the column and everything else scored on it.

    1. Mystery Game PuzzlesEpoch AI Benchmarking Hub0.16121 on the scale
    2. Chess PuzzlesEpoch AI Benchmarking Hub0.27119 on the scale
    3. FrontierMath-Tiers-1-3-v2-PrivateEpoch AI Benchmarking Hub0.37109 on the scale
  150. 150gpt-5.2-2025-12-11not in the cataloglow104.8991

    9 columns on 1 board, hardest first are the whole evidence behind 104.89. Each is a door to the column and everything else scored on it.

    1. Mystery Game PuzzlesEpoch AI Benchmarking Hub0.10121 on the scale
    2. FrontierMath-Tier-4-2025-07-01-PrivateEpoch AI Benchmarking Hub0.06120 on the scale
    3. Chess PuzzlesEpoch AI Benchmarking Hub0.26119 on the scale
    4. FrontierMath-Tier-4-2025-07-01-PublicEpoch AI Benchmarking Hub0116 on the scale
    5. SimpleQA VerifiedEpoch AI Benchmarking Hub0.33115 on the scale
    6. FrontierMath-2025-02-28-PrivateEpoch AI Benchmarking Hub0.27115 on the scale
    7. FrontierMath-2025-02-28-PublicEpoch AI Benchmarking Hub0.40106 on the scale
    8. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.7994 on the scale
    9. GPQA diamondEpoch AI Benchmarking Hub0.8383 on the scale
  151. 151moonshotai/kimi-k2-thinkingnot in the catalogunstated104.8241

    4 columns on 1 board, hardest first are the whole evidence behind 104.82. Each is a door to the column and everything else scored on it.

    1. FrontierMath-Tier-4-2025-07-01-PrivateEpoch AI Benchmarking Hub0120 on the scale
    2. FrontierMath-Tier-4-2025-07-01-PublicEpoch AI Benchmarking Hub0116 on the scale
    3. FrontierMath-2025-02-28-PrivateEpoch AI Benchmarking Hub0.21115 on the scale
    4. FrontierMath-2025-02-28-PublicEpoch AI Benchmarking Hub0.40106 on the scale
  152. 152claude-opus-4-5-20251101-16knot in the catalogunstated104.7051

    5 columns on 1 board, hardest first are the whole evidence behind 104.70. Each is a door to the column and everything else scored on it.

    1. FrontierMath-Tier-4-2025-07-01-PrivateEpoch AI Benchmarking Hub0.02120 on the scale
    2. FrontierMath-2025-02-28-PrivateEpoch AI Benchmarking Hub0.20115 on the scale
    3. FrontierMath-2025-02-28-PublicEpoch AI Benchmarking Hub0.40106 on the scale
    4. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.8294 on the scale
    5. GPQA diamondEpoch AI Benchmarking Hub0.8583 on the scale
  153. 153minimax/minimax-m3unstated104.58272

    27 columns on 2 boards, hardest first are the whole evidence behind 104.58. Each is a door to the column and everything else scored on it.

    1. typescriptLiveBench23.33122 on the scale
    2. Mystery Game PuzzlesEpoch AI Benchmarking Hub0.07121 on the scale
    3. Chess PuzzlesEpoch AI Benchmarking Hub0.17119 on the scale
    4. tablejoinLiveBench45.85117 on the scale
    5. pythonLiveBench35109 on the scale
    6. plot_unscramblingLiveBench50.17106 on the scale
    7. integrals_with_gameLiveBench56104 on the scale
    8. consecutive_eventsLiveBench84.61102 on the scale
    9. zebra_puzzleLiveBench61102 on the scale
    10. javascriptLiveBench63.6499 on the scale
    11. logic_with_navigationLiveBench6696 on the scale
    12. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.7194 on the scale
    13. simplifyLiveBench56.6292 on the scale
    14. connectionsLiveBench96.3391 on the scale
    15. theory_of_mindLiveBench76.9288 on the scale
    16. code_completionLiveBench67.3987 on the scale
    17. paraphraseLiveBench55.9386 on the scale
    18. summarizeLiveBench53.9385 on the scale
    19. GPQA diamondEpoch AI Benchmarking Hub0.9183 on the scale
    20. typosLiveBench8477 on the scale
    21. code_generationLiveBench69.0176 on the scale
    22. story_generationLiveBench63.5574 on the scale
    23. olympiadLiveBench85.6172 on the scale
    24. spatialLiveBench9453 on the scale
    25. AMPS_HardLiveBench7547 on the scale
    26. math_compLiveBench91.1842 on the scale
    27. tablereformatLiveBench98.0441 on the scale
  154. 154gpt-5-mini-2025-08-07not in the cataloghigh104.57121

    12 columns on 1 board, hardest first are the whole evidence behind 104.57. Each is a door to the column and everything else scored on it.

    1. Mystery Game PuzzlesEpoch AI Benchmarking Hub0.05121 on the scale
    2. FrontierMath-Tier-4-2025-07-01-PrivateEpoch AI Benchmarking Hub0.06120 on the scale
    3. Chess PuzzlesEpoch AI Benchmarking Hub0.24119 on the scale
    4. FrontierMath-Tier-4-2025-07-01-PublicEpoch AI Benchmarking Hub0116 on the scale
    5. FrontierMath-Tier-4-v2-PrivateEpoch AI Benchmarking Hub0.12116 on the scale
    6. SimpleQA VerifiedEpoch AI Benchmarking Hub0.22115 on the scale
    7. FrontierMath-2025-02-28-PrivateEpoch AI Benchmarking Hub0.27115 on the scale
    8. FrontierMath-Tiers-1-3-v2-PrivateEpoch AI Benchmarking Hub0.47109 on the scale
    9. FrontierMath-2025-02-28-PublicEpoch AI Benchmarking Hub0.30106 on the scale
    10. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.8794 on the scale
    11. GPQA diamondEpoch AI Benchmarking Hub0.7583 on the scale
    12. MATH level 5Epoch AI Benchmarking Hub0.9881 on the scale
  155. 155google/gemini-3.5-flashminimal104.4131

    3 columns on 1 board, hardest first are the whole evidence behind 104.41. Each is a door to the column and everything else scored on it.

    1. Chess PuzzlesEpoch AI Benchmarking Hub0.27119 on the scale
    2. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.8094 on the scale
    3. GPQA diamondEpoch AI Benchmarking Hub0.8683 on the scale
  156. 156qwen/qwen3.5-397b-a17bunstated104.4031

    3 columns on 1 board, hardest first are the whole evidence behind 104.40. Each is a door to the column and everything else scored on it.

    1. FrontierMath-Tiers-1-3-v2-PrivateEpoch AI Benchmarking Hub0.29109 on the scale
    2. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.8994 on the scale
    3. GPQA diamondEpoch AI Benchmarking Hub0.8683 on the scale
  157. 157claude-opus-4-8not in the catalognone104.3131

    3 columns on 1 board, hardest first are the whole evidence behind 104.31. Each is a door to the column and everything else scored on it.

    1. Chess PuzzlesEpoch AI Benchmarking Hub0.19119 on the scale
    2. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.8494 on the scale
    3. GPQA diamondEpoch AI Benchmarking Hub0.8583 on the scale
  158. 158openai/gpt-5.4-minixhigh104.22231

    23 columns on 1 board, hardest first are the whole evidence behind 104.22. Each is a door to the column and everything else scored on it.

    1. typescriptLiveBench20122 on the scale
    2. tablejoinLiveBench49.38117 on the scale
    3. pythonLiveBench55109 on the scale
    4. plot_unscramblingLiveBench43.88106 on the scale
    5. integrals_with_gameLiveBench37104 on the scale
    6. consecutive_eventsLiveBench62.97102 on the scale
    7. zebra_puzzleLiveBench60.37102 on the scale
    8. javascriptLiveBench5099 on the scale
    9. logic_with_navigationLiveBench6096 on the scale
    10. simplifyLiveBench54.0792 on the scale
    11. connectionsLiveBench98.9891 on the scale
    12. theory_of_mindLiveBench76.9288 on the scale
    13. code_completionLiveBench75.5687 on the scale
    14. paraphraseLiveBench58.8886 on the scale
    15. summarizeLiveBench59.6385 on the scale
    16. typosLiveBench7077 on the scale
    17. code_generationLiveBench67.6976 on the scale
    18. story_generationLiveBench66.6374 on the scale
    19. olympiadLiveBench85.7372 on the scale
    20. spatialLiveBench8853 on the scale
    21. AMPS_HardLiveBench9747 on the scale
    22. math_compLiveBench94.1242 on the scale
    23. tablereformatLiveBench10041 on the scale
  159. 159gpt-5.4-2026-03-05not in the cataloglow104.1641

    4 columns on 1 board, hardest first are the whole evidence behind 104.16. Each is a door to the column and everything else scored on it.

    1. Mystery Game PuzzlesEpoch AI Benchmarking Hub0.17121 on the scale
    2. Chess PuzzlesEpoch AI Benchmarking Hub0.19119 on the scale
    3. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.8494 on the scale
    4. GPQA diamondEpoch AI Benchmarking Hub0.8583 on the scale
  160. 160grok-4-0709not in the catalogunstated104.1651

    5 columns on 1 board, hardest first are the whole evidence behind 104.16. Each is a door to the column and everything else scored on it.

    1. FrontierMath-Tier-4-2025-07-01-PrivateEpoch AI Benchmarking Hub0.02120 on the scale
    2. FrontierMath-Tier-4-2025-07-01-PublicEpoch AI Benchmarking Hub0116 on the scale
    3. FrontierMath-2025-02-28-PrivateEpoch AI Benchmarking Hub0.20115 on the scale
    4. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.8494 on the scale
    5. GPQA diamondEpoch AI Benchmarking Hub0.8783 on the scale
  161. 161qwen/qwen3-235b-a22b-thinking-2507unstated104.1041

    4 columns on 1 board, hardest first are the whole evidence behind 104.10. Each is a door to the column and everything else scored on it.

    1. Mystery Game PuzzlesEpoch AI Benchmarking Hub0.09121 on the scale
    2. SimpleQA VerifiedEpoch AI Benchmarking Hub0.40115 on the scale
    3. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.8794 on the scale
    4. GPQA diamondEpoch AI Benchmarking Hub0.8083 on the scale
  162. 162z-ai/glm-4.7unstated104.0741

    4 columns on 1 board, hardest first are the whole evidence behind 104.07. Each is a door to the column and everything else scored on it.

    1. Chess PuzzlesEpoch AI Benchmarking Hub0.21119 on the scale
    2. SimpleQA VerifiedEpoch AI Benchmarking Hub0.32115 on the scale
    3. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.8394 on the scale
    4. GPQA diamondEpoch AI Benchmarking Hub0.8383 on the scale
  163. 163claude-opus-4-5-20251101-32knot in the catalogunstated104.0581

    8 columns on 1 board, hardest first are the whole evidence behind 104.05. Each is a door to the column and everything else scored on it.

    1. FrontierMath-Tier-4-2025-07-01-PrivateEpoch AI Benchmarking Hub0.04120 on the scale
    2. Chess PuzzlesEpoch AI Benchmarking Hub0.05119 on the scale
    3. FrontierMath-Tier-4-v2-PrivateEpoch AI Benchmarking Hub0.05116 on the scale
    4. SimpleQA VerifiedEpoch AI Benchmarking Hub0.46115 on the scale
    5. FrontierMath-2025-02-28-PrivateEpoch AI Benchmarking Hub0.21115 on the scale
    6. FrontierMath-Tiers-1-3-v2-PrivateEpoch AI Benchmarking Hub0.34109 on the scale
    7. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.8694 on the scale
    8. GPQA diamondEpoch AI Benchmarking Hub0.8683 on the scale
  164. 164gpt-5-mini-2025-08-07not in the catalogmedium103.8391

    9 columns on 1 board, hardest first are the whole evidence behind 103.83. Each is a door to the column and everything else scored on it.

    1. Mystery Game PuzzlesEpoch AI Benchmarking Hub0.04121 on the scale
    2. FrontierMath-Tier-4-2025-07-01-PrivateEpoch AI Benchmarking Hub0.04120 on the scale
    3. FrontierMath-Tier-4-2025-07-01-PublicEpoch AI Benchmarking Hub0116 on the scale
    4. FrontierMath-2025-02-28-PrivateEpoch AI Benchmarking Hub0.20115 on the scale
    5. FrontierMath-2025-02-28-PublicEpoch AI Benchmarking Hub0.40106 on the scale
    6. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.7894 on the scale
    7. SWE-Bench verifiedEpoch AI Benchmarking Hub0.6584 on the scale
    8. GPQA diamondEpoch AI Benchmarking Hub0.7283 on the scale
    9. MATH level 5Epoch AI Benchmarking Hub0.9781 on the scale
  165. 165google/gemini-2.5-prounstated103.7391

    9 columns on 1 board, hardest first are the whole evidence behind 103.73. Each is a door to the column and everything else scored on it.

    1. FrontierMath-Tier-4-2025-07-01-PrivateEpoch AI Benchmarking Hub0.04120 on the scale
    2. FrontierMath-Tier-4-2025-07-01-PublicEpoch AI Benchmarking Hub0116 on the scale
    3. FrontierMath-Tier-4-v2-PrivateEpoch AI Benchmarking Hub0116 on the scale
    4. FrontierMath-2025-02-28-PrivateEpoch AI Benchmarking Hub0.14115 on the scale
    5. FrontierMath-Tiers-1-3-v2-PrivateEpoch AI Benchmarking Hub0.25109 on the scale
    6. FrontierMath-2025-02-28-PublicEpoch AI Benchmarking Hub0.40106 on the scale
    7. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.8494 on the scale
    8. SWE-Bench verifiedEpoch AI Benchmarking Hub0.5884 on the scale
    9. GPQA diamondEpoch AI Benchmarking Hub0.8583 on the scale
  166. 166qwen/qwen3.6-27bunstated103.72262

    26 columns on 2 boards, hardest first are the whole evidence behind 103.72. Each is a door to the column and everything else scored on it.

    1. typescriptLiveBench23.33122 on the scale
    2. tablejoinLiveBench42.85117 on the scale
    3. pythonLiveBench40109 on the scale
    4. FrontierMath-Tiers-1-3-v2-PrivateEpoch AI Benchmarking Hub0.35109 on the scale
    5. plot_unscramblingLiveBench42.75106 on the scale
    6. integrals_with_gameLiveBench52104 on the scale
    7. consecutive_eventsLiveBench70.39102 on the scale
    8. zebra_puzzleLiveBench53.75102 on the scale
    9. javascriptLiveBench54.5599 on the scale
    10. logic_with_navigationLiveBench6296 on the scale
    11. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.9194 on the scale
    12. simplifyLiveBench50.7392 on the scale
    13. connectionsLiveBench77.1791 on the scale
    14. theory_of_mindLiveBench65.3988 on the scale
    15. code_completionLiveBench71.7487 on the scale
    16. paraphraseLiveBench49.4386 on the scale
    17. summarizeLiveBench52.6285 on the scale
    18. GPQA diamondEpoch AI Benchmarking Hub0.8683 on the scale
    19. typosLiveBench7077 on the scale
    20. code_generationLiveBench71.8376 on the scale
    21. story_generationLiveBench60.1374 on the scale
    22. olympiadLiveBench82.3272 on the scale
    23. spatialLiveBench10053 on the scale
    24. AMPS_HardLiveBench9347 on the scale
    25. math_compLiveBench92.1642 on the scale
    26. tablereformatLiveBench98.0441 on the scale
  167. 167qwen/qwen3.5-397b-a17bnone103.5541

    4 columns on 1 board, hardest first are the whole evidence behind 103.55. Each is a door to the column and everything else scored on it.

    1. Mystery Game PuzzlesEpoch AI Benchmarking Hub0.18121 on the scale
    2. FrontierMath-Tiers-1-3-v2-PrivateEpoch AI Benchmarking Hub0.31109 on the scale
    3. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.8294 on the scale
    4. GPQA diamondEpoch AI Benchmarking Hub0.8683 on the scale
  168. 168o4-mini-2025-04-16not in the cataloghigh103.35121

    12 columns on 1 board, hardest first are the whole evidence behind 103.35. Each is a door to the column and everything else scored on it.

    1. Mystery Game PuzzlesEpoch AI Benchmarking Hub0.05121 on the scale
    2. FrontierMath-Tier-4-2025-07-01-PrivateEpoch AI Benchmarking Hub0.06120 on the scale
    3. Chess PuzzlesEpoch AI Benchmarking Hub0.13119 on the scale
    4. FrontierMath-Tier-4-2025-07-01-PublicEpoch AI Benchmarking Hub0116 on the scale
    5. FrontierMath-Tier-4-v2-PrivateEpoch AI Benchmarking Hub0.05116 on the scale
    6. SimpleQA VerifiedEpoch AI Benchmarking Hub0.19115 on the scale
    7. FrontierMath-2025-02-28-PrivateEpoch AI Benchmarking Hub0.25115 on the scale
    8. FrontierMath-Tiers-1-3-v2-PrivateEpoch AI Benchmarking Hub0.36109 on the scale
    9. FrontierMath-2025-02-28-PublicEpoch AI Benchmarking Hub0.30106 on the scale
    10. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.8294 on the scale
    11. GPQA diamondEpoch AI Benchmarking Hub0.8083 on the scale
    12. MATH level 5Epoch AI Benchmarking Hub0.9881 on the scale
  169. 169gemini-2.5-pro-preview-06-05not in the catalogunstated103.2751

    5 columns on 1 board, hardest first are the whole evidence behind 103.27. Each is a door to the column and everything else scored on it.

    1. FrontierMath-Tier-4-2025-07-01-PrivateEpoch AI Benchmarking Hub0.02120 on the scale
    2. FrontierMath-Tier-4-2025-07-01-PublicEpoch AI Benchmarking Hub0116 on the scale
    3. FrontierMath-2025-02-28-PrivateEpoch AI Benchmarking Hub0.10115 on the scale
    4. FrontierMath-2025-02-28-PublicEpoch AI Benchmarking Hub0.30106 on the scale
    5. GPQA diamondEpoch AI Benchmarking Hub0.8583 on the scale
  170. 170qwen/qwen3.7-plusnone103.1741

    4 columns on 1 board, hardest first are the whole evidence behind 103.17. Each is a door to the column and everything else scored on it.

    1. Mystery Game PuzzlesEpoch AI Benchmarking Hub0.17121 on the scale
    2. FrontierMath-Tiers-1-3-v2-PrivateEpoch AI Benchmarking Hub0.34109 on the scale
    3. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.8094 on the scale
    4. GPQA diamondEpoch AI Benchmarking Hub0.8283 on the scale
  171. 171x-ai/grok-4.3unstated103.07231

    23 columns on 1 board, hardest first are the whole evidence behind 103.07. Each is a door to the column and everything else scored on it.

    1. typescriptLiveBench13.33122 on the scale
    2. tablejoinLiveBench41.25117 on the scale
    3. pythonLiveBench15109 on the scale
    4. plot_unscramblingLiveBench48.74106 on the scale
    5. integrals_with_gameLiveBench63104 on the scale
    6. consecutive_eventsLiveBench28.03102 on the scale
    7. zebra_puzzleLiveBench57.75102 on the scale
    8. javascriptLiveBench27.2799 on the scale
    9. logic_with_navigationLiveBench6696 on the scale
    10. simplifyLiveBench57.6092 on the scale
    11. connectionsLiveBench9491 on the scale
    12. theory_of_mindLiveBench61.5488 on the scale
    13. code_completionLiveBench65.2287 on the scale
    14. paraphraseLiveBench64.3886 on the scale
    15. summarizeLiveBench58.4285 on the scale
    16. typosLiveBench7877 on the scale
    17. code_generationLiveBench74.6576 on the scale
    18. story_generationLiveBench70.6074 on the scale
    19. olympiadLiveBench82.2672 on the scale
    20. spatialLiveBench9853 on the scale
    21. AMPS_HardLiveBench9747 on the scale
    22. math_compLiveBench95.1042 on the scale
    23. tablereformatLiveBench98.0441 on the scale
  172. 172claude-sonnet-4-6not in the catalogmedium103.0131

    3 columns on 1 board, hardest first are the whole evidence behind 103.01. Each is a door to the column and everything else scored on it.

    1. Chess PuzzlesEpoch AI Benchmarking Hub0.16119 on the scale
    2. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.8294 on the scale
    3. GPQA diamondEpoch AI Benchmarking Hub0.8383 on the scale
  173. 174deepseek/deepseek-v4-flashunstated102.96231

    23 columns on 1 board, hardest first are the whole evidence behind 102.96. Each is a door to the column and everything else scored on it.

    1. typescriptLiveBench23.33122 on the scale
    2. tablejoinLiveBench46.12117 on the scale
    3. pythonLiveBench35109 on the scale
    4. plot_unscramblingLiveBench46.87106 on the scale
    5. integrals_with_gameLiveBench37104 on the scale
    6. consecutive_eventsLiveBench59.91102 on the scale
    7. zebra_puzzleLiveBench49.25102 on the scale
    8. javascriptLiveBench54.5599 on the scale
    9. logic_with_navigationLiveBench6496 on the scale
    10. simplifyLiveBench54.0592 on the scale
    11. connectionsLiveBench89.5091 on the scale
    12. theory_of_mindLiveBench73.0888 on the scale
    13. code_completionLiveBench65.2287 on the scale
    14. paraphraseLiveBench62.3886 on the scale
    15. summarizeLiveBench68.8585 on the scale
    16. typosLiveBench7477 on the scale
    17. code_generationLiveBench73.2476 on the scale
    18. story_generationLiveBench67.2774 on the scale
    19. olympiadLiveBench86.5372 on the scale
    20. spatialLiveBench9653 on the scale
    21. AMPS_HardLiveBench9847 on the scale
    22. math_compLiveBench97.0642 on the scale
    23. tablereformatLiveBench98.0441 on the scale
  174. 173o3-2025-04-16not in the cataloghigh102.96111

    11 columns on 1 board, hardest first are the whole evidence behind 102.96. Each is a door to the column and everything else scored on it.

    1. Mystery Game PuzzlesEpoch AI Benchmarking Hub0.29121 on the scale
    2. FrontierMath-Tier-4-2025-07-01-PrivateEpoch AI Benchmarking Hub0.02120 on the scale
    3. Chess PuzzlesEpoch AI Benchmarking Hub0.36119 on the scale
    4. FrontierMath-Tier-4-2025-07-01-PublicEpoch AI Benchmarking Hub0116 on the scale
    5. SimpleQA VerifiedEpoch AI Benchmarking Hub0.49115 on the scale
    6. FrontierMath-2025-02-28-PrivateEpoch AI Benchmarking Hub0.19115 on the scale
    7. FrontierMath-Tiers-1-3-v2-PrivateEpoch AI Benchmarking Hub0.33109 on the scale
    8. FrontierMath-2025-02-28-PublicEpoch AI Benchmarking Hub0.10106 on the scale
    9. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.8494 on the scale
    10. GPQA diamondEpoch AI Benchmarking Hub0.8283 on the scale
    11. MATH level 5Epoch AI Benchmarking Hub0.9881 on the scale
  175. 175kimi-k2-thinking-turbonot in the catalogunstated102.4631

    3 columns on 1 board, hardest first are the whole evidence behind 102.46. Each is a door to the column and everything else scored on it.

    1. FrontierMath-2025-02-28-PublicEpoch AI Benchmarking Hub0.20106 on the scale
    2. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.8394 on the scale
    3. GPQA diamondEpoch AI Benchmarking Hub0.8483 on the scale
  176. 176o3-mini-2025-01-31not in the cataloghigh102.45121

    12 columns on 1 board, hardest first are the whole evidence behind 102.45. Each is a door to the column and everything else scored on it.

    1. Mystery Game PuzzlesEpoch AI Benchmarking Hub0.07121 on the scale
    2. FrontierMath-Tier-4-2025-07-01-PrivateEpoch AI Benchmarking Hub0.04120 on the scale
    3. Chess PuzzlesEpoch AI Benchmarking Hub0.15119 on the scale
    4. FrontierMath-Tier-4-2025-07-01-PublicEpoch AI Benchmarking Hub0116 on the scale
    5. FrontierMath-Tier-4-v2-PrivateEpoch AI Benchmarking Hub0116 on the scale
    6. SimpleQA VerifiedEpoch AI Benchmarking Hub0.15115 on the scale
    7. FrontierMath-2025-02-28-PrivateEpoch AI Benchmarking Hub0.12115 on the scale
    8. FrontierMath-Tiers-1-3-v2-PrivateEpoch AI Benchmarking Hub0.19109 on the scale
    9. FrontierMath-2025-02-28-PublicEpoch AI Benchmarking Hub0.40106 on the scale
    10. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.7794 on the scale
    11. GPQA diamondEpoch AI Benchmarking Hub0.7783 on the scale
    12. MATH level 5Epoch AI Benchmarking Hub0.9681 on the scale
  177. 177gemini-2.5-pro-preview-05-06not in the catalogunstated102.4332

    3 columns on 2 boards, hardest first are the whole evidence behind 102.43. Each is a door to the column and everything else scored on it.

    1. polyglot pass rateAider polyglot76.9097 on the scale
    2. GPQA diamondEpoch AI Benchmarking Hub0.6783 on the scale
    3. MATH level 5Epoch AI Benchmarking Hub0.9681 on the scale
  178. 178claude-sonnet-4-6not in the cataloghigh102.3041

    4 columns on 1 board, hardest first are the whole evidence behind 102.30. Each is a door to the column and everything else scored on it.

    1. Chess PuzzlesEpoch AI Benchmarking Hub0.19119 on the scale
    2. SimpleQA VerifiedEpoch AI Benchmarking Hub0.35115 on the scale
    3. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.7694 on the scale
    4. GPQA diamondEpoch AI Benchmarking Hub0.8383 on the scale
  179. 179qwen/qwen3.7-flashunstated102.1641

    4 columns on 1 board, hardest first are the whole evidence behind 102.16. Each is a door to the column and everything else scored on it.

    1. Mystery Game PuzzlesEpoch AI Benchmarking Hub0.15121 on the scale
    2. FrontierMath-Tiers-1-3-v2-PrivateEpoch AI Benchmarking Hub0.19109 on the scale
    3. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.8794 on the scale
    4. GPQA diamondEpoch AI Benchmarking Hub0.8283 on the scale
  180. 180google/gemini-3.1-flash-litehigh102.1331

    3 columns on 1 board, hardest first are the whole evidence behind 102.13. Each is a door to the column and everything else scored on it.

    1. FrontierMath-Tiers-1-3-v2-PrivateEpoch AI Benchmarking Hub0.28109 on the scale
    2. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.8094 on the scale
    3. GPQA diamondEpoch AI Benchmarking Hub0.8283 on the scale
  181. 181qwen/qwen3.6-35b-a3bunstated102.0431

    3 columns on 1 board, hardest first are the whole evidence behind 102.04. Each is a door to the column and everything else scored on it.

    1. FrontierMath-Tiers-1-3-v2-PrivateEpoch AI Benchmarking Hub0.18109 on the scale
    2. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.8794 on the scale
    3. GPQA diamondEpoch AI Benchmarking Hub0.8483 on the scale
  182. 182o4-mini-2025-04-16not in the catalogmedium101.9381

    8 columns on 1 board, hardest first are the whole evidence behind 101.93. Each is a door to the column and everything else scored on it.

    1. FrontierMath-Tier-4-2025-07-01-PrivateEpoch AI Benchmarking Hub0.02120 on the scale
    2. Chess PuzzlesEpoch AI Benchmarking Hub0.22119 on the scale
    3. FrontierMath-Tier-4-2025-07-01-PublicEpoch AI Benchmarking Hub0116 on the scale
    4. FrontierMath-2025-02-28-PrivateEpoch AI Benchmarking Hub0.19115 on the scale
    5. FrontierMath-Tiers-1-3-v2-PrivateEpoch AI Benchmarking Hub0.29109 on the scale
    6. FrontierMath-2025-02-28-PublicEpoch AI Benchmarking Hub0.20106 on the scale
    7. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.7394 on the scale
    8. GPQA diamondEpoch AI Benchmarking Hub0.7883 on the scale
  183. 183openai/gpt-5.6-lunalow101.9251

    5 columns on 1 board, hardest first are the whole evidence behind 101.92. Each is a door to the column and everything else scored on it.

    1. Mystery Game PuzzlesEpoch AI Benchmarking Hub0.17121 on the scale
    2. Chess PuzzlesEpoch AI Benchmarking Hub0.17119 on the scale
    3. FrontierMath-Tiers-1-3-v2-PrivateEpoch AI Benchmarking Hub0.41109 on the scale
    4. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.6794 on the scale
    5. GPQA diamondEpoch AI Benchmarking Hub0.8283 on the scale
  184. 184qwen/qwen3-235b-a22b-thinking-2507not in the catalogunstated101.2941

    4 columns on 1 board, hardest first are the whole evidence behind 101.29. Each is a door to the column and everything else scored on it.

    1. FrontierMath-Tier-4-2025-07-01-PrivateEpoch AI Benchmarking Hub0120 on the scale
    2. FrontierMath-Tier-4-2025-07-01-PublicEpoch AI Benchmarking Hub0116 on the scale
    3. FrontierMath-2025-02-28-PrivateEpoch AI Benchmarking Hub0.08115 on the scale
    4. FrontierMath-2025-02-28-PublicEpoch AI Benchmarking Hub0.20106 on the scale
  185. 185claude-sonnet-4-5-20250929-59knot in the catalogunstated101.2651

    5 columns on 1 board, hardest first are the whole evidence behind 101.26. Each is a door to the column and everything else scored on it.

    1. Chess PuzzlesEpoch AI Benchmarking Hub0.10119 on the scale
    2. SimpleQA VerifiedEpoch AI Benchmarking Hub0.31115 on the scale
    3. FrontierMath-2025-02-28-PrivateEpoch AI Benchmarking Hub0.13115 on the scale
    4. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.7894 on the scale
    5. GPQA diamondEpoch AI Benchmarking Hub0.8283 on the scale
  186. 186claude-sonnet-4-5-20250929-32knot in the catalogunstated101.1881

    8 columns on 1 board, hardest first are the whole evidence behind 101.18. Each is a door to the column and everything else scored on it.

    1. FrontierMath-Tier-4-2025-07-01-PrivateEpoch AI Benchmarking Hub0.04120 on the scale
    2. Chess PuzzlesEpoch AI Benchmarking Hub0.10119 on the scale
    3. FrontierMath-Tier-4-v2-PrivateEpoch AI Benchmarking Hub0.02116 on the scale
    4. FrontierMath-2025-02-28-PrivateEpoch AI Benchmarking Hub0.15115 on the scale
    5. FrontierMath-Tiers-1-3-v2-PrivateEpoch AI Benchmarking Hub0.24109 on the scale
    6. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.7894 on the scale
    7. GPQA diamondEpoch AI Benchmarking Hub0.8283 on the scale
    8. MATH level 5Epoch AI Benchmarking Hub0.9881 on the scale
  187. 187claude-sonnet-4-6not in the catalogmax101.1741

    4 columns on 1 board, hardest first are the whole evidence behind 101.17. Each is a door to the column and everything else scored on it.

    1. Chess PuzzlesEpoch AI Benchmarking Hub0.23119 on the scale
    2. SimpleQA VerifiedEpoch AI Benchmarking Hub0.33115 on the scale
    3. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.7194 on the scale
    4. GPQA diamondEpoch AI Benchmarking Hub0.7983 on the scale
  188. 188o3-2025-04-16not in the catalogmedium101.1181

    8 columns on 1 board, hardest first are the whole evidence behind 101.11. Each is a door to the column and everything else scored on it.

    1. Mystery Game PuzzlesEpoch AI Benchmarking Hub0.23121 on the scale
    2. Chess PuzzlesEpoch AI Benchmarking Hub0.37119 on the scale
    3. FrontierMath-2025-02-28-PrivateEpoch AI Benchmarking Hub0.17115 on the scale
    4. FrontierMath-Tiers-1-3-v2-PrivateEpoch AI Benchmarking Hub0.30109 on the scale
    5. FrontierMath-2025-02-28-PublicEpoch AI Benchmarking Hub0106 on the scale
    6. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.8494 on the scale
    7. SWE-Bench verifiedEpoch AI Benchmarking Hub0.6284 on the scale
    8. GPQA diamondEpoch AI Benchmarking Hub0.8183 on the scale
  189. 189openai/gpt-5.6-solnone100.9841

    4 columns on 1 board, hardest first are the whole evidence behind 100.98. Each is a door to the column and everything else scored on it.

    1. Mystery Game PuzzlesEpoch AI Benchmarking Hub0.33121 on the scale
    2. Chess PuzzlesEpoch AI Benchmarking Hub0.07119 on the scale
    3. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.6994 on the scale
    4. GPQA diamondEpoch AI Benchmarking Hub0.8383 on the scale
  190. 190qwen/qwen3.6-flashunstated100.9591

    9 columns on 1 board, hardest first are the whole evidence behind 100.95. Each is a door to the column and everything else scored on it.

    1. Mystery Game PuzzlesEpoch AI Benchmarking Hub0.12121 on the scale
    2. FrontierMath-Tier-4-2025-07-01-PrivateEpoch AI Benchmarking Hub0120 on the scale
    3. Chess PuzzlesEpoch AI Benchmarking Hub0.12119 on the scale
    4. SimpleQA VerifiedEpoch AI Benchmarking Hub0.16115 on the scale
    5. FrontierMath-2025-02-28-PrivateEpoch AI Benchmarking Hub0.10115 on the scale
    6. FrontierMath-Tiers-1-3-v2-PrivateEpoch AI Benchmarking Hub0.17109 on the scale
    7. FrontierMath-2025-02-28-PublicEpoch AI Benchmarking Hub0.20106 on the scale
    8. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.8494 on the scale
    9. GPQA diamondEpoch AI Benchmarking Hub0.8383 on the scale
  191. 191gpt-5.1-2025-11-13not in the cataloglow100.6441

    4 columns on 1 board, hardest first are the whole evidence behind 100.64. Each is a door to the column and everything else scored on it.

    1. Mystery Game PuzzlesEpoch AI Benchmarking Hub0.19121 on the scale
    2. Chess PuzzlesEpoch AI Benchmarking Hub0.23119 on the scale
    3. FrontierMath-2025-02-28-PrivateEpoch AI Benchmarking Hub0.17115 on the scale
    4. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.6494 on the scale
  192. 192o4-mini-2025-04-16not in the cataloglow100.6171

    7 columns on 1 board, hardest first are the whole evidence behind 100.61. Each is a door to the column and everything else scored on it.

    1. Chess PuzzlesEpoch AI Benchmarking Hub0.15119 on the scale
    2. SimpleQA VerifiedEpoch AI Benchmarking Hub0.20115 on the scale
    3. FrontierMath-2025-02-28-PrivateEpoch AI Benchmarking Hub0.11115 on the scale
    4. FrontierMath-Tiers-1-3-v2-PrivateEpoch AI Benchmarking Hub0.16109 on the scale
    5. FrontierMath-2025-02-28-PublicEpoch AI Benchmarking Hub0.30106 on the scale
    6. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.5894 on the scale
    7. GPQA diamondEpoch AI Benchmarking Hub0.7583 on the scale
  193. 193qwen/qwen3.7-flashnone100.5441

    4 columns on 1 board, hardest first are the whole evidence behind 100.54. Each is a door to the column and everything else scored on it.

    1. Mystery Game PuzzlesEpoch AI Benchmarking Hub0.14121 on the scale
    2. FrontierMath-Tiers-1-3-v2-PrivateEpoch AI Benchmarking Hub0.19109 on the scale
    3. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.7894 on the scale
    4. GPQA diamondEpoch AI Benchmarking Hub0.8183 on the scale
  194. 194gpt-5-nano-2025-08-07not in the cataloghigh100.45121

    12 columns on 1 board, hardest first are the whole evidence behind 100.45. Each is a door to the column and everything else scored on it.

    1. Mystery Game PuzzlesEpoch AI Benchmarking Hub0.08121 on the scale
    2. FrontierMath-Tier-4-2025-07-01-PrivateEpoch AI Benchmarking Hub0120 on the scale
    3. Chess PuzzlesEpoch AI Benchmarking Hub0.22119 on the scale
    4. FrontierMath-Tier-4-2025-07-01-PublicEpoch AI Benchmarking Hub0116 on the scale
    5. FrontierMath-Tier-4-v2-PrivateEpoch AI Benchmarking Hub0.02116 on the scale
    6. SimpleQA VerifiedEpoch AI Benchmarking Hub0.12115 on the scale
    7. FrontierMath-2025-02-28-PrivateEpoch AI Benchmarking Hub0.08115 on the scale
    8. FrontierMath-Tiers-1-3-v2-PrivateEpoch AI Benchmarking Hub0.20109 on the scale
    9. FrontierMath-2025-02-28-PublicEpoch AI Benchmarking Hub0.20106 on the scale
    10. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.8194 on the scale
    11. GPQA diamondEpoch AI Benchmarking Hub0.6983 on the scale
    12. MATH level 5Epoch AI Benchmarking Hub0.9581 on the scale
  195. 195qwen/qwen3.6-27bnone100.3241

    4 columns on 1 board, hardest first are the whole evidence behind 100.32. Each is a door to the column and everything else scored on it.

    1. Mystery Game PuzzlesEpoch AI Benchmarking Hub0.07121 on the scale
    2. FrontierMath-Tiers-1-3-v2-PrivateEpoch AI Benchmarking Hub0.34109 on the scale
    3. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.6794 on the scale
    4. GPQA diamondEpoch AI Benchmarking Hub0.8583 on the scale
  196. 196qwen/qwen3.6-35b-a3bnone100.2241

    4 columns on 1 board, hardest first are the whole evidence behind 100.22. Each is a door to the column and everything else scored on it.

    1. Mystery Game PuzzlesEpoch AI Benchmarking Hub0.22121 on the scale
    2. FrontierMath-Tiers-1-3-v2-PrivateEpoch AI Benchmarking Hub0.20109 on the scale
    3. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.6994 on the scale
    4. GPQA diamondEpoch AI Benchmarking Hub0.8583 on the scale
  197. 197moonshotai/kimi-k3low100.1241

    4 columns on 1 board, hardest first are the whole evidence behind 100.12. Each is a door to the column and everything else scored on it.

    1. Mystery Game PuzzlesEpoch AI Benchmarking Hub0.12121 on the scale
    2. Chess PuzzlesEpoch AI Benchmarking Hub0.18119 on the scale
    3. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.6994 on the scale
    4. GPQA diamondEpoch AI Benchmarking Hub0.8583 on the scale
  198. 198qwen3-max-2025-09-23not in the catalogunstated100.0361

    6 columns on 1 board, hardest first are the whole evidence behind 100.03. Each is a door to the column and everything else scored on it.

    1. Mystery Game PuzzlesEpoch AI Benchmarking Hub0.05121 on the scale
    2. SimpleQA VerifiedEpoch AI Benchmarking Hub0.49115 on the scale
    3. FrontierMath-Tiers-1-3-v2-PrivateEpoch AI Benchmarking Hub0.19109 on the scale
    4. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.7394 on the scale
    5. GPQA diamondEpoch AI Benchmarking Hub0.7383 on the scale
    6. MATH level 5Epoch AI Benchmarking Hub0.9781 on the scale
  199. 199google/gemini-3.5-flash-litehigh99.97282

    28 columns on 2 boards, hardest first are the whole evidence behind 99.97. Each is a door to the column and everything else scored on it.

    1. typescriptLiveBench26.67122 on the scale
    2. Chess PuzzlesEpoch AI Benchmarking Hub0.16119 on the scale
    3. tablejoinLiveBench40.62117 on the scale
    4. FrontierMath-Tier-4-v2-PrivateEpoch AI Benchmarking Hub0116 on the scale
    5. pythonLiveBench50109 on the scale
    6. FrontierMath-Tiers-1-3-v2-PrivateEpoch AI Benchmarking Hub0.26109 on the scale
    7. plot_unscramblingLiveBench49.46106 on the scale
    8. integrals_with_gameLiveBench26104 on the scale
    9. consecutive_eventsLiveBench21.09102 on the scale
    10. zebra_puzzleLiveBench32.75102 on the scale
    11. javascriptLiveBench59.0999 on the scale
    12. logic_with_navigationLiveBench6896 on the scale
    13. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.7194 on the scale
    14. simplifyLiveBench68.0292 on the scale
    15. connectionsLiveBench9291 on the scale
    16. theory_of_mindLiveBench5088 on the scale
    17. code_completionLiveBench76.0987 on the scale
    18. paraphraseLiveBench6586 on the scale
    19. summarizeLiveBench68.4785 on the scale
    20. GPQA diamondEpoch AI Benchmarking Hub0.8383 on the scale
    21. typosLiveBench7477 on the scale
    22. code_generationLiveBench76.0676 on the scale
    23. story_generationLiveBench67.4774 on the scale
    24. olympiadLiveBench81.8072 on the scale
    25. spatialLiveBench9053 on the scale
    26. AMPS_HardLiveBench9547 on the scale
    27. math_compLiveBench92.1642 on the scale
    28. tablereformatLiveBench98.0441 on the scale
  200. 200z-ai/glm-5unstated99.9671

    7 columns on 1 board, hardest first are the whole evidence behind 99.96. Each is a door to the column and everything else scored on it.

    1. FrontierMath-Tier-4-2025-07-01-PrivateEpoch AI Benchmarking Hub0.02120 on the scale
    2. FrontierMath-Tier-4-2025-07-01-PublicEpoch AI Benchmarking Hub0116 on the scale
    3. FrontierMath-2025-02-28-PrivateEpoch AI Benchmarking Hub0.16115 on the scale
    4. FrontierMath-2025-02-28-PublicEpoch AI Benchmarking Hub0.02106 on the scale
    5. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.8094 on the scale
    6. SWE-Bench verifiedEpoch AI Benchmarking Hub0.7284 on the scale
    7. GPQA diamondEpoch AI Benchmarking Hub0.8883 on the scale
  201. 201claude-opus-4-5-20251101not in the catalogunstated99.9271

    7 columns on 1 board, hardest first are the whole evidence behind 99.92. Each is a door to the column and everything else scored on it.

    1. FrontierMath-Tier-4-2025-07-01-PrivateEpoch AI Benchmarking Hub0.04120 on the scale
    2. Chess PuzzlesEpoch AI Benchmarking Hub0.05119 on the scale
    3. FrontierMath-2025-02-28-PrivateEpoch AI Benchmarking Hub0.21115 on the scale
    4. FrontierMath-2025-02-28-PublicEpoch AI Benchmarking Hub0.20106 on the scale
    5. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.4894 on the scale
    6. SWE-Bench verifiedEpoch AI Benchmarking Hub0.7784 on the scale
    7. GPQA diamondEpoch AI Benchmarking Hub0.8183 on the scale
  202. 202gpt-5.5-instantnot in the catalogunstated99.8941

    4 columns on 1 board, hardest first are the whole evidence behind 99.89. Each is a door to the column and everything else scored on it.

    1. FrontierMath-Tier-4-v2-PrivateEpoch AI Benchmarking Hub0.02116 on the scale
    2. FrontierMath-Tiers-1-3-v2-PrivateEpoch AI Benchmarking Hub0.26109 on the scale
    3. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.6894 on the scale
    4. GPQA diamondEpoch AI Benchmarking Hub0.8383 on the scale
  203. 203qwen3.5-flashnot in the catalogunstated99.5891

    9 columns on 1 board, hardest first are the whole evidence behind 99.58. Each is a door to the column and everything else scored on it.

    1. Mystery Game PuzzlesEpoch AI Benchmarking Hub0.20121 on the scale
    2. FrontierMath-Tier-4-2025-07-01-PrivateEpoch AI Benchmarking Hub0120 on the scale
    3. Chess PuzzlesEpoch AI Benchmarking Hub0.14119 on the scale
    4. SimpleQA VerifiedEpoch AI Benchmarking Hub0.20115 on the scale
    5. FrontierMath-2025-02-28-PrivateEpoch AI Benchmarking Hub0.06115 on the scale
    6. FrontierMath-Tiers-1-3-v2-PrivateEpoch AI Benchmarking Hub0.09109 on the scale
    7. FrontierMath-2025-02-28-PublicEpoch AI Benchmarking Hub0.10106 on the scale
    8. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.8494 on the scale
    9. GPQA diamondEpoch AI Benchmarking Hub0.8283 on the scale
  204. 204o3-2025-04-16not in the cataloglow99.3761

    6 columns on 1 board, hardest first are the whole evidence behind 99.37. Each is a door to the column and everything else scored on it.

    1. Chess PuzzlesEpoch AI Benchmarking Hub0.36119 on the scale
    2. FrontierMath-2025-02-28-PrivateEpoch AI Benchmarking Hub0.10115 on the scale
    3. FrontierMath-Tiers-1-3-v2-PrivateEpoch AI Benchmarking Hub0.19109 on the scale
    4. FrontierMath-2025-02-28-PublicEpoch AI Benchmarking Hub0.10106 on the scale
    5. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.6094 on the scale
    6. GPQA diamondEpoch AI Benchmarking Hub0.8083 on the scale
  205. 205claude-sonnet-4-20250514-59knot in the catalogunstated99.1731

    3 columns on 1 board, hardest first are the whole evidence behind 99.17. Each is a door to the column and everything else scored on it.

    1. FrontierMath-Tier-4-2025-07-01-PublicEpoch AI Benchmarking Hub0116 on the scale
    2. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.6994 on the scale
    3. GPQA diamondEpoch AI Benchmarking Hub0.7883 on the scale
  206. 206gpt-5-nano-2025-08-07not in the catalogmedium99.0381

    8 columns on 1 board, hardest first are the whole evidence behind 99.03. Each is a door to the column and everything else scored on it.

    1. Mystery Game PuzzlesEpoch AI Benchmarking Hub0.09121 on the scale
    2. FrontierMath-Tier-4-2025-07-01-PrivateEpoch AI Benchmarking Hub0.02120 on the scale
    3. FrontierMath-Tier-4-2025-07-01-PublicEpoch AI Benchmarking Hub0116 on the scale
    4. FrontierMath-2025-02-28-PrivateEpoch AI Benchmarking Hub0.07115 on the scale
    5. FrontierMath-2025-02-28-PublicEpoch AI Benchmarking Hub0.10106 on the scale
    6. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.7494 on the scale
    7. GPQA diamondEpoch AI Benchmarking Hub0.6783 on the scale
    8. MATH level 5Epoch AI Benchmarking Hub0.9581 on the scale
  207. 207deepseek/deepseek-r1-0528unstated98.8141

    4 columns on 1 board, hardest first are the whole evidence behind 98.81. Each is a door to the column and everything else scored on it.

    1. FrontierMath-Tier-4-2025-07-01-PublicEpoch AI Benchmarking Hub0116 on the scale
    2. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.6694 on the scale
    3. GPQA diamondEpoch AI Benchmarking Hub0.7683 on the scale
    4. MATH level 5Epoch AI Benchmarking Hub0.9781 on the scale
  208. 208google/gemini-3.5-flash-litelow98.6841

    4 columns on 1 board, hardest first are the whole evidence behind 98.68. Each is a door to the column and everything else scored on it.

    1. Mystery Game PuzzlesEpoch AI Benchmarking Hub0.19121 on the scale
    2. Chess PuzzlesEpoch AI Benchmarking Hub0.21119 on the scale
    3. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.6094 on the scale
    4. GPQA diamondEpoch AI Benchmarking Hub0.7683 on the scale
  209. 209gpt-5.4-nano-2026-03-17not in the cataloglow98.4051

    5 columns on 1 board, hardest first are the whole evidence behind 98.40. Each is a door to the column and everything else scored on it.

    1. Mystery Game PuzzlesEpoch AI Benchmarking Hub0.03121 on the scale
    2. Chess PuzzlesEpoch AI Benchmarking Hub0.20119 on the scale
    3. FrontierMath-Tiers-1-3-v2-PrivateEpoch AI Benchmarking Hub0.20109 on the scale
    4. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.6994 on the scale
    5. GPQA diamondEpoch AI Benchmarking Hub0.7283 on the scale
  210. 210o1-2024-12-17not in the cataloghigh98.2792

    9 columns on 2 boards, hardest first are the whole evidence behind 98.27. Each is a door to the column and everything else scored on it.

    1. Chess PuzzlesEpoch AI Benchmarking Hub0.10119 on the scale
    2. SimpleQA VerifiedEpoch AI Benchmarking Hub0.41115 on the scale
    3. FrontierMath-2025-02-28-PrivateEpoch AI Benchmarking Hub0.09115 on the scale
    4. FrontierMath-Tiers-1-3-v2-PrivateEpoch AI Benchmarking Hub0.15109 on the scale
    5. FrontierMath-2025-02-28-PublicEpoch AI Benchmarking Hub0106 on the scale
    6. polyglot pass rateAider polyglot61.7097 on the scale
    7. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.7394 on the scale
    8. GPQA diamondEpoch AI Benchmarking Hub0.7783 on the scale
    9. MATH level 5Epoch AI Benchmarking Hub0.9581 on the scale
  211. 211o3-mini-2025-01-31not in the catalogmedium97.9471

    7 columns on 1 board, hardest first are the whole evidence behind 97.94. Each is a door to the column and everything else scored on it.

    1. Chess PuzzlesEpoch AI Benchmarking Hub0.11119 on the scale
    2. FrontierMath-2025-02-28-PrivateEpoch AI Benchmarking Hub0.08115 on the scale
    3. FrontierMath-Tiers-1-3-v2-PrivateEpoch AI Benchmarking Hub0.11109 on the scale
    4. FrontierMath-2025-02-28-PublicEpoch AI Benchmarking Hub0.11106 on the scale
    5. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.6494 on the scale
    6. GPQA diamondEpoch AI Benchmarking Hub0.7483 on the scale
    7. MATH level 5Epoch AI Benchmarking Hub0.9581 on the scale
  212. 212o1-2024-12-17not in the catalogmedium97.8151

    5 columns on 1 board, hardest first are the whole evidence behind 97.81. Each is a door to the column and everything else scored on it.

    1. Chess PuzzlesEpoch AI Benchmarking Hub0.08119 on the scale
    2. FrontierMath-Tiers-1-3-v2-PrivateEpoch AI Benchmarking Hub0.10109 on the scale
    3. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.7394 on the scale
    4. GPQA diamondEpoch AI Benchmarking Hub0.7683 on the scale
    5. MATH level 5Epoch AI Benchmarking Hub0.9481 on the scale
  213. 213seed-1.6not in the catalogunstated97.7041

    4 columns on 1 board, hardest first are the whole evidence behind 97.70. Each is a door to the column and everything else scored on it.

    1. Chess PuzzlesEpoch AI Benchmarking Hub0.05119 on the scale
    2. SimpleQA VerifiedEpoch AI Benchmarking Hub0.17115 on the scale
    3. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.6994 on the scale
    4. GPQA diamondEpoch AI Benchmarking Hub0.7883 on the scale
  214. 214claude-opus-4-20250514-27knot in the catalogunstated97.6941

    4 columns on 1 board, hardest first are the whole evidence behind 97.69. Each is a door to the column and everything else scored on it.

    1. FrontierMath-Tier-4-2025-07-01-PrivateEpoch AI Benchmarking Hub0.04120 on the scale
    2. FrontierMath-Tier-4-2025-07-01-PublicEpoch AI Benchmarking Hub0116 on the scale
    3. FrontierMath-2025-02-28-PrivateEpoch AI Benchmarking Hub0.04115 on the scale
    4. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.6494 on the scale
  215. 215claude-opus-4-1-20250805-27knot in the catalogunstated97.2951

    5 columns on 1 board, hardest first are the whole evidence behind 97.29. Each is a door to the column and everything else scored on it.

    1. FrontierMath-Tier-4-2025-07-01-PrivateEpoch AI Benchmarking Hub0.04120 on the scale
    2. FrontierMath-2025-02-28-PrivateEpoch AI Benchmarking Hub0.07115 on the scale
    3. FrontierMath-2025-02-28-PublicEpoch AI Benchmarking Hub0106 on the scale
    4. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.6994 on the scale
    5. GPQA diamondEpoch AI Benchmarking Hub0.7783 on the scale
  216. 216openai/gpt-5.5none97.1141

    4 columns on 1 board, hardest first are the whole evidence behind 97.11. Each is a door to the column and everything else scored on it.

    1. Mystery Game PuzzlesEpoch AI Benchmarking Hub0.18121 on the scale
    2. Chess PuzzlesEpoch AI Benchmarking Hub0.09119 on the scale
    3. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.5894 on the scale
    4. GPQA diamondEpoch AI Benchmarking Hub0.7783 on the scale
  217. 217grok-3-mini-betanot in the cataloghigh97.0372

    7 columns on 2 boards, hardest first are the whole evidence behind 97.03. Each is a door to the column and everything else scored on it.

    1. FrontierMath-Tier-4-2025-07-01-PublicEpoch AI Benchmarking Hub0116 on the scale
    2. FrontierMath-2025-02-28-PrivateEpoch AI Benchmarking Hub0.06115 on the scale
    3. FrontierMath-2025-02-28-PublicEpoch AI Benchmarking Hub0106 on the scale
    4. polyglot pass rateAider polyglot49.3097 on the scale
    5. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.7894 on the scale
    6. GPQA diamondEpoch AI Benchmarking Hub0.7583 on the scale
    7. MATH level 5Epoch AI Benchmarking Hub0.8881 on the scale
  218. 218gpt-5.2-2025-12-11not in the catalognone96.5341

    4 columns on 1 board, hardest first are the whole evidence behind 96.53. Each is a door to the column and everything else scored on it.

    1. Mystery Game PuzzlesEpoch AI Benchmarking Hub0.14121 on the scale
    2. Chess PuzzlesEpoch AI Benchmarking Hub0.02119 on the scale
    3. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.6294 on the scale
    4. GPQA diamondEpoch AI Benchmarking Hub0.7383 on the scale
  219. 219claude-opus-4-1-20250805-16knot in the catalogunstated96.3931

    3 columns on 1 board, hardest first are the whole evidence behind 96.39. Each is a door to the column and everything else scored on it.

    1. FrontierMath-2025-02-28-PublicEpoch AI Benchmarking Hub0106 on the scale
    2. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.6494 on the scale
    3. GPQA diamondEpoch AI Benchmarking Hub0.7783 on the scale
  220. 220z-ai/glm-5.2none96.2251

    5 columns on 1 board, hardest first are the whole evidence behind 96.22. Each is a door to the column and everything else scored on it.

    1. Mystery Game PuzzlesEpoch AI Benchmarking Hub0.18121 on the scale
    2. Chess PuzzlesEpoch AI Benchmarking Hub0.19119 on the scale
    3. FrontierMath-Tiers-1-3-v2-PrivateEpoch AI Benchmarking Hub0.42109 on the scale
    4. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.2994 on the scale
    5. GPQA diamondEpoch AI Benchmarking Hub0.7183 on the scale
  221. 221qwen/qwen3-32bunstated96.2132

    3 columns on 2 boards, hardest first are the whole evidence behind 96.21. Each is a door to the column and everything else scored on it.

    1. polyglot pass rateAider polyglot4097 on the scale
    2. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.6794 on the scale
    3. GPQA diamondEpoch AI Benchmarking Hub0.6683 on the scale
  222. 222gpt-5.4-2026-03-05not in the catalognone96.1541

    4 columns on 1 board, hardest first are the whole evidence behind 96.15. Each is a door to the column and everything else scored on it.

    1. Mystery Game PuzzlesEpoch AI Benchmarking Hub0.16121 on the scale
    2. Chess PuzzlesEpoch AI Benchmarking Hub0.03119 on the scale
    3. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.5894 on the scale
    4. GPQA diamondEpoch AI Benchmarking Hub0.7583 on the scale
  223. 223deepseek-r1not in the catalogunstated96.0842

    4 columns on 2 boards, hardest first are the whole evidence behind 96.08. Each is a door to the column and everything else scored on it.

    1. polyglot pass rateAider polyglot56.9097 on the scale
    2. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.5394 on the scale
    3. GPQA diamondEpoch AI Benchmarking Hub0.6983 on the scale
    4. MATH level 5Epoch AI Benchmarking Hub0.9381 on the scale
  224. 224claude-haiku-4-5-20251001-32knot in the catalogunstated96.0181

    8 columns on 1 board, hardest first are the whole evidence behind 96.01. Each is a door to the column and everything else scored on it.

    1. FrontierMath-Tier-4-2025-07-01-PrivateEpoch AI Benchmarking Hub0.02120 on the scale
    2. Chess PuzzlesEpoch AI Benchmarking Hub0.05119 on the scale
    3. SimpleQA VerifiedEpoch AI Benchmarking Hub0.13115 on the scale
    4. FrontierMath-2025-02-28-PrivateEpoch AI Benchmarking Hub0.06115 on the scale
    5. FrontierMath-2025-02-28-PublicEpoch AI Benchmarking Hub0106 on the scale
    6. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.6794 on the scale
    7. GPQA diamondEpoch AI Benchmarking Hub0.7183 on the scale
    8. MATH level 5Epoch AI Benchmarking Hub0.9681 on the scale
  225. 225openai/gpt-5.6-lunanone95.9351

    5 columns on 1 board, hardest first are the whole evidence behind 95.93. Each is a door to the column and everything else scored on it.

    1. Mystery Game PuzzlesEpoch AI Benchmarking Hub0.20121 on the scale
    2. Chess PuzzlesEpoch AI Benchmarking Hub0.03119 on the scale
    3. FrontierMath-Tiers-1-3-v2-PrivateEpoch AI Benchmarking Hub0.40109 on the scale
    4. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.4094 on the scale
    5. GPQA diamondEpoch AI Benchmarking Hub0.6483 on the scale
  226. 226openai/gpt-5.6-terranone95.5741

    4 columns on 1 board, hardest first are the whole evidence behind 95.57. Each is a door to the column and everything else scored on it.

    1. Mystery Game PuzzlesEpoch AI Benchmarking Hub0.14121 on the scale
    2. Chess PuzzlesEpoch AI Benchmarking Hub0.05119 on the scale
    3. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.5394 on the scale
    4. GPQA diamondEpoch AI Benchmarking Hub0.7783 on the scale
  227. 227claude-3-7-sonnet-20250219-64knot in the catalogunstated95.1861

    6 columns on 1 board, hardest first are the whole evidence behind 95.18. Each is a door to the column and everything else scored on it.

    1. FrontierMath-Tier-4-2025-07-01-PublicEpoch AI Benchmarking Hub0116 on the scale
    2. FrontierMath-2025-02-28-PrivateEpoch AI Benchmarking Hub0.03115 on the scale
    3. FrontierMath-2025-02-28-PublicEpoch AI Benchmarking Hub0106 on the scale
    4. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.5894 on the scale
    5. GPQA diamondEpoch AI Benchmarking Hub0.7983 on the scale
    6. MATH level 5Epoch AI Benchmarking Hub0.9181 on the scale
  228. 228gpt-5-2025-08-07not in the catalogminimal95.1451

    5 columns on 1 board, hardest first are the whole evidence behind 95.14. Each is a door to the column and everything else scored on it.

    1. Mystery Game PuzzlesEpoch AI Benchmarking Hub0.14121 on the scale
    2. Chess PuzzlesEpoch AI Benchmarking Hub0.11119 on the scale
    3. FrontierMath-Tiers-1-3-v2-PrivateEpoch AI Benchmarking Hub0.18109 on the scale
    4. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.4794 on the scale
    5. GPQA diamondEpoch AI Benchmarking Hub0.7283 on the scale
  229. 229google/gemini-3.5-flash-liteminimal94.9541

    4 columns on 1 board, hardest first are the whole evidence behind 94.95. Each is a door to the column and everything else scored on it.

    1. Mystery Game PuzzlesEpoch AI Benchmarking Hub0.12121 on the scale
    2. Chess PuzzlesEpoch AI Benchmarking Hub0.07119 on the scale
    3. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.5194 on the scale
    4. GPQA diamondEpoch AI Benchmarking Hub0.7483 on the scale
  230. 230google/gemini-3.1-flash-litelow94.9431

    3 columns on 1 board, hardest first are the whole evidence behind 94.94. Each is a door to the column and everything else scored on it.

    1. FrontierMath-Tiers-1-3-v2-PrivateEpoch AI Benchmarking Hub0.22109 on the scale
    2. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.4494 on the scale
    3. GPQA diamondEpoch AI Benchmarking Hub0.7483 on the scale
  231. 232grok-3-mini-betanot in the cataloglow94.7162

    6 columns on 2 boards, hardest first are the whole evidence behind 94.71. Each is a door to the column and everything else scored on it.

    1. FrontierMath-2025-02-28-PrivateEpoch AI Benchmarking Hub0.03115 on the scale
    2. FrontierMath-2025-02-28-PublicEpoch AI Benchmarking Hub0106 on the scale
    3. polyglot pass rateAider polyglot34.7097 on the scale
    4. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.6294 on the scale
    5. GPQA diamondEpoch AI Benchmarking Hub0.7683 on the scale
    6. MATH level 5Epoch AI Benchmarking Hub0.9181 on the scale
  232. 231o1-2024-12-17not in the cataloglow94.7141

    4 columns on 1 board, hardest first are the whole evidence behind 94.71. Each is a door to the column and everything else scored on it.

    1. Chess PuzzlesEpoch AI Benchmarking Hub0.11119 on the scale
    2. FrontierMath-Tiers-1-3-v2-PrivateEpoch AI Benchmarking Hub0.08109 on the scale
    3. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.5394 on the scale
    4. GPQA diamondEpoch AI Benchmarking Hub0.7483 on the scale
  233. 233grok-3-betanot in the catalogunstated94.6582

    8 columns on 2 boards, hardest first are the whole evidence behind 94.65. Each is a door to the column and everything else scored on it.

    1. FrontierMath-Tier-4-2025-07-01-PrivateEpoch AI Benchmarking Hub0120 on the scale
    2. FrontierMath-Tier-4-2025-07-01-PublicEpoch AI Benchmarking Hub0116 on the scale
    3. FrontierMath-2025-02-28-PrivateEpoch AI Benchmarking Hub0.04115 on the scale
    4. FrontierMath-2025-02-28-PublicEpoch AI Benchmarking Hub0106 on the scale
    5. polyglot pass rateAider polyglot53.3097 on the scale
    6. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.5694 on the scale
    7. GPQA diamondEpoch AI Benchmarking Hub0.6883 on the scale
    8. MATH level 5Epoch AI Benchmarking Hub0.8981 on the scale
  234. 234claude-3-7-sonnet-20250219-32knot in the catalogunstated94.4051

    5 columns on 1 board, hardest first are the whole evidence behind 94.40. Each is a door to the column and everything else scored on it.

    1. FrontierMath-2025-02-28-PrivateEpoch AI Benchmarking Hub0.03115 on the scale
    2. FrontierMath-2025-02-28-PublicEpoch AI Benchmarking Hub0106 on the scale
    3. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.5394 on the scale
    4. GPQA diamondEpoch AI Benchmarking Hub0.7783 on the scale
    5. MATH level 5Epoch AI Benchmarking Hub0.9081 on the scale
  235. 235deepseek/deepseek-v4-pronone94.2841

    4 columns on 1 board, hardest first are the whole evidence behind 94.28. Each is a door to the column and everything else scored on it.

    1. Mystery Game PuzzlesEpoch AI Benchmarking Hub0.17121 on the scale
    2. Chess PuzzlesEpoch AI Benchmarking Hub0.04119 on the scale
    3. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.4794 on the scale
    4. GPQA diamondEpoch AI Benchmarking Hub0.7383 on the scale
  236. 236gpt-5-mini-2025-08-07not in the catalogminimal93.8651

    5 columns on 1 board, hardest first are the whole evidence behind 93.86. Each is a door to the column and everything else scored on it.

    1. Mystery Game PuzzlesEpoch AI Benchmarking Hub0.10121 on the scale
    2. Chess PuzzlesEpoch AI Benchmarking Hub0119 on the scale
    3. FrontierMath-Tiers-1-3-v2-PrivateEpoch AI Benchmarking Hub0.06109 on the scale
    4. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.5694 on the scale
    5. GPQA diamondEpoch AI Benchmarking Hub0.7283 on the scale
  237. 237claude-opus-4-1-20250805not in the catalogunstated93.8161

    6 columns on 1 board, hardest first are the whole evidence behind 93.81. Each is a door to the column and everything else scored on it.

    1. EBR-benchEpoch AI Benchmarking Hub0.08123 on the scale
    2. FrontierMath-2025-02-28-PrivateEpoch AI Benchmarking Hub0.06115 on the scale
    3. FrontierMath-2025-02-28-PublicEpoch AI Benchmarking Hub0106 on the scale
    4. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.4094 on the scale
    5. SWE-Bench verifiedEpoch AI Benchmarking Hub0.7384 on the scale
    6. GPQA diamondEpoch AI Benchmarking Hub0.7383 on the scale
  238. 238google/gemini-3.1-flash-liteminimal93.6831

    3 columns on 1 board, hardest first are the whole evidence behind 93.68. Each is a door to the column and everything else scored on it.

    1. FrontierMath-Tiers-1-3-v2-PrivateEpoch AI Benchmarking Hub0.21109 on the scale
    2. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.3894 on the scale
    3. GPQA diamondEpoch AI Benchmarking Hub0.7483 on the scale
  239. 239deepseek-r1-distill-llama-70bnot in the catalogunstated93.5531

    3 columns on 1 board, hardest first are the whole evidence behind 93.55. Each is a door to the column and everything else scored on it.

    1. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.5194 on the scale
    2. GPQA diamondEpoch AI Benchmarking Hub0.5683 on the scale
    3. MATH level 5Epoch AI Benchmarking Hub0.9081 on the scale
  240. 240gpt-4.1-mini-2025-04-14not in the catalogunstated93.4891

    9 columns on 1 board, hardest first are the whole evidence behind 93.48. Each is a door to the column and everything else scored on it.

    1. Mystery Game PuzzlesEpoch AI Benchmarking Hub0.07121 on the scale
    2. Chess PuzzlesEpoch AI Benchmarking Hub0.01119 on the scale
    3. SimpleQA VerifiedEpoch AI Benchmarking Hub0.13115 on the scale
    4. FrontierMath-2025-02-28-PrivateEpoch AI Benchmarking Hub0.04115 on the scale
    5. FrontierMath-Tiers-1-3-v2-PrivateEpoch AI Benchmarking Hub0.07109 on the scale
    6. FrontierMath-2025-02-28-PublicEpoch AI Benchmarking Hub0.10106 on the scale
    7. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.4594 on the scale
    8. GPQA diamondEpoch AI Benchmarking Hub0.6683 on the scale
    9. MATH level 5Epoch AI Benchmarking Hub0.8781 on the scale
  241. 241claude-sonnet-4-5-20250929not in the catalogunstated93.21101

    10 columns on 1 board, hardest first are the whole evidence behind 93.21. Each is a door to the column and everything else scored on it.

    1. EBR-benchEpoch AI Benchmarking Hub0.02123 on the scale
    2. FrontierMath-Tier-4-2025-07-01-PrivateEpoch AI Benchmarking Hub0.02120 on the scale
    3. Chess PuzzlesEpoch AI Benchmarking Hub0.06119 on the scale
    4. FrontierMath-Tier-4-2025-07-01-PublicEpoch AI Benchmarking Hub0116 on the scale
    5. SimpleQA VerifiedEpoch AI Benchmarking Hub0.24115 on the scale
    6. FrontierMath-2025-02-28-PrivateEpoch AI Benchmarking Hub0.09115 on the scale
    7. FrontierMath-2025-02-28-PublicEpoch AI Benchmarking Hub0106 on the scale
    8. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.3694 on the scale
    9. SWE-Bench verifiedEpoch AI Benchmarking Hub0.7184 on the scale
    10. GPQA diamondEpoch AI Benchmarking Hub0.7483 on the scale
  242. 242claude-3-7-sonnet-20250219-16knot in the catalogunstated93.2051

    5 columns on 1 board, hardest first are the whole evidence behind 93.20. Each is a door to the column and everything else scored on it.

    1. FrontierMath-2025-02-28-PrivateEpoch AI Benchmarking Hub0.04115 on the scale
    2. FrontierMath-2025-02-28-PublicEpoch AI Benchmarking Hub0106 on the scale
    3. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.4794 on the scale
    4. GPQA diamondEpoch AI Benchmarking Hub0.7783 on the scale
    5. MATH level 5Epoch AI Benchmarking Hub0.8681 on the scale
  243. 243qwq-32bnot in the catalogunstated93.1832

    3 columns on 2 boards, hardest first are the whole evidence behind 93.18. Each is a door to the column and everything else scored on it.

    1. polyglot pass rateAider polyglot20.9097 on the scale
    2. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.5994 on the scale
    3. GPQA diamondEpoch AI Benchmarking Hub0.6583 on the scale
  244. 244gpt-5-nano-2025-08-07not in the cataloglow92.7451

    5 columns on 1 board, hardest first are the whole evidence behind 92.74. Each is a door to the column and everything else scored on it.

    1. Mystery Game PuzzlesEpoch AI Benchmarking Hub0.09121 on the scale
    2. Chess PuzzlesEpoch AI Benchmarking Hub0.15119 on the scale
    3. FrontierMath-Tiers-1-3-v2-PrivateEpoch AI Benchmarking Hub0.06109 on the scale
    4. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.4794 on the scale
    5. GPQA diamondEpoch AI Benchmarking Hub0.5883 on the scale
  245. 245o1-mini-2024-09-12not in the cataloghigh92.5351

    5 columns on 1 board, hardest first are the whole evidence behind 92.53. Each is a door to the column and everything else scored on it.

    1. FrontierMath-2025-02-28-PrivateEpoch AI Benchmarking Hub0.01115 on the scale
    2. FrontierMath-2025-02-28-PublicEpoch AI Benchmarking Hub0106 on the scale
    3. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.4794 on the scale
    4. GPQA diamondEpoch AI Benchmarking Hub0.6283 on the scale
    5. MATH level 5Epoch AI Benchmarking Hub0.8981 on the scale
  246. 246claude-opus-4-20250514not in the catalogunstated92.4881

    8 columns on 1 board, hardest first are the whole evidence behind 92.48. Each is a door to the column and everything else scored on it.

    1. FrontierMath-Tier-4-2025-07-01-PrivateEpoch AI Benchmarking Hub0120 on the scale
    2. FrontierMath-Tier-4-2025-07-01-PublicEpoch AI Benchmarking Hub0116 on the scale
    3. FrontierMath-2025-02-28-PrivateEpoch AI Benchmarking Hub0.04115 on the scale
    4. FrontierMath-2025-02-28-PublicEpoch AI Benchmarking Hub0106 on the scale
    5. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.4294 on the scale
    6. SWE-Bench verifiedEpoch AI Benchmarking Hub0.7184 on the scale
    7. GPQA diamondEpoch AI Benchmarking Hub0.6983 on the scale
    8. MATH level 5Epoch AI Benchmarking Hub0.8581 on the scale
  247. 247deepseek-r1-distill-qwen-14bnot in the catalogunstated92.3031

    3 columns on 1 board, hardest first are the whole evidence behind 92.30. Each is a door to the column and everything else scored on it.

    1. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.5194 on the scale
    2. GPQA diamondEpoch AI Benchmarking Hub0.4583 on the scale
    3. MATH level 5Epoch AI Benchmarking Hub0.8781 on the scale
  248. 248zai-org/glm-4.6not in the catalogunstated92.2141

    4 columns on 1 board, hardest first are the whole evidence behind 92.21. Each is a door to the column and everything else scored on it.

    1. FrontierMath-Tier-4-2025-07-01-PrivateEpoch AI Benchmarking Hub0.02120 on the scale
    2. FrontierMath-Tier-4-2025-07-01-PublicEpoch AI Benchmarking Hub0116 on the scale
    3. FrontierMath-2025-02-28-PrivateEpoch AI Benchmarking Hub0.04115 on the scale
    4. FrontierMath-2025-02-28-PublicEpoch AI Benchmarking Hub0106 on the scale
  249. 249gemini-2.0-flash-thinking-exp-01-21not in the catalogunstated92.1432

    3 columns on 2 boards, hardest first are the whole evidence behind 92.14. Each is a door to the column and everything else scored on it.

    1. polyglot pass rateAider polyglot18.2097 on the scale
    2. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.5894 on the scale
    3. GPQA diamondEpoch AI Benchmarking Hub0.5783 on the scale
  250. 250o3-mini-2025-01-31not in the cataloglow91.9141

    4 columns on 1 board, hardest first are the whole evidence behind 91.91. Each is a door to the column and everything else scored on it.

    1. Chess PuzzlesEpoch AI Benchmarking Hub0.06119 on the scale
    2. FrontierMath-Tiers-1-3-v2-PrivateEpoch AI Benchmarking Hub0.04109 on the scale
    3. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.4494 on the scale
    4. GPQA diamondEpoch AI Benchmarking Hub0.6883 on the scale
  251. 251gpt-5.1-2025-11-13not in the catalognone91.9051

    5 columns on 1 board, hardest first are the whole evidence behind 91.90. Each is a door to the column and everything else scored on it.

    1. Mystery Game PuzzlesEpoch AI Benchmarking Hub0.15121 on the scale
    2. Chess PuzzlesEpoch AI Benchmarking Hub0.06119 on the scale
    3. FrontierMath-2025-02-28-PrivateEpoch AI Benchmarking Hub0.02115 on the scale
    4. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.3894 on the scale
    5. GPQA diamondEpoch AI Benchmarking Hub0.6783 on the scale
  252. 252gpt-4.1-2025-04-14not in the catalogunstated91.64111

    11 columns on 1 board, hardest first are the whole evidence behind 91.64. Each is a door to the column and everything else scored on it.

    1. FrontierMath-Tier-4-2025-07-01-PrivateEpoch AI Benchmarking Hub0120 on the scale
    2. Chess PuzzlesEpoch AI Benchmarking Hub0.11119 on the scale
    3. FrontierMath-Tier-4-2025-07-01-PublicEpoch AI Benchmarking Hub0116 on the scale
    4. SimpleQA VerifiedEpoch AI Benchmarking Hub0.31115 on the scale
    5. FrontierMath-2025-02-28-PrivateEpoch AI Benchmarking Hub0.06115 on the scale
    6. FrontierMath-Tiers-1-3-v2-PrivateEpoch AI Benchmarking Hub0.06109 on the scale
    7. FrontierMath-2025-02-28-PublicEpoch AI Benchmarking Hub0106 on the scale
    8. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.3894 on the scale
    9. SWE-Bench verifiedEpoch AI Benchmarking Hub0.4984 on the scale
    10. GPQA diamondEpoch AI Benchmarking Hub0.6783 on the scale
    11. MATH level 5Epoch AI Benchmarking Hub0.8381 on the scale
  253. 253o1-mini-2024-09-12not in the catalogmedium91.5151

    5 columns on 1 board, hardest first are the whole evidence behind 91.51. Each is a door to the column and everything else scored on it.

    1. FrontierMath-2025-02-28-PrivateEpoch AI Benchmarking Hub0.02115 on the scale
    2. FrontierMath-2025-02-28-PublicEpoch AI Benchmarking Hub0106 on the scale
    3. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.4594 on the scale
    4. GPQA diamondEpoch AI Benchmarking Hub0.6083 on the scale
    5. MATH level 5Epoch AI Benchmarking Hub0.8481 on the scale
  254. 254gpt-5.4-nano-2026-03-17not in the catalognone91.3351

    5 columns on 1 board, hardest first are the whole evidence behind 91.33. Each is a door to the column and everything else scored on it.

    1. Mystery Game PuzzlesEpoch AI Benchmarking Hub0.09121 on the scale
    2. Chess PuzzlesEpoch AI Benchmarking Hub0.02119 on the scale
    3. FrontierMath-Tiers-1-3-v2-PrivateEpoch AI Benchmarking Hub0.05109 on the scale
    4. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.4794 on the scale
    5. GPQA diamondEpoch AI Benchmarking Hub0.5683 on the scale
  255. 255claude-haiku-4-5-20251001not in the catalogunstated90.9951

    5 columns on 1 board, hardest first are the whole evidence behind 90.99. Each is a door to the column and everything else scored on it.

    1. SimpleQA VerifiedEpoch AI Benchmarking Hub0.13115 on the scale
    2. FrontierMath-2025-02-28-PrivateEpoch AI Benchmarking Hub0.04115 on the scale
    3. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.3694 on the scale
    4. GPQA diamondEpoch AI Benchmarking Hub0.6083 on the scale
    5. MATH level 5Epoch AI Benchmarking Hub0.8781 on the scale
  256. 257minimax/minimax-m3none90.8441

    4 columns on 1 board, hardest first are the whole evidence behind 90.84. Each is a door to the column and everything else scored on it.

    1. Mystery Game PuzzlesEpoch AI Benchmarking Hub0.08121 on the scale
    2. Chess PuzzlesEpoch AI Benchmarking Hub0.08119 on the scale
    3. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.2794 on the scale
    4. GPQA diamondEpoch AI Benchmarking Hub0.8183 on the scale
  257. 256gemini-2.0-pro-exp-02-05not in the catalogunstated90.8442

    4 columns on 2 boards, hardest first are the whole evidence behind 90.84. Each is a door to the column and everything else scored on it.

    1. FrontierMath-2025-02-28-PublicEpoch AI Benchmarking Hub0106 on the scale
    2. polyglot pass rateAider polyglot35.6097 on the scale
    3. GPQA diamondEpoch AI Benchmarking Hub0.6683 on the scale
    4. MATH level 5Epoch AI Benchmarking Hub0.8381 on the scale
  258. 258gpt-4.5-preview-2025-02-27not in the catalogunstated90.7531

    3 columns on 1 board, hardest first are the whole evidence behind 90.75. Each is a door to the column and everything else scored on it.

    1. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.3894 on the scale
    2. GPQA diamondEpoch AI Benchmarking Hub0.6983 on the scale
    3. MATH level 5Epoch AI Benchmarking Hub0.7981 on the scale
  259. 259gpt-5.4-mini-2026-03-17not in the catalognone90.4851

    5 columns on 1 board, hardest first are the whole evidence behind 90.48. Each is a door to the column and everything else scored on it.

    1. Mystery Game PuzzlesEpoch AI Benchmarking Hub0.11121 on the scale
    2. Chess PuzzlesEpoch AI Benchmarking Hub0.02119 on the scale
    3. FrontierMath-Tiers-1-3-v2-PrivateEpoch AI Benchmarking Hub0.17109 on the scale
    4. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.2794 on the scale
    5. GPQA diamondEpoch AI Benchmarking Hub0.6483 on the scale
  260. 260claude-sonnet-4-20250514not in the catalogunstated90.1671

    7 columns on 1 board, hardest first are the whole evidence behind 90.16. Each is a door to the column and everything else scored on it.

    1. FrontierMath-Tier-4-2025-07-01-PrivateEpoch AI Benchmarking Hub0120 on the scale
    2. FrontierMath-Tier-4-2025-07-01-PublicEpoch AI Benchmarking Hub0116 on the scale
    3. FrontierMath-2025-02-28-PrivateEpoch AI Benchmarking Hub0.04115 on the scale
    4. FrontierMath-2025-02-28-PublicEpoch AI Benchmarking Hub0106 on the scale
    5. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.2994 on the scale
    6. GPQA diamondEpoch AI Benchmarking Hub0.6783 on the scale
    7. MATH level 5Epoch AI Benchmarking Hub0.8481 on the scale
  261. 261deepseek-v3-0324not in the catalogunstated90.1241

    4 columns on 1 board, hardest first are the whole evidence behind 90.12. Each is a door to the column and everything else scored on it.

    1. FrontierMath-2025-02-28-PublicEpoch AI Benchmarking Hub0106 on the scale
    2. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.3894 on the scale
    3. GPQA diamondEpoch AI Benchmarking Hub0.6883 on the scale
    4. MATH level 5Epoch AI Benchmarking Hub0.7681 on the scale
  262. 262gemini-2.0-flash-001not in the catalogunstated89.7551

    5 columns on 1 board, hardest first are the whole evidence behind 89.75. Each is a door to the column and everything else scored on it.

    1. FrontierMath-2025-02-28-PrivateEpoch AI Benchmarking Hub0.02115 on the scale
    2. FrontierMath-2025-02-28-PublicEpoch AI Benchmarking Hub0106 on the scale
    3. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.3194 on the scale
    4. GPQA diamondEpoch AI Benchmarking Hub0.6483 on the scale
    5. MATH level 5Epoch AI Benchmarking Hub0.8281 on the scale
  263. 263mistral-medium-2505not in the catalogunstated89.4151

    5 columns on 1 board, hardest first are the whole evidence behind 89.41. Each is a door to the column and everything else scored on it.

    1. FrontierMath-2025-02-28-PrivateEpoch AI Benchmarking Hub0.00115 on the scale
    2. FrontierMath-2025-02-28-PublicEpoch AI Benchmarking Hub0106 on the scale
    3. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.3294 on the scale
    4. GPQA diamondEpoch AI Benchmarking Hub0.6083 on the scale
    5. MATH level 5Epoch AI Benchmarking Hub0.8281 on the scale
  264. 264o1-preview-2024-09-12not in the catalogunstated89.0831

    3 columns on 1 board, hardest first are the whole evidence behind 89.08. Each is a door to the column and everything else scored on it.

    1. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.3194 on the scale
    2. GPQA diamondEpoch AI Benchmarking Hub0.5083 on the scale
    3. MATH level 5Epoch AI Benchmarking Hub0.8281 on the scale
  265. 265magistral-small-2506not in the catalogunstated88.6331

    3 columns on 1 board, hardest first are the whole evidence behind 88.63. Each is a door to the column and everything else scored on it.

    1. FrontierMath-2025-02-28-PublicEpoch AI Benchmarking Hub0106 on the scale
    2. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.3094 on the scale
    3. GPQA diamondEpoch AI Benchmarking Hub0.5683 on the scale
  266. 266gpt-5-nano-2025-08-07not in the catalogminimal88.0851

    5 columns on 1 board, hardest first are the whole evidence behind 88.08. Each is a door to the column and everything else scored on it.

    1. Mystery Game PuzzlesEpoch AI Benchmarking Hub0.05121 on the scale
    2. Chess PuzzlesEpoch AI Benchmarking Hub0.02119 on the scale
    3. FrontierMath-Tiers-1-3-v2-PrivateEpoch AI Benchmarking Hub0.02109 on the scale
    4. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.3694 on the scale
    5. GPQA diamondEpoch AI Benchmarking Hub0.4883 on the scale
  267. 267qwen3-235b-a22bnot in the catalogunstated87.5631

    3 columns on 1 board, hardest first are the whole evidence behind 87.56. Each is a door to the column and everything else scored on it.

    1. FrontierMath-2025-02-28-PublicEpoch AI Benchmarking Hub0106 on the scale
    2. GPQA diamondEpoch AI Benchmarking Hub0.7183 on the scale
    3. MATH level 5Epoch AI Benchmarking Hub0.6981 on the scale
  268. 268nemotron-3.5-lightning-30b-a3bnot in the catalogunstated87.31231

    23 columns on 1 board, hardest first are the whole evidence behind 87.31. Each is a door to the column and everything else scored on it.

    1. typescriptLiveBench6.67122 on the scale
    2. tablejoinLiveBench40.48117 on the scale
    3. pythonLiveBench35109 on the scale
    4. plot_unscramblingLiveBench22.87106 on the scale
    5. integrals_with_gameLiveBench24104 on the scale
    6. consecutive_eventsLiveBench2.51102 on the scale
    7. zebra_puzzleLiveBench17.25102 on the scale
    8. javascriptLiveBench18.1899 on the scale
    9. logic_with_navigationLiveBench1896 on the scale
    10. simplifyLiveBench52.6892 on the scale
    11. connectionsLiveBench3491 on the scale
    12. theory_of_mindLiveBench44.2388 on the scale
    13. code_completionLiveBench23.9187 on the scale
    14. paraphraseLiveBench57.3286 on the scale
    15. summarizeLiveBench50.4285 on the scale
    16. typosLiveBench5877 on the scale
    17. code_generationLiveBench67.6176 on the scale
    18. story_generationLiveBench59.3574 on the scale
    19. olympiadLiveBench58.9272 on the scale
    20. spatialLiveBench9253 on the scale
    21. AMPS_HardLiveBench9747 on the scale
    22. math_compLiveBench86.2842 on the scale
    23. tablereformatLiveBench86.2841 on the scale
  269. 269claude-3-7-sonnet-20250219not in the catalogunstated87.2261

    6 columns on 1 board, hardest first are the whole evidence behind 87.22. Each is a door to the column and everything else scored on it.

    1. FrontierMath-2025-02-28-PrivateEpoch AI Benchmarking Hub0.03115 on the scale
    2. FrontierMath-2025-02-28-PublicEpoch AI Benchmarking Hub0106 on the scale
    3. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.2294 on the scale
    4. SWE-Bench verifiedEpoch AI Benchmarking Hub0.6184 on the scale
    5. GPQA diamondEpoch AI Benchmarking Hub0.6683 on the scale
    6. MATH level 5Epoch AI Benchmarking Hub0.6881 on the scale
  270. 270llama-4-maverick-17b-128e-instruct-fp8not in the catalogunstated87.2151

    5 columns on 1 board, hardest first are the whole evidence behind 87.21. Each is a door to the column and everything else scored on it.

    1. FrontierMath-2025-02-28-PrivateEpoch AI Benchmarking Hub0.01115 on the scale
    2. FrontierMath-2025-02-28-PublicEpoch AI Benchmarking Hub0106 on the scale
    3. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.2194 on the scale
    4. GPQA diamondEpoch AI Benchmarking Hub0.6783 on the scale
    5. MATH level 5Epoch AI Benchmarking Hub0.7381 on the scale
  271. 271gemini-1.5-pro-002not in the catalogunstated86.8031

    3 columns on 1 board, hardest first are the whole evidence behind 86.80. Each is a door to the column and everything else scored on it.

    1. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.2394 on the scale
    2. GPQA diamondEpoch AI Benchmarking Hub0.5783 on the scale
    3. MATH level 5Epoch AI Benchmarking Hub0.7081 on the scale
  272. 272gpt-4.1-nano-2025-04-14not in the catalogunstated86.2271

    7 columns on 1 board, hardest first are the whole evidence behind 86.22. Each is a door to the column and everything else scored on it.

    1. Chess PuzzlesEpoch AI Benchmarking Hub0119 on the scale
    2. SimpleQA VerifiedEpoch AI Benchmarking Hub0.06115 on the scale
    3. FrontierMath-2025-02-28-PrivateEpoch AI Benchmarking Hub0.01115 on the scale
    4. FrontierMath-2025-02-28-PublicEpoch AI Benchmarking Hub0106 on the scale
    5. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.2994 on the scale
    6. GPQA diamondEpoch AI Benchmarking Hub0.4983 on the scale
    7. MATH level 5Epoch AI Benchmarking Hub0.7081 on the scale
  273. 273claude-3-5-sonnet-20241022not in the catalogunstated85.3182

    8 columns on 2 boards, hardest first are the whole evidence behind 85.31. Each is a door to the column and everything else scored on it.

    1. FrontierMath-Tier-4-2025-07-01-PrivateEpoch AI Benchmarking Hub0120 on the scale
    2. FrontierMath-Tier-4-2025-07-01-PublicEpoch AI Benchmarking Hub0116 on the scale
    3. FrontierMath-2025-02-28-PrivateEpoch AI Benchmarking Hub0.02115 on the scale
    4. FrontierMath-2025-02-28-PublicEpoch AI Benchmarking Hub0106 on the scale
    5. polyglot pass rateAider polyglot51.6097 on the scale
    6. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.0894 on the scale
    7. GPQA diamondEpoch AI Benchmarking Hub0.5583 on the scale
    8. MATH level 5Epoch AI Benchmarking Hub0.5781 on the scale
  274. 274qwen-max-2025-01-25not in the catalogunstated85.1162

    6 columns on 2 boards, hardest first are the whole evidence behind 85.11. Each is a door to the column and everything else scored on it.

    1. FrontierMath-2025-02-28-PrivateEpoch AI Benchmarking Hub0.01115 on the scale
    2. FrontierMath-2025-02-28-PublicEpoch AI Benchmarking Hub0106 on the scale
    3. polyglot pass rateAider polyglot21.8097 on the scale
    4. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.1694 on the scale
    5. GPQA diamondEpoch AI Benchmarking Hub0.5683 on the scale
    6. MATH level 5Epoch AI Benchmarking Hub0.6781 on the scale
  275. 275google/gemma-3-27b-itunstated85.0542

    4 columns on 2 boards, hardest first are the whole evidence behind 85.05. Each is a door to the column and everything else scored on it.

    1. polyglot pass rateAider polyglot4.9097 on the scale
    2. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.2394 on the scale
    3. GPQA diamondEpoch AI Benchmarking Hub0.4883 on the scale
    4. MATH level 5Epoch AI Benchmarking Hub0.7481 on the scale
  276. 276deepseek-v3not in the catalogunstated84.9651

    5 columns on 1 board, hardest first are the whole evidence behind 84.96. Each is a door to the column and everything else scored on it.

    1. FrontierMath-2025-02-28-PrivateEpoch AI Benchmarking Hub0.02115 on the scale
    2. FrontierMath-2025-02-28-PublicEpoch AI Benchmarking Hub0106 on the scale
    3. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.1694 on the scale
    4. GPQA diamondEpoch AI Benchmarking Hub0.5783 on the scale
    5. MATH level 5Epoch AI Benchmarking Hub0.6581 on the scale
  277. 277qwen-plus-2025-01-25not in the catalogunstated84.7631

    3 columns on 1 board, hardest first are the whole evidence behind 84.76. Each is a door to the column and everything else scored on it.

    1. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.1894 on the scale
    2. GPQA diamondEpoch AI Benchmarking Hub0.4883 on the scale
    3. MATH level 5Epoch AI Benchmarking Hub0.6581 on the scale
  278. 278microsoft/phi-4unstated84.6431

    3 columns on 1 board, hardest first are the whole evidence behind 84.64. Each is a door to the column and everything else scored on it.

    1. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.1494 on the scale
    2. GPQA diamondEpoch AI Benchmarking Hub0.5683 on the scale
    3. MATH level 5Epoch AI Benchmarking Hub0.6581 on the scale
  279. 279grok-2-1212not in the catalogunstated83.8951

    5 columns on 1 board, hardest first are the whole evidence behind 83.89. Each is a door to the column and everything else scored on it.

    1. FrontierMath-2025-02-28-PrivateEpoch AI Benchmarking Hub0.01115 on the scale
    2. FrontierMath-2025-02-28-PublicEpoch AI Benchmarking Hub0106 on the scale
    3. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.1294 on the scale
    4. GPQA diamondEpoch AI Benchmarking Hub0.5483 on the scale
    5. MATH level 5Epoch AI Benchmarking Hub0.6481 on the scale
  280. 280gemini-1.5-flash-002not in the catalogunstated83.8651

    5 columns on 1 board, hardest first are the whole evidence behind 83.86. Each is a door to the column and everything else scored on it.

    1. FrontierMath-2025-02-28-PrivateEpoch AI Benchmarking Hub0115 on the scale
    2. FrontierMath-2025-02-28-PublicEpoch AI Benchmarking Hub0106 on the scale
    3. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.1694 on the scale
    4. GPQA diamondEpoch AI Benchmarking Hub0.4783 on the scale
    5. MATH level 5Epoch AI Benchmarking Hub0.6281 on the scale
  281. 281qwen2.5-72b-instructnot in the catalogunstated83.1131

    3 columns on 1 board, hardest first are the whole evidence behind 83.11. Each is a door to the column and everything else scored on it.

    1. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.0894 on the scale
    2. GPQA diamondEpoch AI Benchmarking Hub0.4983 on the scale
    3. MATH level 5Epoch AI Benchmarking Hub0.6381 on the scale
  282. 282llama-4-scout-17b-16e-instructnot in the catalogunstated82.9951

    5 columns on 1 board, hardest first are the whole evidence behind 82.99. Each is a door to the column and everything else scored on it.

    1. FrontierMath-2025-02-28-PrivateEpoch AI Benchmarking Hub0115 on the scale
    2. FrontierMath-2025-02-28-PublicEpoch AI Benchmarking Hub0106 on the scale
    3. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.0894 on the scale
    4. GPQA diamondEpoch AI Benchmarking Hub0.5283 on the scale
    5. MATH level 5Epoch AI Benchmarking Hub0.6281 on the scale
  283. 283openai/gpt-4o-2024-08-06unstated82.7692

    9 columns on 2 boards, hardest first are the whole evidence behind 82.76. Each is a door to the column and everything else scored on it.

    1. Chess PuzzlesEpoch AI Benchmarking Hub0.09119 on the scale
    2. SimpleQA VerifiedEpoch AI Benchmarking Hub0.26115 on the scale
    3. FrontierMath-2025-02-28-PrivateEpoch AI Benchmarking Hub0.00115 on the scale
    4. FrontierMath-Tiers-1-3-v2-PrivateEpoch AI Benchmarking Hub0.00109 on the scale
    5. FrontierMath-2025-02-28-PublicEpoch AI Benchmarking Hub0106 on the scale
    6. polyglot pass rateAider polyglot23.1097 on the scale
    7. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.0694 on the scale
    8. GPQA diamondEpoch AI Benchmarking Hub0.4983 on the scale
    9. MATH level 5Epoch AI Benchmarking Hub0.5381 on the scale
  284. 284qwen2.5-32b-instructnot in the catalogunstated81.7631

    3 columns on 1 board, hardest first are the whole evidence behind 81.76. Each is a door to the column and everything else scored on it.

    1. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.0794 on the scale
    2. GPQA diamondEpoch AI Benchmarking Hub0.4683 on the scale
    3. MATH level 5Epoch AI Benchmarking Hub0.5681 on the scale
  285. 285claude-3-5-sonnet-20240620not in the catalogunstated81.5971

    7 columns on 1 board, hardest first are the whole evidence behind 81.59. Each is a door to the column and everything else scored on it.

    1. FrontierMath-Tier-4-2025-07-01-PrivateEpoch AI Benchmarking Hub0120 on the scale
    2. FrontierMath-Tier-4-2025-07-01-PublicEpoch AI Benchmarking Hub0116 on the scale
    3. FrontierMath-2025-02-28-PrivateEpoch AI Benchmarking Hub0.01115 on the scale
    4. FrontierMath-2025-02-28-PublicEpoch AI Benchmarking Hub0106 on the scale
    5. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.0794 on the scale
    6. GPQA diamondEpoch AI Benchmarking Hub0.5483 on the scale
    7. MATH level 5Epoch AI Benchmarking Hub0.5281 on the scale
  286. 286llama-3.1-405b-instructnot in the catalogunstated81.4931

    3 columns on 1 board, hardest first are the whole evidence behind 81.49. Each is a door to the column and everything else scored on it.

    1. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.1094 on the scale
    2. GPQA diamondEpoch AI Benchmarking Hub0.5183 on the scale
    3. MATH level 5Epoch AI Benchmarking Hub0.5081 on the scale
  287. 287qwen-turbo-2024-11-01not in the catalogunstated81.3031

    3 columns on 1 board, hardest first are the whole evidence behind 81.30. Each is a door to the column and everything else scored on it.

    1. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.0694 on the scale
    2. GPQA diamondEpoch AI Benchmarking Hub0.4283 on the scale
    3. MATH level 5Epoch AI Benchmarking Hub0.5681 on the scale
  288. 288mistral-large-2411not in the catalogunstated81.2451

    5 columns on 1 board, hardest first are the whole evidence behind 81.24. Each is a door to the column and everything else scored on it.

    1. FrontierMath-2025-02-28-PrivateEpoch AI Benchmarking Hub0.00115 on the scale
    2. FrontierMath-2025-02-28-PublicEpoch AI Benchmarking Hub0106 on the scale
    3. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.0894 on the scale
    4. GPQA diamondEpoch AI Benchmarking Hub0.5183 on the scale
    5. MATH level 5Epoch AI Benchmarking Hub0.5081 on the scale
  289. 289openai/gpt-4o-2024-05-13unstated81.0131

    3 columns on 1 board, hardest first are the whole evidence behind 81.01. Each is a door to the column and everything else scored on it.

    1. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.0694 on the scale
    2. GPQA diamondEpoch AI Benchmarking Hub0.4983 on the scale
    3. MATH level 5Epoch AI Benchmarking Hub0.5181 on the scale
  290. 290claude-3-5-haiku-20241022not in the catalogunstated80.4262

    6 columns on 2 boards, hardest first are the whole evidence behind 80.42. Each is a door to the column and everything else scored on it.

    1. FrontierMath-2025-02-28-PrivateEpoch AI Benchmarking Hub0.00115 on the scale
    2. FrontierMath-2025-02-28-PublicEpoch AI Benchmarking Hub0106 on the scale
    3. polyglot pass rateAider polyglot2897 on the scale
    4. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.0494 on the scale
    5. GPQA diamondEpoch AI Benchmarking Hub0.3883 on the scale
    6. MATH level 5Epoch AI Benchmarking Hub0.4681 on the scale
  291. 291mistralai/mistral-large-2407unstated80.4031

    3 columns on 1 board, hardest first are the whole evidence behind 80.40. Each is a door to the column and everything else scored on it.

    1. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.0894 on the scale
    2. GPQA diamondEpoch AI Benchmarking Hub0.4983 on the scale
    3. MATH level 5Epoch AI Benchmarking Hub0.4581 on the scale
  292. 292openai/gpt-4o-2024-11-20unstated80.3772

    7 columns on 2 boards, hardest first are the whole evidence behind 80.37. Each is a door to the column and everything else scored on it.

    1. FrontierMath-2025-02-28-PrivateEpoch AI Benchmarking Hub0.00115 on the scale
    2. FrontierMath-2025-02-28-PublicEpoch AI Benchmarking Hub0106 on the scale
    3. polyglot pass rateAider polyglot18.2097 on the scale
    4. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.0694 on the scale
    5. SWE-Bench verifiedEpoch AI Benchmarking Hub0.3184 on the scale
    6. GPQA diamondEpoch AI Benchmarking Hub0.4883 on the scale
    7. MATH level 5Epoch AI Benchmarking Hub0.5081 on the scale
  293. 293mistral-small-2503not in the catalogunstated80.1831

    3 columns on 1 board, hardest first are the whole evidence behind 80.18. Each is a door to the column and everything else scored on it.

    1. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.0694 on the scale
    2. GPQA diamondEpoch AI Benchmarking Hub0.4783 on the scale
    3. MATH level 5Epoch AI Benchmarking Hub0.4781 on the scale
  294. 294openai/gpt-4o-mini-2024-07-18unstated80.1082

    8 columns on 2 boards, hardest first are the whole evidence behind 80.10. Each is a door to the column and everything else scored on it.

    1. Mystery Game PuzzlesEpoch AI Benchmarking Hub0.12121 on the scale
    2. Chess PuzzlesEpoch AI Benchmarking Hub0.03119 on the scale
    3. SimpleQA VerifiedEpoch AI Benchmarking Hub0.08115 on the scale
    4. FrontierMath-Tiers-1-3-v2-PrivateEpoch AI Benchmarking Hub0.01109 on the scale
    5. polyglot pass rateAider polyglot3.6097 on the scale
    6. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.0794 on the scale
    7. GPQA diamondEpoch AI Benchmarking Hub0.3883 on the scale
    8. MATH level 5Epoch AI Benchmarking Hub0.5381 on the scale
  295. 295gpt-4-turbo-2024-04-09not in the catalogunstated80.0741

    4 columns on 1 board, hardest first are the whole evidence behind 80.07. Each is a door to the column and everything else scored on it.

    1. FrontierMath-Tiers-1-3-v2-PrivateEpoch AI Benchmarking Hub0.01109 on the scale
    2. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.0794 on the scale
    3. GPQA diamondEpoch AI Benchmarking Hub0.4783 on the scale
    4. MATH level 5Epoch AI Benchmarking Hub0.4781 on the scale
  296. 296mistral-small-2501not in the catalogunstated79.6231

    3 columns on 1 board, hardest first are the whole evidence behind 79.62. Each is a door to the column and everything else scored on it.

    1. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.0594 on the scale
    2. GPQA diamondEpoch AI Benchmarking Hub0.4583 on the scale
    3. MATH level 5Epoch AI Benchmarking Hub0.4581 on the scale
  297. 297gemini-1.5-pro-001not in the catalogunstated79.2531

    3 columns on 1 board, hardest first are the whole evidence behind 79.25. Each is a door to the column and everything else scored on it.

    1. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.0794 on the scale
    2. GPQA diamondEpoch AI Benchmarking Hub0.4683 on the scale
    3. MATH level 5Epoch AI Benchmarking Hub0.4181 on the scale
  298. 298meta-llama/llama-3.3-70b-instructunstated79.2231

    3 columns on 1 board, hardest first are the whole evidence behind 79.22. Each is a door to the column and everything else scored on it.

    1. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.0594 on the scale
    2. GPQA diamondEpoch AI Benchmarking Hub0.4783 on the scale
    3. MATH level 5Epoch AI Benchmarking Hub0.4281 on the scale
  299. 299llama-3.1-tulu-3-70b-dponot in the catalogunstated79.2031

    3 columns on 1 board, hardest first are the whole evidence behind 79.20. Each is a door to the column and everything else scored on it.

    1. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.0494 on the scale
    2. GPQA diamondEpoch AI Benchmarking Hub0.4683 on the scale
    3. MATH level 5Epoch AI Benchmarking Hub0.4381 on the scale
  300. 300claude-3-opus-20240229not in the catalogunstated78.8851

    5 columns on 1 board, hardest first are the whole evidence behind 78.88. Each is a door to the column and everything else scored on it.

    1. Chess PuzzlesEpoch AI Benchmarking Hub0.04119 on the scale
    2. SimpleQA VerifiedEpoch AI Benchmarking Hub0.13115 on the scale
    3. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.0594 on the scale
    4. GPQA diamondEpoch AI Benchmarking Hub0.4783 on the scale
    5. MATH level 5Epoch AI Benchmarking Hub0.3781 on the scale
  301. 301llama-3.2-90b-vision-instructnot in the catalogunstated77.9331

    3 columns on 1 board, hardest first are the whole evidence behind 77.93. Each is a door to the column and everything else scored on it.

    1. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.0394 on the scale
    2. GPQA diamondEpoch AI Benchmarking Hub0.4183 on the scale
    3. MATH level 5Epoch AI Benchmarking Hub0.3981 on the scale
  302. 302meta-llama/llama-3.1-70b-instructunstated77.8631

    3 columns on 1 board, hardest first are the whole evidence behind 77.86. Each is a door to the column and everything else scored on it.

    1. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.0494 on the scale
    2. GPQA diamondEpoch AI Benchmarking Hub0.4483 on the scale
    3. MATH level 5Epoch AI Benchmarking Hub0.3781 on the scale
  303. 303gemini-1.5-flash-001not in the catalogunstated75.3531

    3 columns on 1 board, hardest first are the whole evidence behind 75.35. Each is a door to the column and everything else scored on it.

    1. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.0494 on the scale
    2. GPQA diamondEpoch AI Benchmarking Hub0.4083 on the scale
    3. MATH level 5Epoch AI Benchmarking Hub0.2581 on the scale
  304. 304google/gemma-2-27b-itunstated75.0331

    3 columns on 1 board, hardest first are the whole evidence behind 75.03. Each is a door to the column and everything else scored on it.

    1. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.0194 on the scale
    2. GPQA diamondEpoch AI Benchmarking Hub0.3683 on the scale
    3. MATH level 5Epoch AI Benchmarking Hub0.2881 on the scale
  305. 305meta-llama-3-70b-instructnot in the catalogunstated74.9131

    3 columns on 1 board, hardest first are the whole evidence behind 74.91. Each is a door to the column and everything else scored on it.

    1. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.0494 on the scale
    2. GPQA diamondEpoch AI Benchmarking Hub0.4183 on the scale
    3. MATH level 5Epoch AI Benchmarking Hub0.2381 on the scale
  306. 306mistral-large-2402not in the catalogunstated74.6231

    3 columns on 1 board, hardest first are the whole evidence behind 74.62. Each is a door to the column and everything else scored on it.

    1. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.0294 on the scale
    2. GPQA diamondEpoch AI Benchmarking Hub0.3983 on the scale
    3. MATH level 5Epoch AI Benchmarking Hub0.2481 on the scale
  307. 307gpt-4-0613not in the catalogunstated74.5641

    4 columns on 1 board, hardest first are the whole evidence behind 74.56. Each is a door to the column and everything else scored on it.

    1. Mystery Game PuzzlesEpoch AI Benchmarking Hub0.12121 on the scale
    2. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.0194 on the scale
    3. GPQA diamondEpoch AI Benchmarking Hub0.3183 on the scale
    4. MATH level 5Epoch AI Benchmarking Hub0.2381 on the scale
  308. 308hermes-2-theta-llama-3-70bnot in the catalogunstated74.2131

    3 columns on 1 board, hardest first are the whole evidence behind 74.21. Each is a door to the column and everything else scored on it.

    1. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.0394 on the scale
    2. GPQA diamondEpoch AI Benchmarking Hub0.3783 on the scale
    3. MATH level 5Epoch AI Benchmarking Hub0.2381 on the scale
  309. 309claude-3-sonnet-20240229not in the catalogunstated73.4631

    3 columns on 1 board, hardest first are the whole evidence behind 73.46. Each is a door to the column and everything else scored on it.

    1. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.0394 on the scale
    2. GPQA diamondEpoch AI Benchmarking Hub0.4183 on the scale
    3. MATH level 5Epoch AI Benchmarking Hub0.1881 on the scale
  310. 310meta-llama/llama-3.1-8b-instructunstated72.8931

    3 columns on 1 board, hardest first are the whole evidence behind 72.89. Each is a door to the column and everything else scored on it.

    1. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.0294 on the scale
    2. GPQA diamondEpoch AI Benchmarking Hub0.2783 on the scale
    3. MATH level 5Epoch AI Benchmarking Hub0.2381 on the scale
  311. 311gemma-2-9b-itnot in the catalogunstated72.1431

    3 columns on 1 board, hardest first are the whole evidence behind 72.14. Each is a door to the column and everything else scored on it.

    1. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.0194 on the scale
    2. GPQA diamondEpoch AI Benchmarking Hub0.2783 on the scale
    3. MATH level 5Epoch AI Benchmarking Hub0.2181 on the scale
  312. 312claude-3-haiku-20240307not in the catalogunstated71.8731

    3 columns on 1 board, hardest first are the whole evidence behind 71.87. Each is a door to the column and everything else scored on it.

    1. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.0294 on the scale
    2. GPQA diamondEpoch AI Benchmarking Hub0.3683 on the scale
    3. MATH level 5Epoch AI Benchmarking Hub0.1581 on the scale
  313. 313claude-2.0not in the catalogunstated70.9131

    3 columns on 1 board, hardest first are the whole evidence behind 70.91. Each is a door to the column and everything else scored on it.

    1. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.0394 on the scale
    2. GPQA diamondEpoch AI Benchmarking Hub0.3583 on the scale
    3. MATH level 5Epoch AI Benchmarking Hub0.1281 on the scale
  314. 314gemini-1.0-pro-001not in the catalogunstated70.1831

    3 columns on 1 board, hardest first are the whole evidence behind 70.18. Each is a door to the column and everything else scored on it.

    1. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.0194 on the scale
    2. GPQA diamondEpoch AI Benchmarking Hub0.3483 on the scale
    3. MATH level 5Epoch AI Benchmarking Hub0.1181 on the scale
  315. 315gpt-3.5-turbo-0125not in the catalogunstated69.9251

    5 columns on 1 board, hardest first are the whole evidence behind 69.92. Each is a door to the column and everything else scored on it.

    1. Mystery Game PuzzlesEpoch AI Benchmarking Hub0.03121 on the scale
    2. FrontierMath-Tiers-1-3-v2-PrivateEpoch AI Benchmarking Hub0109 on the scale
    3. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.0294 on the scale
    4. GPQA diamondEpoch AI Benchmarking Hub0.2783 on the scale
    5. MATH level 5Epoch AI Benchmarking Hub0.1281 on the scale
  316. 316meta-llama-3-8b-instructnot in the catalogunstated67.0131

    3 columns on 1 board, hardest first are the whole evidence behind 67.01. Each is a door to the column and everything else scored on it.

    1. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.0294 on the scale
    2. GPQA diamondEpoch AI Benchmarking Hub0.2683 on the scale
    3. MATH level 5Epoch AI Benchmarking Hub0.0681 on the scale
  317. 317deepseek-llm-67b-chatnot in the catalogunstated66.2331

    3 columns on 1 board, hardest first are the whole evidence behind 66.23. Each is a door to the column and everything else scored on it.

    1. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.0194 on the scale
    2. GPQA diamondEpoch AI Benchmarking Hub0.2583 on the scale
    3. MATH level 5Epoch AI Benchmarking Hub0.0681 on the scale
  318. 318llama-2-70b-chat-hfnot in the catalogunstated64.4031

    3 columns on 1 board, hardest first are the whole evidence behind 64.40. Each is a door to the column and everything else scored on it.

    1. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub094 on the scale
    2. GPQA diamondEpoch AI Benchmarking Hub0.2683 on the scale
    3. MATH level 5Epoch AI Benchmarking Hub0.0381 on the scale
  319. 319mistral-7b-instruct-v0.3not in the catalogunstated60.8431

    3 columns on 1 board, hardest first are the whole evidence behind 60.84. Each is a door to the column and everything else scored on it.

    1. OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub0.0094 on the scale
    2. GPQA diamondEpoch AI Benchmarking Hub0.1583 on the scale
    3. MATH level 5Epoch AI Benchmarking Hub0.0481 on the scale

319 of 319 ranked runs, highest on the scale first. Position is the run's place on the scale and stays with it under any order. A row opens onto the cells behind its index, which is the same join the fit was given.

A run on 3 columns and one on 38 print the same width here and are not the same claim, which is why both counts travel on the row. A run whose model the catalog does not list keeps the spelling its publisher used and is marked; it contributes to the fit and to every column difficulty, and carries no price here because nothing in the record prices it. Effort is unstated where the publisher wrote no setting on the run, which is not the same as minimal. The 428 runs scored only on columns kept off this axis are not in the ledger at all, and the column ledger below names those columns and says why.

Benchmark columns46 columns · 3 of 6 mirrored boardshardest first
The span is where a run goes from one chance in four to three in four; the shading is where the ranked runs are.
column · boarddifficulty · slope · runs
FrontierMath-ErdosEpoch AI Benchmarking Hub+3.55 · 2.23 · 16 runs

16 runs scored on it, 16 of them ranked, best score first, in the publisher's own unit. A ranked run is a door to its row.

  1. gpt-6.2-astramax · not in the catalog0.10135.84
  2. openai/gpt-6.1-solmax0.04130.00
  3. openai/gpt-6-astramax0.03132.41
  4. google/gemini-4-carbonhigh0.03131.68
  5. claude-opus-5-5max · not in the catalog0.03128.09
  6. claude-sonnet-5-5max · not in the catalog0.03122.13
  7. google/gemini-4-argonhigh0.01124.90
  8. openai/gpt-6-solmax0.01124.00
  9. anthropic/claude-fable-5max0122.58
  10. anthropic/claude-opus-5max0122.24
  11. google/gemini-3.8-flashhigh0114.21
  12. moonshotai/kimi-k3max0114.75
  13. openai/gpt-5.5xhigh0120.29
  14. openai/gpt-5.6-solmax0123.35
  15. claude-fable-5-1max · not in the catalog0125.12
  16. x-ai/grok-4.7xhigh0113.32
SpireClimb (Slay the Spire 1, Ascension 20 Heart)Epoch AI Benchmarking Hub+2.57 · 3.35 · 12 runs

12 runs scored on it, 12 of them ranked, best score first, in the publisher's own unit. A ranked run is a door to its row.

  1. openai/gpt-6-astramax0.33132.41
  2. gpt-6.2-astramax · not in the catalog0.33135.84
  3. openai/gpt-6.1-solmax0.18130.00
  4. claude-fable-5-2max · not in the catalog0.13132.06
  5. google/gemini-4-hydrogenxhigh0.10125.83
  6. openai/gpt-6.1-terramax0.10130.85
  7. openai/gpt-6-solmax0.05124.00
  8. claude-opus-5-5max · not in the catalog0.05128.09
  9. openai/gpt-6-lunamax0113.99
  10. claude-fable-5-1max · not in the catalog0125.12
  11. claude-sonnet-5-5max · not in the catalog0122.13
  12. kimi-k3.1-pro-togethermax · not in the catalog0118.88
SpireClimbEpoch AI Benchmarking Hub+2.48 · 3.35 · 12 runs

12 runs scored on it, 12 of them ranked, best score first, in the publisher's own unit. A ranked run is a door to its row.

  1. gpt-6.2-astramax · not in the catalog0.41135.84
  2. openai/gpt-6-astramax0.34132.41
  3. openai/gpt-6.1-solmax0.24130.00
  4. openai/gpt-6.1-terramax0.22130.85
  5. claude-fable-5-2max · not in the catalog0.15132.06
  6. openai/gpt-6-solmax0.09124.00
  7. google/gemini-4-hydrogenxhigh0.08125.83
  8. claude-opus-5-5max · not in the catalog0.06128.09
  9. claude-fable-5-1max · not in the catalog0.02125.12
  10. claude-sonnet-5-5max · not in the catalog0.01122.13
  11. openai/gpt-6-lunamax0113.99
  12. kimi-k3.1-pro-togethermax · not in the catalog0118.88
SpireClimb (Slay the Spire 2, Ascension 10)Epoch AI Benchmarking Hub+2.40 · 3.40 · 12 runs

12 runs scored on it, 12 of them ranked, best score first, in the publisher's own unit. A ranked run is a door to its row.

  1. gpt-6.2-astramax · not in the catalog0.49135.84
  2. openai/gpt-6-astramax0.35132.41
  3. openai/gpt-6.1-terramax0.35130.85
  4. openai/gpt-6.1-solmax0.29130.00
  5. claude-fable-5-2max · not in the catalog0.17132.06
  6. openai/gpt-6-solmax0.13124.00
  7. claude-opus-5-5max · not in the catalog0.07128.09
  8. google/gemini-4-hydrogenxhigh0.05125.83
  9. claude-fable-5-1max · not in the catalog0.04125.12
  10. claude-sonnet-5-5max · not in the catalog0.03122.13
  11. openai/gpt-6-lunamax0113.99
  12. kimi-k3.1-pro-togethermax · not in the catalog0118.88
OEIS OpenEpoch AI Benchmarking Hub+1.80 · 1.22 · 3 runs

3 runs scored on it, 1 of them ranked, best score first, in the publisher's own unit. A ranked run is a door to its row.

  1. claude-opus-4-8high · not in the catalog0.30set aside
  2. openai/gpt-5.5medium0.26set aside
  3. google/gemini-3.5-flashhigh0.22111.12
EBR-benchEpoch AI Benchmarking Hub+1.53 · 2.20 · 34 runs

34 runs scored on it, 33 of them ranked, best score first, in the publisher's own unit. A ranked run is a door to its row.

  1. gpt-6.2-astramax · not in the catalog0.92135.84
  2. claude-fable-5-2max · not in the catalog0.90132.06
  3. google/gemini-4-carbonhigh0.88131.68
  4. openai/gpt-6.1-terramax0.78130.85
  5. openai/gpt-6-astramax0.76132.41
  6. claude-opus-5-5max · not in the catalog0.71128.09
  7. google/gemini-4-hydrogenxhigh0.70125.83
  8. google/gemini-4-argonhigh0.65124.90
  9. claude-fable-5-1max · not in the catalog0.57125.12
  10. openai/gpt-6.1-solmax0.54130.00
  11. openai/gpt-6-solmax0.53124.00
  12. anthropic/claude-opus-5max0.46122.24
  13. openai/gpt-5.6-solmax0.45123.35
  14. claude-haiku-5-5max · not in the catalog0.44113.88
  15. anthropic/claude-fable-5max0.40122.58
  16. kimi-k3.1-pro-togethermax · not in the catalog0.37118.88
  17. openai/gpt-5.5xhigh0.34120.29
  18. muse-wonder-1.0max · not in the catalog0.31120.86
  19. x-ai/grok-4.6xhigh0.30114.39
  20. claude-opus-4-8max · not in the catalog0.29116.89
  21. gpt-5.4-2026-03-05xhigh · not in the catalog0.25116.23
  22. gpt-5.2-2025-12-11xhigh · not in the catalog0.23113.39
  23. claude-opus-4-7max · not in the catalog0.19113.03
  24. mistral-large-4-0-osshigh · not in the catalog0.18110.78
  25. google/gemini-3.1-pro-previewunstated0.14111.66
  26. claude-opus-4-5-20251101-128kunstated · not in the catalog0.14set aside
  27. claude-opus-4-6max · not in the catalog0.13111.69
  28. gpt-5-2025-08-07high · not in the catalog0.13108.61
  29. qwen/qwen3.7-maxunstated0.10111.06
  30. z-ai/glm-5.2max0.10110.33
  31. claude-opus-4-1-20250805unstated · not in the catalog0.0893.81
  32. google/gemini-3.5-flashhigh0.05111.12
  33. moonshotai/kimi-k2.6unstated0.02110.82
  34. claude-sonnet-4-5-20250929unstated · not in the catalog0.0293.21
OEIS Open LiteEpoch AI Benchmarking Hub+1.47 · 1.22 · 5 runs

5 runs scored on it, 2 of them ranked, best score first, in the publisher's own unit. A ranked run is a door to its row.

  1. anthropic/claude-fable-5high0.44119.29
  2. openai/gpt-5.6-solmedium0.43set aside
  3. claude-opus-4-8high · not in the catalog0.39set aside
  4. openai/gpt-5.5medium0.36set aside
  5. google/gemini-3.5-flashhigh0.29111.12
typescriptLiveBench+1.46 · 0.86 · 71 runs

71 runs scored on it, 71 of them ranked, best score first, in the publisher's own unit. A ranked run is a door to its row.

  1. claude-opus-5-5max · not in the catalog63.33128.09
  2. deepseek/deepseek-v4.1-flashmax60116.49
  3. meta/muse-spark-1.3xhigh60116.79
  4. claude-fable-5-1max · not in the catalog60125.12
  5. muse-wonder-1.0max · not in the catalog60120.86
  6. deepseek/deepseek-v4-flash-vision-expunstated56.67116.36
  7. claude-sonnet-5-5max · not in the catalog56.67122.13
  8. qwen3.8-maxunstated · not in the catalog56.67118.08
  9. smaug-agenticunstated · not in the catalog56.67116.30
  10. anthropic/claude-fable-5max53.33122.58
  11. moonshotai/kimi-k3unstated53.33116.54
  12. claude-opus-5-5xhigh · not in the catalog53.33125.14
  13. smaug-miniunstated · not in the catalog53.33114.73
  14. anthropic/claude-sonnet-5xhigh50113.50
  15. meta/muse-spark-1.2xhigh50117.04
  16. openai/gpt-5.6-solmax50123.35
  17. qwen/qwen3.8-27bunstated50112.72
  18. smaug-flashunstated · not in the catalog50116.63
  19. z-ai/glm-5.3unstated50112.92
  20. deepseek/deepseek-v4-pro-0813unstated46.67118.60
  21. google/gemini-3.7-flashhigh46.67116.01
  22. openai/gpt-5.6-terramax46.67119.24
  23. openai/gpt-6.1-solxhigh46.67124.64
  24. claude-sonnet-5-5xhigh · not in the catalog46.67119.88
  25. qwen3.8-flash-nextunstated · not in the catalog46.67113.12
  26. z-ai/glm-5.3-flashunstated46.67108.42
  27. anthropic/claude-opus-5max43.33122.24
  28. meta/muse-spark-1.1xhigh43.33114.21
  29. openai/gpt-5.4xhigh43.33119.02
  30. openai/gpt-5.5xhigh43.33120.29
  31. openai/gpt-6-astramax43.33132.41
  32. claude-haiku-5-5max · not in the catalog43.33113.88
  33. claude-opus-4-7xhigh · not in the catalog43.33113.14
  34. mistral-large-4high · not in the catalog43.33109.81
  35. ox-alphamax · not in the catalog43.33106.05
  36. x-ai/grok-4.6unstated43.33117.62
  37. x-ai/grok-4.7xhigh43.33113.32
  38. google/gemini-3.8-flashhigh40114.21
  39. openai/gpt-6-lunamax40113.99
  40. openai/gpt-6-solmax40124.00
  41. openai/gpt-6.1-solmax40130.00
  42. claude-haiku-5-5xhigh · not in the catalog40112.88
  43. openai/gpt-5.6-lunamax36.67114.95
  44. gpt-5.2-2025-12-11high · not in the catalog36.67110.74
  45. x-ai/grok-4.5unstated36.67114.74
  46. z-ai/glm-5.2unstated36.67109.40
  47. google/gemini-3.5-flashhigh33.33111.12
  48. claude-opus-4-6-thinking-autohigh · not in the catalog33.33113.04
  49. claude-opus-4-8max · not in the catalog33.33116.89
  50. x-ai/grok-build-0.1unstated33.33106.25
  51. thinkingmachines/inklingxhigh30107.98
  52. deepseek/deepseek-v4-flash-0731unstated26.67113.47
  53. google/gemini-3.5-flash-litehigh26.6799.97
  54. google/gemini-3.6-flashhigh26.67110.95
  55. openai/gpt-5.4-nanoxhigh26.67110.30
  56. qwen/qwen3.7-maxunstated26.67111.06
  57. kimi-k2.6-thinkingunstated · not in the catalog26.67107.26
  58. deepseek/deepseek-v4-flashunstated23.33102.96
  59. deepseek/deepseek-v4-prounstated23.33111.64
  60. google/gemini-3.1-pro-previewhigh23.33113.89
  61. minimax/minimax-m3unstated23.33104.58
  62. moonshotai/kimi-k2.7-codeunstated23.33107.73
  63. qwen/qwen3.6-27bunstated23.33103.72
  64. claude-sonnet-4-6-thinking-automedium · not in the catalog23.33114.06
  65. openai/gpt-5.2-codexunstated20110.02
  66. openai/gpt-5.4-minixhigh20104.22
  67. qwen/qwen3.6-plusunstated20106.49
  68. claude-opus-4-5-20251101-thinking-64khigh · not in the catalog20110.65
  69. nvidia/nemotron-3-ultra-550b-a55bunstated16.67105.72
  70. x-ai/grok-4.3unstated13.33103.07
  71. nemotron-3.5-lightning-30b-a3bunstated · not in the catalog6.6787.31
Mystery Game PuzzlesEpoch AI Benchmarking Hub+1.42 · 1.36 · 149 runs

149 runs scored on it, 118 of them ranked, best score first, in the publisher's own unit. A ranked run is a door to its row.

  1. gpt-6.2-astramax · not in the catalog0.95135.84
  2. claude-fable-5-2max · not in the catalog0.90132.06
  3. gemini-4-neonxhigh · not in the catalog0.85134.54
  4. openai/gpt-6-astramax0.84132.41
  5. openai/gpt-6.1-solmax0.80130.00
  6. openai/gpt-6.1-terramax0.74130.85
  7. google/gemini-4-carbonhigh0.73131.68
  8. claude-opus-5-5max · not in the catalog0.71128.09
  9. google/gemini-4-hydrogenxhigh0.65125.83
  10. claude-sonnet-5-5max · not in the catalog0.65122.13
  11. google/gemini-4-argonhigh0.64124.90
  12. anthropic/claude-opus-5max0.59122.24
  13. openai/gpt-5.6-solmax0.58123.35
  14. claude-fable-5-1max · not in the catalog0.58125.12
  15. openai/gpt-5.5xhigh0.56120.29
  16. openai/gpt-6-solmax0.56124.00
  17. anthropic/claude-fable-5max0.52122.58
  18. openai/gpt-5.5high0.52set aside
  19. muse-wonder-1.0max · not in the catalog0.51120.86
  20. deepseek/deepseek-v4.1-flash-1017max0.49116.25
  21. google/gemini-3.8-flashhigh0.47114.21
  22. deepseek/deepseek-v4-pro-0813max0.43113.60
  23. deepseek/deepseek-v4.1-flashmax0.43116.49
  24. kimi-k3.1-pro-togethermax · not in the catalog0.42118.88
  25. qwen3.8-maxxhigh · not in the catalog0.38116.39
  26. anthropic/claude-opus-5unstated0.37115.94
  27. google/gemini-3.7-flashhigh0.37116.01
  28. gpt-5.4-2026-03-05xhigh · not in the catalog0.37116.23
  29. claude-opus-4-8max · not in the catalog0.36116.89
  30. anthropic/claude-sonnet-5max0.35112.43
  31. openai/gpt-5.6-terramax0.35119.24
  32. deepseek/deepseek-v4-flash-0731max0.34111.14
  33. google/gemini-3.1-pro-previewhigh0.34113.89
  34. x-ai/grok-4.6xhigh0.34114.39
  35. openai/gpt-5.6-solnone0.33100.98
  36. z-ai/glm-5.3max0.33112.54
  37. google/gemini-3.1-pro-previewmedium0.32set aside
  38. google/gemini-3.5-flashhigh0.32111.12
  39. qwen/qwen3.7-maxunstated0.32111.06
  40. claude-opus-4-8xhigh · not in the catalog0.31set aside
  41. google/gemini-3.6-flashhigh0.30110.95
  42. claude-haiku-5-5max · not in the catalog0.30113.88
  43. google/gemini-3.1-pro-previewlow0.29set aside
  44. o3-2025-04-16high · not in the catalog0.29102.96
  45. x-ai/grok-4.7xhigh0.29113.32
  46. google/gemini-3.5-flashlow0.28110.83
  47. openai/gpt-5.5low0.28107.86
  48. claude-opus-4-7max · not in the catalog0.28113.03
  49. gpt-5.4-2026-03-05medium · not in the catalog0.28112.04
  50. google/gemini-3-flash-previewlow0.26set aside
  51. moonshotai/kimi-k3max0.26114.75
  52. openai/gpt-5.6-sollow0.26110.85
  53. qwen/qwen3.7-maxnone0.26set aside
  54. google/gemini-3-flash-previewminimal0.25set aside
  55. google/gemini-3.6-flashminimal0.25105.55
  56. meta/muse-spark-1.3max0.25115.55
  57. claude-opus-4-6max · not in the catalog0.25111.69
  58. google/gemini-3.6-flashlow0.23107.80
  59. gpt-5-2025-08-07high · not in the catalog0.23108.61
  60. gpt-5.2-2025-12-11high · not in the catalog0.23110.74
  61. o3-2025-04-16medium · not in the catalog0.23101.11
  62. qwen/qwen3.6-35b-a3bnone0.22100.22
  63. claude-opus-4-5-20251101-48kunstated · not in the catalog0.22set aside
  64. gpt-5.2-2025-12-11medium · not in the catalog0.22108.75
  65. openai/gpt-5.6-lunamax0.21114.95
  66. claude-opus-4-1-20250805-24kunstated · not in the catalog0.21set aside
  67. google/gemini-3-flash-previewhigh0.20113.70
  68. openai/gpt-5.6-lunanone0.2095.93
  69. mistral-large-4-0-osshigh · not in the catalog0.20110.78
  70. nemotron-3-ultraunstated · not in the catalog0.20105.62
  71. qwen3.5-flashunstated · not in the catalog0.2099.58
  72. google/gemini-3.5-flash-litelow0.1998.68
  73. openai/gpt-5.6-terralow0.19106.93
  74. gpt-5.1-2025-11-13low · not in the catalog0.19100.64
  75. qwen3.6-max-previewnone · not in the catalog0.19set aside
  76. z-ai/glm-5.2low0.19105.42
  77. moonshotai/kimi-k2.6unstated0.18110.82
  78. openai/gpt-5.5none0.1897.11
  79. qwen/qwen3.5-397b-a17bnone0.18103.55
  80. qwen/qwen3.6-flashnone0.18set aside
  81. z-ai/glm-5.2minimal0.18set aside
  82. z-ai/glm-5.2none0.1896.22
  83. deepseek/deepseek-v4-pronone0.1794.28
  84. mistralai/mistral-large-4-0high0.17110.63
  85. openai/gpt-5.6-lunalow0.17101.92
  86. qwen/qwen3.5-122b-a10bnone0.17set aside
  87. qwen/qwen3.7-plusunstated0.17107.80
  88. qwen/qwen3.7-plusnone0.17103.17
  89. claude-sonnet-4-5-20250929-48kunstated · not in the catalog0.17set aside
  90. gpt-5.4-2026-03-05low · not in the catalog0.17104.16
  91. qwen3.5-plusnone · not in the catalog0.17set aside
  92. anthropic/claude-sonnet-5unstated0.16set aside
  93. claude-sonnet-4-6low · not in the catalog0.16set aside
  94. gpt-5-2025-08-07low · not in the catalog0.16105.22
  95. gpt-5.1-2025-11-13medium · not in the catalog0.16105.41
  96. gpt-5.4-2026-03-05none · not in the catalog0.1696.15
  97. qwen3.5-flashnone · not in the catalog0.16set aside
  98. qwen3.5-plusunstated · not in the catalog0.16105.31
  99. qwen/qwen3.7-flashunstated0.15102.16
  100. claude-opus-4-6unstated · not in the catalog0.15110.08
  101. gpt-5-2025-08-07medium · not in the catalog0.15108.12
  102. gpt-5.1-2025-11-13none · not in the catalog0.1591.90
  103. z-ai/glm-5.2medium0.15set aside
  104. meta/muse-spark-1.3xhigh0.14116.79
  105. openai/gpt-5.6-terranone0.1495.57
  106. qwen/qwen3.7-flashnone0.14100.54
  107. claude-sonnet-4-6unstated · not in the catalog0.14set aside
  108. gpt-5-2025-08-07minimal · not in the catalog0.1495.14
  109. gpt-5.2-2025-12-11none · not in the catalog0.1496.53
  110. claude-opus-4-7unstated · not in the catalog0.13set aside
  111. google/gemini-3.5-flash-liteminimal0.1294.95
  112. moonshotai/kimi-k2.6none0.12set aside
  113. moonshotai/kimi-k3low0.12100.12
  114. openai/gpt-4o-mini-2024-07-18unstated0.1280.10
  115. openai/gpt-5.6-lunamedium0.12set aside
  116. qwen/qwen3.6-flashunstated0.12100.95
  117. qwen/qwen3.6-plusnone0.12set aside
  118. gpt-4-0613unstated · not in the catalog0.1274.56
  119. gpt-5.4-mini-2026-03-17none · not in the catalog0.1190.48
  120. openai/gpt-5.6-terramedium0.10set aside
  121. gpt-5-mini-2025-08-07minimal · not in the catalog0.1093.86
  122. gpt-5.2-2025-12-11low · not in the catalog0.10104.89
  123. qwen/qwen3-235b-a22b-thinking-2507unstated0.09104.10
  124. gpt-5-nano-2025-08-07low · not in the catalog0.0992.74
  125. gpt-5-nano-2025-08-07medium · not in the catalog0.0999.03
  126. gpt-5.4-nano-2026-03-17none · not in the catalog0.0991.33
  127. minimax/minimax-m3none0.0890.84
  128. gpt-5-nano-2025-08-07high · not in the catalog0.08100.45
  129. gpt-5.4-mini-2026-03-17low · not in the catalog0.08set aside
  130. z-ai/glm-5.3-flashmax0.08108.45
  131. minimax/minimax-m3unstated0.07104.58
  132. openai/gpt-6-lunamax0.07113.99
  133. qwen/qwen3.6-27bnone0.07100.32
  134. claude-opus-4-6low · not in the catalog0.07set aside
  135. gpt-4.1-mini-2025-04-14unstated · not in the catalog0.0793.48
  136. gpt-5.4-mini-2026-03-17medium · not in the catalog0.07set aside
  137. o3-mini-2025-01-31high · not in the catalog0.07102.45
  138. thinkingmachines/inkling-smallxhigh0.06106.54
  139. gpt-5.4-nano-2026-03-17medium · not in the catalog0.06set aside
  140. gpt-5-mini-2025-08-07high · not in the catalog0.05104.57
  141. gpt-5-nano-2025-08-07minimal · not in the catalog0.0588.08
  142. gpt-5.4-nano-2026-03-17high · not in the catalog0.05106.76
  143. o4-mini-2025-04-16high · not in the catalog0.05103.35
  144. qwen3-max-2025-09-23unstated · not in the catalog0.05100.03
  145. gpt-5-mini-2025-08-07medium · not in the catalog0.04103.83
  146. gpt-3.5-turbo-0125unstated · not in the catalog0.0369.92
  147. gpt-5.4-nano-2026-03-17low · not in the catalog0.0398.40
  148. openai/gpt-oss-120bmedium0.02set aside
  149. openai/gpt-oss-120bhigh0set aside
FrontierMath-Tier-4-2025-07-01-PrivateEpoch AI Benchmarking Hub+1.36 · 2.81 · 72 runs

72 runs scored on it, 63 of them ranked, best score first, in the publisher's own unit. A ranked run is a door to its row.

  1. gdm-ai-co-mathematicianunstated · not in the catalog0.48set aside
  2. gpt-5.5-pro-pre-releasehigh · not in the catalog0.40set aside
  3. gpt-5.5-pro-pre-releasexhigh · not in the catalog0.40117.38
  4. gpt-5.4-pro-2026-03-05-web-appunstated · not in the catalog0.38set aside
  5. gpt-5.5-pre-releasexhigh · not in the catalog0.35116.86
  6. gpt-5.2-pro-2025-12-11-webappunstated · not in the catalog0.31set aside
  7. claude-opus-4-8max · not in the catalog0.31116.89
  8. gpt-5.4-2026-03-05xhigh · not in the catalog0.27116.23
  9. claude-opus-4-7xhigh · not in the catalog0.23113.14
  10. claude-opus-4-6max · not in the catalog0.23111.69
  11. claude-opus-4-6-32kunstated · not in the catalog0.21111.03
  12. claude-opus-4-6-64kunstated · not in the catalog0.21111.92
  13. gpt-5.2-2025-12-11high · not in the catalog0.19110.74
  14. gpt-5.2-2025-12-11xhigh · not in the catalog0.19113.39
  15. gemini-3-pro-previewunstated · not in the catalog0.19110.74
  16. google/gemini-3.1-pro-previewunstated0.17111.66
  17. gpt-5.2-2025-12-11medium · not in the catalog0.17108.75
  18. gpt-5-pro-2025-10-06high · not in the catalog0.15109.23
  19. muse-sparkunstated · not in the catalog0.15110.41
  20. google/gemini-3.5-flashhigh0.15111.12
  21. claude-opus-4-6unstated · not in the catalog0.15110.08
  22. moonshotai/kimi-k2.6unstated0.15110.82
  23. gpt-5-2025-08-07high · not in the catalog0.13108.61
  24. gpt-5.1-2025-11-13high · not in the catalog0.13109.94
  25. z-ai/glm-5.1unstated0.13109.27
  26. gemini-2.5-deep-think-2025-08-01-webappunstated · not in the catalog0.10set aside
  27. qwen/qwen3.6-plusunstated0.08106.49
  28. claude-sonnet-4-6-16kunstated · not in the catalog0.08109.98
  29. gpt-5-2025-08-07medium · not in the catalog0.06108.12
  30. gpt-5-mini-2025-08-07high · not in the catalog0.06104.57
  31. gpt-5.2-2025-12-11low · not in the catalog0.06104.89
  32. gpt-5.4-nano-2026-03-17high · not in the catalog0.06106.76
  33. o4-mini-2025-04-16high · not in the catalog0.06103.35
  34. fireworks/kimi-k2p5unstated · not in the catalog0.04107.32
  35. google/gemini-2.5-flashunstated0.04set aside
  36. google/gemini-2.5-prounstated0.04103.73
  37. google/gemini-3-flash-previewunstated0.04108.16
  38. claude-opus-4-1-20250805-27kunstated · not in the catalog0.0497.29
  39. claude-opus-4-20250514-27kunstated · not in the catalog0.0497.69
  40. claude-opus-4-5-20251101unstated · not in the catalog0.0499.92
  41. claude-opus-4-5-20251101-32kunstated · not in the catalog0.04104.05
  42. claude-sonnet-4-5-20250929-32kunstated · not in the catalog0.04101.18
  43. gpt-5-mini-2025-08-07medium · not in the catalog0.04103.83
  44. gpt-5.1-2025-11-13medium · not in the catalog0.04105.41
  45. o3-mini-2025-01-31high · not in the catalog0.04102.45
  46. qwen3.6-max-previewunstated · not in the catalog0.04106.75
  47. zai-org/glm-4.6unstated · not in the catalog0.0292.21
  48. fireworks/deepseek-v3p2unstated · not in the catalog0.02set aside
  49. z-ai/glm-5unstated0.0299.96
  50. claude-haiku-4-5-20251001-32kunstated · not in the catalog0.0296.01
  51. claude-opus-4-5-20251101-16kunstated · not in the catalog0.02104.70
  52. claude-sonnet-4-5-20250929unstated · not in the catalog0.0293.21
  53. gemini-2.5-pro-preview-06-05unstated · not in the catalog0.02103.27
  54. gpt-5-nano-2025-08-07medium · not in the catalog0.0299.03
  55. grok-4-0709unstated · not in the catalog0.02104.16
  56. o3-2025-04-16high · not in the catalog0.02102.96
  57. o4-mini-2025-04-16medium · not in the catalog0.02101.93
  58. qwen3.5-plusunstated · not in the catalog0.02105.31
  59. gpt-5.4-mini-2026-03-17high · not in the catalog0.02106.09
  60. grok-4-heavy-web-appunstated · not in the catalog0.02set aside
  61. qwen/qwen3.6-flashunstated0100.95
  62. claude-3-5-sonnet-20240620unstated · not in the catalog081.59
  63. claude-3-5-sonnet-20241022unstated · not in the catalog085.31
  64. claude-opus-4-20250514unstated · not in the catalog092.48
  65. claude-sonnet-4-20250514unstated · not in the catalog090.16
  66. gpt-4.1-2025-04-14unstated · not in the catalog091.64
  67. gpt-5-nano-2025-08-07high · not in the catalog0100.45
  68. grok-3-betaunstated · not in the catalog094.65
  69. moonshotai/kimi-k2-thinkingunstated · not in the catalog0104.82
  70. qwen/qwen3-235b-a22b-thinking-2507unstated · not in the catalog0101.29
  71. qwen3.5-flashunstated · not in the catalog099.58
  72. zai-org/glm-4.7unstated · not in the catalog0set aside
Furniture AssemblyEpoch AI Benchmarking Hub+1.31 · 1.89 · 42 runs

42 runs scored on it, 41 of them ranked, best score first, in the publisher's own unit. A ranked run is a door to its row.

  1. claude-fable-5-2max · not in the catalog0.90132.06
  2. gemini-4-neonxhigh · not in the catalog0.89134.54
  3. gpt-6.2-astramax · not in the catalog0.89135.84
  4. claude-opus-5-5max · not in the catalog0.83128.09
  5. openai/gpt-6-astramax0.80132.41
  6. openai/gpt-6.1-solmax0.80130.00
  7. openai/gpt-6.1-terramax0.79130.85
  8. google/gemini-4-carbonhigh0.78131.68
  9. claude-sonnet-5-5max · not in the catalog0.75122.13
  10. google/gemini-4-argonhigh0.72124.90
  11. claude-fable-5-1max · not in the catalog0.70125.12
  12. anthropic/claude-opus-5max0.61122.24
  13. openai/gpt-6-solmax0.58124.00
  14. google/gemini-4-hydrogenxhigh0.57125.83
  15. openai/gpt-5.6-solmax0.57123.35
  16. kimi-k3.1-pro-togethermax · not in the catalog0.56118.88
  17. openai/gpt-5.6-terramax0.54119.24
  18. muse-wonder-1.0max · not in the catalog0.54120.86
  19. claude-haiku-5-5max · not in the catalog0.47113.88
  20. openai/gpt-5.5xhigh0.44120.29
  21. openai/gpt-6-lunamax0.44113.99
  22. openai/gpt-5.6-lunamax0.42114.95
  23. claude-opus-4-8max · not in the catalog0.42116.89
  24. x-ai/grok-4.6xhigh0.40114.39
  25. gpt-5.2-2025-12-11xhigh · not in the catalog0.38113.39
  26. gpt-5.4-2026-03-05xhigh · not in the catalog0.38116.23
  27. anthropic/claude-fable-5max0.36122.58
  28. deepseek/deepseek-v4.1-flashmax0.34116.49
  29. moonshotai/kimi-k3max0.34114.75
  30. claude-opus-4-7max · not in the catalog0.33113.03
  31. google/gemini-3.8-flashhigh0.32114.21
  32. mistral-large-4-0-osshigh · not in the catalog0.31110.78
  33. claude-opus-4-5-20251101-64kunstated · not in the catalog0.28set aside
  34. claude-opus-4-6max · not in the catalog0.28111.69
  35. google/gemini-3.1-pro-previewhigh0.27113.89
  36. google/gemini-3.7-flashhigh0.27116.01
  37. google/gemini-3.6-flashhigh0.23110.95
  38. x-ai/grok-4.5high0.23111.55
  39. moonshotai/kimi-k2.6unstated0.22110.82
  40. mistralai/mistral-large-4-0high0.21110.63
  41. x-ai/grok-4.7xhigh0.21113.32
  42. qwen/qwen3.8-max-0902xhigh0.20113.51
Chess PuzzlesEpoch AI Benchmarking Hub+1.26 · 1.39 · 167 runs

167 runs scored on it, 159 of them ranked, best score first, in the publisher's own unit. A ranked run is a door to its row.

  1. gemini-4-neonxhigh · not in the catalog0.83134.54
  2. claude-fable-5-2max · not in the catalog0.79132.06
  3. google/gemini-4-carbonhigh0.78131.68
  4. gpt-6.2-astramax · not in the catalog0.78135.84
  5. gpt-6-astra-promaxunstated · not in the catalog0.76set aside
  6. openai/gpt-6-astramax0.74132.41
  7. openai/gpt-6.1-solmax0.68130.00
  8. gpt-5.6-sol-promaxunstated · not in the catalog0.68set aside
  9. claude-opus-5-5max · not in the catalog0.67128.09
  10. google/gemini-3.7-flashhigh0.66116.01
  11. openai/gpt-5.5xhigh0.63120.29
  12. openai/gpt-5.5-proxhigh0.62122.66
  13. google/gemini-4-hydrogenxhigh0.60125.83
  14. gpt-5.2-pro-2025-12-11xhigh · not in the catalog0.60116.74
  15. google/gemini-4-argonhigh0.59124.90
  16. openai/gpt-5.6-solmax0.59123.35
  17. claude-sonnet-5-5max · not in the catalog0.59122.13
  18. gpt-5.4-pro-2026-03-05xhigh · not in the catalog0.59117.92
  19. google/gemini-3.8-flashhigh0.58114.21
  20. openai/gpt-6-solmax0.56124.00
  21. claude-haiku-5-5max · not in the catalog0.55113.88
  22. claude-opus-4-8max · not in the catalog0.52116.89
  23. google/gemini-3.1-pro-previewhigh0.51113.89
  24. deepseek/deepseek-v4.1-flashmax0.48116.49
  25. claude-fable-5-1max · not in the catalog0.48125.12
  26. gpt-5-pro-2025-10-06high · not in the catalog0.48109.23
  27. gpt-5.2-2025-12-11xhigh · not in the catalog0.48113.39
  28. gpt-5.4-2026-03-05xhigh · not in the catalog0.48116.23
  29. anthropic/claude-fable-5max0.47122.58
  30. openai/gpt-5.6-terramax0.47119.24
  31. deepseek/deepseek-v4-pro-0813max0.46113.60
  32. deepseek/deepseek-v4.1-flash-1017max0.46116.25
  33. qwen3.8-maxxhigh · not in the catalog0.46116.39
  34. anthropic/claude-fable-5high0.45119.29
  35. anthropic/claude-sonnet-5max0.45112.43
  36. google/gemini-3.5-flashhigh0.45111.12
  37. gpt-5.2-2025-12-11high · not in the catalog0.45110.74
  38. gpt-5.4-nano-2026-03-17xhigh · not in the catalog0.45set aside
  39. kimi-k3.1-pro-togethermax · not in the catalog0.45118.88
  40. anthropic/claude-opus-5max0.43122.24
  41. openai/gpt-5.6-lunamax0.43114.95
  42. google/gemini-3.5-flashlow0.42110.83
  43. google/gemini-3.6-flashlow0.42107.80
  44. gpt-5.1-2025-11-13high · not in the catalog0.42109.94
  45. gpt-5.4-2026-03-05high · not in the catalog0.42115.98
  46. claude-opus-4-7max · not in the catalog0.41113.03
  47. x-ai/grok-4.7xhigh0.41113.32
  48. google/gemini-3-flash-previewhigh0.40113.70
  49. google/gemini-3.6-flashhigh0.40110.95
  50. doubao-seed-evolvinghigh · not in the catalog0.40114.76
  51. meta/muse-spark-1.3max0.37115.55
  52. moonshotai/kimi-k3high0.37112.20
  53. qwen/qwen3.8-max-0902xhigh0.37113.51
  54. gpt-5.4-2026-03-05medium · not in the catalog0.37112.04
  55. o3-2025-04-16medium · not in the catalog0.37101.11
  56. z-ai/glm-5.3max0.37112.54
  57. moonshotai/kimi-k3max0.36114.75
  58. openai/gpt-6-lunamax0.36113.99
  59. claude-opus-4-7xhigh · not in the catalog0.36113.14
  60. gpt-5-2025-08-07high · not in the catalog0.36108.61
  61. gpt-5.2-2025-12-11medium · not in the catalog0.36108.75
  62. gpt-5.4-nano-2026-03-17high · not in the catalog0.36106.76
  63. o3-2025-04-16high · not in the catalog0.36102.96
  64. o3-2025-04-16low · not in the catalog0.3699.37
  65. x-ai/grok-4.5high0.35111.55
  66. anthropic/claude-sonnet-5xhigh0.34113.50
  67. meta/muse-spark-1.1xhigh0.34114.21
  68. meta/muse-spark-1.3xhigh0.34116.79
  69. mistralai/mistral-large-4-0high0.33110.63
  70. x-ai/grok-4.6high0.33114.02
  71. x-ai/grok-4.6xhigh0.33114.39
  72. deepseek/deepseek-v4-flash-0731max0.32111.14
  73. gpt-5-2025-08-07medium · not in the catalog0.32108.12
  74. anthropic/claude-fable-5low0.31110.20
  75. openai/gpt-5.6-sollow0.31110.85
  76. openai/gpt-5.5low0.30107.86
  77. google/gemini-3.6-flashminimal0.29105.55
  78. claude-opus-4-8low · not in the catalog0.29111.54
  79. grok-4.20-0309-reasoningunstated · not in the catalog0.29108.33
  80. mistral-large-4-0-osshigh · not in the catalog0.29110.78
  81. anthropic/claude-opus-5low0.27109.13
  82. google/gemini-3.5-flashminimal0.27104.41
  83. meta/muse-spark-1.2xhigh0.27117.04
  84. openai/gpt-5.6-terralow0.27106.93
  85. qwen/qwen3.7-maxunstated0.27111.06
  86. gpt-5-2025-08-07low · not in the catalog0.27105.22
  87. claude-opus-4-7low · not in the catalog0.26set aside
  88. doubao-seed-2.1-turbo-260628high · not in the catalog0.26108.84
  89. gpt-5.2-2025-12-11low · not in the catalog0.26104.89
  90. claude-haiku-5-5low · not in the catalog0.24set aside
  91. gpt-5-mini-2025-08-07high · not in the catalog0.24104.57
  92. claude-sonnet-4-6max · not in the catalog0.23101.17
  93. gpt-5.1-2025-11-13low · not in the catalog0.23100.64
  94. gpt-5.4-mini-2026-03-17high · not in the catalog0.23106.09
  95. gpt-5-nano-2025-08-07high · not in the catalog0.22100.45
  96. o4-mini-2025-04-16medium · not in the catalog0.22101.93
  97. z-ai/glm-5.2max0.22110.33
  98. google/gemini-3.5-flash-litelow0.2198.68
  99. thinkingmachines/inklingxhigh0.21107.98
  100. claude-opus-4-6max · not in the catalog0.21111.69
  101. doubao-seed-2.1-pro-260628high · not in the catalog0.21109.61
  102. z-ai/glm-4.7unstated0.21104.07
  103. z-ai/glm-5.3-flashmax0.21108.45
  104. moonshotai/kimi-k2.6unstated0.20110.82
  105. doubao-seed-2.0-lite-260428high · not in the catalog0.20106.42
  106. doubao-seed-2.0-pro-260215high · not in the catalog0.20108.12
  107. gpt-5.4-nano-2026-03-17low · not in the catalog0.2098.40
  108. z-ai/glm-5.1unstated0.20109.27
  109. deepseek/deepseek-v4-promax0.19107.02
  110. claude-opus-4-8none · not in the catalog0.19104.31
  111. claude-sonnet-4-6high · not in the catalog0.19102.30
  112. gpt-5.4-2026-03-05low · not in the catalog0.19104.16
  113. z-ai/glm-5.2none0.1996.22
  114. moonshotai/kimi-k3low0.18100.12
  115. x-ai/grok-4.3high0.18107.39
  116. z-ai/glm-5.2low0.18105.42
  117. minimax/minimax-m3unstated0.17104.58
  118. openai/gpt-5.6-lunalow0.17101.92
  119. gpt-5.4-mini-2026-03-17xhigh · not in the catalog0.17106.91
  120. deepseek/deepseek-v4-prohigh0.16108.20
  121. google/gemini-3.5-flash-litehigh0.1699.97
  122. qwen/qwen3.6-plusunstated0.16106.49
  123. claude-sonnet-4-6medium · not in the catalog0.16103.01
  124. gpt-5-mini-2025-08-07low · not in the catalog0.16set aside
  125. gpt-5-nano-2025-08-07low · not in the catalog0.1592.74
  126. o3-mini-2025-01-31high · not in the catalog0.15102.45
  127. o4-mini-2025-04-16low · not in the catalog0.15100.61
  128. moonshotai/kimi-k2.7-codeunstated0.14107.73
  129. claude-opus-4-5-20251101-59kunstated · not in the catalog0.14set aside
  130. qwen3.5-flashunstated · not in the catalog0.1499.58
  131. o4-mini-2025-04-16high · not in the catalog0.13103.35
  132. qwen/qwen3.6-flashunstated0.12100.95
  133. gpt-4.1-2025-04-14unstated · not in the catalog0.1191.64
  134. gpt-5-2025-08-07minimal · not in the catalog0.1195.14
  135. o1-2024-12-17low · not in the catalog0.1194.71
  136. o3-mini-2025-01-31medium · not in the catalog0.1197.94
  137. claude-sonnet-4-5-20250929-32kunstated · not in the catalog0.10101.18
  138. claude-sonnet-4-5-20250929-59kunstated · not in the catalog0.10101.26
  139. o1-2024-12-17high · not in the catalog0.1098.27
  140. openai/gpt-4o-2024-08-06unstated0.0982.76
  141. openai/gpt-5.5none0.0997.11
  142. qwen3.5-plusunstated · not in the catalog0.09105.31
  143. minimax/minimax-m3none0.0890.84
  144. claude-haiku-4-5-20251001-59kunstated · not in the catalog0.08set aside
  145. o1-2024-12-17medium · not in the catalog0.0897.81
  146. google/gemini-3.5-flash-liteminimal0.0794.95
  147. openai/gpt-5.6-solnone0.07100.98
  148. claude-sonnet-4-5-20250929unstated · not in the catalog0.0693.21
  149. gpt-5.1-2025-11-13none · not in the catalog0.0691.90
  150. o3-mini-2025-01-31low · not in the catalog0.0691.91
  151. openai/gpt-5.6-terranone0.0595.57
  152. claude-haiku-4-5-20251001-32kunstated · not in the catalog0.0596.01
  153. claude-opus-4-5-20251101unstated · not in the catalog0.0599.92
  154. claude-opus-4-5-20251101-32kunstated · not in the catalog0.05104.05
  155. seed-1.6unstated · not in the catalog0.0597.70
  156. deepseek/deepseek-v4-pronone0.0494.28
  157. claude-3-opus-20240229unstated · not in the catalog0.0478.88
  158. openai/gpt-4o-mini-2024-07-18unstated0.0380.10
  159. openai/gpt-5.6-lunanone0.0395.93
  160. gpt-5.4-2026-03-05none · not in the catalog0.0396.15
  161. gpt-5-nano-2025-08-07minimal · not in the catalog0.0288.08
  162. gpt-5.2-2025-12-11none · not in the catalog0.0296.53
  163. gpt-5.4-mini-2026-03-17none · not in the catalog0.0290.48
  164. gpt-5.4-nano-2026-03-17none · not in the catalog0.0291.33
  165. gpt-4.1-mini-2025-04-14unstated · not in the catalog0.0193.48
  166. gpt-4.1-nano-2025-04-14unstated · not in the catalog086.22
  167. gpt-5-mini-2025-08-07minimal · not in the catalog093.86
MirrorCodeEpoch AI Benchmarking Hub+1.24 · 1.35 · 48 runs

48 runs scored on it, 42 of them ranked, best score first, in the publisher's own unit. A ranked run is a door to its row.

  1. claude-sonnet-5-5max · not in the catalog0.98122.13
  2. claude-opus-5-5max · not in the catalog0.96128.09
  3. claude-fable-5-1max · not in the catalog0.93125.12
  4. anthropic/claude-opus-5max0.88122.24
  5. claude-opus-5-5high · not in the catalog0.79set aside
  6. claude-haiku-5-5max · not in the catalog0.79113.88
  7. openai/gpt-6.1-terramax0.77130.85
  8. claude-fable-5-1high · not in the catalog0.73set aside
  9. anthropic/claude-fable-5max0.70122.58
  10. gpt-6.2-astramax · not in the catalog0.68135.84
  11. claude-opus-4-8max · not in the catalog0.66116.89
  12. deepseek/deepseek-v4.1-flashmax0.64116.49
  13. anthropic/claude-fable-5high0.64119.29
  14. anthropic/claude-sonnet-5max0.63112.43
  15. openai/gpt-6.1-solmax0.61130.00
  16. openai/gpt-6-astramax0.60132.41
  17. google/gemini-4-argonhigh0.59124.90
  18. meta/muse-spark-1.3max0.54115.55
  19. moonshotai/kimi-k3max0.54114.75
  20. x-ai/grok-4.7xhigh0.54113.32
  21. qwen3.8-maxxhigh · not in the catalog0.52116.39
  22. openai/gpt-6-solmax0.49124.00
  23. qwen/qwen3.8-max-0902xhigh0.48113.51
  24. openai/gpt-6-astrahigh0.47set aside
  25. muse-wonder-1.0max · not in the catalog0.46120.86
  26. claude-opus-4-7max · not in the catalog0.43113.03
  27. kimi-k3.1-pro-togethermax · not in the catalog0.43118.88
  28. google/gemini-3.7-flashhigh0.41116.01
  29. openai/gpt-5.6-terramax0.41119.24
  30. x-ai/grok-4.6xhigh0.41114.39
  31. mistralai/mistral-large-4-0high0.40110.63
  32. google/gemini-3.8-flashhigh0.39114.21
  33. z-ai/glm-5.2max0.37110.33
  34. deepseek/deepseek-v4-pro-0813max0.33113.60
  35. claude-opus-4-6max · not in the catalog0.33111.69
  36. gpt-5.2-2025-12-11xhigh · not in the catalog0.32113.39
  37. x-ai/grok-4.5high0.32111.55
  38. claude-opus-4-7high · not in the catalog0.31set aside
  39. openai/gpt-6-lunamax0.27113.99
  40. google/gemini-3.6-flashhigh0.23110.95
  41. openai/gpt-5.5xhigh0.23120.29
  42. gpt-5.4-2026-03-05xhigh · not in the catalog0.23116.23
  43. openai/gpt-5.6-lunamax0.21114.95
  44. openai/gpt-5.6-solhigh0.20set aside
  45. gpt-5.4-2026-03-05high · not in the catalog0.16115.98
  46. openai/gpt-5.5high0.10set aside
  47. google/gemini-3.1-pro-previewhigh0.09113.89
  48. gpt-5-2025-08-07high · not in the catalog0.04108.61
tablejoinLiveBench+1.16 · 0.32 · 71 runs

71 runs scored on it, 71 of them ranked, best score first, in the publisher's own unit. A ranked run is a door to its row.

  1. openai/gpt-6-astramax58.37132.41
  2. openai/gpt-6.1-solmax57.42130.00
  3. claude-fable-5-1max · not in the catalog56.15125.12
  4. anthropic/claude-fable-5max56.13122.58
  5. openai/gpt-5.5xhigh55.90120.29
  6. openai/gpt-6.1-solxhigh55.25124.64
  7. openai/gpt-6-solmax54.02124.00
  8. google/gemini-3.1-pro-previewhigh52.35113.89
  9. claude-opus-5-5max · not in the catalog52.33128.09
  10. anthropic/claude-opus-5max51.96122.24
  11. smaug-miniunstated · not in the catalog51.87114.73
  12. openai/gpt-5.4xhigh51.75119.02
  13. smaug-agenticunstated · not in the catalog51.23116.30
  14. claude-opus-4-8max · not in the catalog51.08116.89
  15. qwen3.8-flash-nextunstated · not in the catalog51.02113.12
  16. claude-opus-5-5xhigh · not in the catalog51125.14
  17. smaug-flashunstated · not in the catalog50.71116.63
  18. openai/gpt-5.4-nanoxhigh50.59110.30
  19. google/gemini-3.5-flashhigh50.50111.12
  20. deepseek/deepseek-v4-flash-vision-expunstated50.35116.36
  21. openai/gpt-5.6-terramax50.25119.24
  22. qwen3.8-maxunstated · not in the catalog50.06118.08
  23. openai/gpt-6-lunamax49.62113.99
  24. deepseek/deepseek-v4-pro-0813unstated49.46118.60
  25. openai/gpt-5.4-minixhigh49.38104.22
  26. openai/gpt-5.6-solmax49.31123.35
  27. claude-haiku-5-5xhigh · not in the catalog49.17112.88
  28. mistral-large-4high · not in the catalog49.10109.81
  29. deepseek/deepseek-v4.1-flashmax49.04116.49
  30. z-ai/glm-5.3-flashunstated48.83108.42
  31. qwen/qwen3.8-27bunstated48.75112.72
  32. deepseek/deepseek-v4-flash-0731unstated48.54113.47
  33. thinkingmachines/inklingxhigh48.48107.98
  34. moonshotai/kimi-k3unstated48.40116.54
  35. deepseek/deepseek-v4-prounstated48.19111.64
  36. meta/muse-spark-1.3xhigh48.19116.79
  37. claude-opus-4-6-thinking-autohigh · not in the catalog48.17113.04
  38. openai/gpt-5.6-lunamax47.60114.95
  39. moonshotai/kimi-k2.7-codeunstated47.54107.73
  40. claude-opus-4-7xhigh · not in the catalog47.23113.14
  41. google/gemini-3.6-flashhigh47.13110.95
  42. ox-alphamax · not in the catalog46.94106.05
  43. claude-sonnet-5-5xhigh · not in the catalog46.88119.88
  44. meta/muse-spark-1.2xhigh46.83117.04
  45. claude-haiku-5-5max · not in the catalog46.67113.88
  46. meta/muse-spark-1.1xhigh46.56114.21
  47. nvidia/nemotron-3-ultra-550b-a55bunstated46.56105.72
  48. muse-wonder-1.0max · not in the catalog46.33120.86
  49. deepseek/deepseek-v4-flashunstated46.12102.96
  50. kimi-k2.6-thinkingunstated · not in the catalog46.10107.26
  51. claude-opus-4-5-20251101-thinking-64khigh · not in the catalog45.92110.65
  52. z-ai/glm-5.2unstated45.87109.40
  53. minimax/minimax-m3unstated45.85104.58
  54. openai/gpt-5.2-codexunstated45.60110.02
  55. gpt-5.2-2025-12-11high · not in the catalog45.58110.74
  56. qwen/qwen3.7-maxunstated45.52111.06
  57. google/gemini-3.7-flashhigh45.48116.01
  58. google/gemini-3.8-flashhigh45.33114.21
  59. claude-sonnet-4-6-thinking-automedium · not in the catalog45.08114.06
  60. x-ai/grok-4.7xhigh44.92113.32
  61. qwen/qwen3.6-plusunstated44.65106.49
  62. x-ai/grok-4.5unstated43.58114.74
  63. x-ai/grok-4.6unstated43.42117.62
  64. qwen/qwen3.6-27bunstated42.85103.72
  65. x-ai/grok-build-0.1unstated42.65106.25
  66. anthropic/claude-sonnet-5xhigh42.44113.50
  67. z-ai/glm-5.3unstated42.35112.92
  68. x-ai/grok-4.3unstated41.25103.07
  69. google/gemini-3.5-flash-litehigh40.6299.97
  70. nemotron-3.5-lightning-30b-a3bunstated · not in the catalog40.4887.31
  71. claude-sonnet-5-5max · not in the catalog39.81122.13
FrontierMath-Tier-4-2025-07-01-PublicEpoch AI Benchmarking Hub+1.10 · 11.86 · 48 runs

48 runs scored on it, 47 of them ranked, best score first, in the publisher's own unit. A ranked run is a door to its row.

  1. anthropic/claude-fable-5max1122.58
  2. gpt-5.4-2026-03-05high · not in the catalog0.50115.98
  3. gpt-5.4-2026-03-05xhigh · not in the catalog0.50116.23
  4. deepseek/deepseek-r1-0528unstated098.81
  5. google/gemini-2.5-prounstated0103.73
  6. google/gemini-3-flash-previewunstated0108.16
  7. google/gemini-3.1-pro-previewunstated0111.66
  8. google/gemini-3.5-flashhigh0111.12
  9. qwen/qwen3.6-plusunstated0106.49
  10. claude-3-5-sonnet-20240620unstated · not in the catalog081.59
  11. claude-3-5-sonnet-20241022unstated · not in the catalog085.31
  12. claude-3-7-sonnet-20250219-64kunstated · not in the catalog095.18
  13. claude-opus-4-20250514unstated · not in the catalog092.48
  14. claude-opus-4-20250514-27kunstated · not in the catalog097.69
  15. claude-opus-4-6max · not in the catalog0111.69
  16. claude-opus-4-6-32kunstated · not in the catalog0111.03
  17. claude-opus-4-6-64kunstated · not in the catalog0111.92
  18. claude-opus-4-7xhigh · not in the catalog0113.14
  19. claude-sonnet-4-20250514unstated · not in the catalog090.16
  20. claude-sonnet-4-20250514-59kunstated · not in the catalog099.17
  21. claude-sonnet-4-5-20250929unstated · not in the catalog093.21
  22. claude-sonnet-4-6-16kunstated · not in the catalog0109.98
  23. gemini-2.5-pro-preview-06-05unstated · not in the catalog0103.27
  24. gemini-3-pro-previewunstated · not in the catalog0110.74
  25. gpt-4.1-2025-04-14unstated · not in the catalog091.64
  26. gpt-5-2025-08-07high · not in the catalog0108.61
  27. gpt-5-2025-08-07medium · not in the catalog0108.12
  28. gpt-5-mini-2025-08-07high · not in the catalog0104.57
  29. gpt-5-mini-2025-08-07medium · not in the catalog0103.83
  30. gpt-5-nano-2025-08-07high · not in the catalog0100.45
  31. gpt-5-nano-2025-08-07medium · not in the catalog099.03
  32. gpt-5.2-2025-12-11high · not in the catalog0110.74
  33. gpt-5.2-2025-12-11low · not in the catalog0104.89
  34. gpt-5.2-2025-12-11medium · not in the catalog0108.75
  35. grok-3-betaunstated · not in the catalog094.65
  36. grok-3-mini-betahigh · not in the catalog097.03
  37. grok-4-0709unstated · not in the catalog0104.16
  38. moonshotai/kimi-k2-thinkingunstated · not in the catalog0104.82
  39. o3-2025-04-16high · not in the catalog0102.96
  40. o3-mini-2025-01-31high · not in the catalog0102.45
  41. o4-mini-2025-04-16high · not in the catalog0103.35
  42. o4-mini-2025-04-16medium · not in the catalog0101.93
  43. qwen/qwen3-235b-a22b-thinking-2507unstated · not in the catalog0101.29
  44. qwen3.6-max-previewunstated · not in the catalog0106.75
  45. zai-org/glm-4.6unstated · not in the catalog092.21
  46. z-ai/glm-4.5unstated0set aside
  47. z-ai/glm-5unstated099.96
  48. z-ai/glm-5.1unstated0109.27
FrontierMath-Tier-4-v2-PrivateEpoch AI Benchmarking Hub+1.09 · 3.33 · 84 runs

84 runs scored on it, 76 of them ranked, best score first, in the publisher's own unit. A ranked run is a door to its row.

  1. openai/gpt-6.1-solmax1130.00
  2. claude-fable-5-2max · not in the catalog1132.06
  3. gpt-6.2-astramax · not in the catalog1135.84
  4. openai/gpt-6-astrahigh0.98set aside
  5. openai/gpt-6-astramax0.98132.41
  6. openai/gpt-6-astraxhigh0.98set aside
  7. openai/gpt-6-astramedium0.98set aside
  8. gemini-4-neonxhigh · not in the catalog0.98134.54
  9. google/gemini-4-carbonhigh0.95131.68
  10. claude-opus-5-5max · not in the catalog0.95128.09
  11. openai/gpt-6.1-terramax0.93130.85
  12. anthropic/claude-fable-5max0.90122.58
  13. openai/gpt-6-solmax0.90124.00
  14. google/gemini-4-hydrogenxhigh0.88125.83
  15. openai/gpt-6-astralow0.88set aside
  16. claude-fable-5-1max · not in the catalog0.88125.12
  17. openai/gpt-5.6-solmax0.83123.35
  18. openai/gpt-6-astranone0.83set aside
  19. claude-sonnet-5-5max · not in the catalog0.80122.13
  20. gpt-5.6-sol-promaxunstated · not in the catalog0.80set aside
  21. google/gemini-4-argonhigh0.78124.90
  22. openai/gpt-5.5-proxhigh0.78122.66
  23. gdm-ai-co-mathematicianunstated · not in the catalog0.76set aside
  24. anthropic/claude-opus-5max0.73122.24
  25. openai/gpt-5.5xhigh0.72120.29
  26. openai/gpt-5.6-terramax0.71119.24
  27. muse-wonder-1.0max · not in the catalog0.71120.86
  28. kimi-k3.1-pro-togethermax · not in the catalog0.66118.88
  29. openai/gpt-5.6-lunamax0.61114.95
  30. gpt-5.4-pro-2026-03-05xhigh · not in the catalog0.59117.92
  31. openai/gpt-6-lunamax0.56113.99
  32. claude-opus-4-8max · not in the catalog0.56116.89
  33. gpt-5.4-2026-03-05xhigh · not in the catalog0.49116.23
  34. deepseek/deepseek-v4.1-flash-1017max0.46116.25
  35. meta/muse-spark-1.3max0.46115.55
  36. claude-haiku-5-5max · not in the catalog0.46113.88
  37. qwen3.8-maxxhigh · not in the catalog0.46116.39
  38. gpt-5.2-pro-2025-12-11xhigh · not in the catalog0.46116.74
  39. meta/muse-spark-1.3xhigh0.41116.79
  40. moonshotai/kimi-k3max0.39114.75
  41. google/gemini-3.7-flashhigh0.37116.01
  42. qwen/qwen3.7-maxunstated0.34111.06
  43. qwen/qwen3.8-max-0902xhigh0.34113.51
  44. claude-opus-4-7max · not in the catalog0.32113.03
  45. muse-spark-open-816b-a42bxhigh · not in the catalog0.32113.92
  46. x-ai/grok-4.6xhigh0.32114.39
  47. gpt-5.2-2025-12-11xhigh · not in the catalog0.32113.39
  48. anthropic/claude-sonnet-5max0.29112.43
  49. z-ai/glm-5.2max0.29110.33
  50. z-ai/glm-5.3max0.29112.54
  51. deepseek/deepseek-v4-pro-0813max0.27113.60
  52. deepseek/deepseek-v4.1-flashmax0.27116.49
  53. google/gemini-3.1-pro-previewunstated0.27111.66
  54. google/gemini-3.5-flashhigh0.27111.12
  55. mistralai/mistral-large-4-0high0.27110.63
  56. claude-opus-4-6max · not in the catalog0.27111.69
  57. moonshotai/kimi-k2.6unstated0.26110.82
  58. deepseek/deepseek-v4-flash-0731max0.24111.14
  59. x-ai/grok-4.5high0.24111.55
  60. google/gemini-3.6-flashhigh0.22110.95
  61. google/gemini-3.8-flashhigh0.22114.21
  62. gpt-5-2025-08-07high · not in the catalog0.22108.61
  63. gpt-5-pro-2025-10-06high · not in the catalog0.20109.23
  64. google/gemini-3-flash-previewunstated0.17108.16
  65. thinkingmachines/inkling-smallxhigh0.17106.54
  66. grok-4.20-0309-reasoningunstated · not in the catalog0.17108.33
  67. x-ai/grok-4.7xhigh0.17113.32
  68. z-ai/glm-5.3-flashmax0.17108.45
  69. x-ai/grok-4.3high0.15107.39
  70. moonshotai/kimi-k2.7-codeunstated0.12107.73
  71. gpt-5-mini-2025-08-07high · not in the catalog0.12104.57
  72. gpt-5.4-nano-2026-03-17high · not in the catalog0.12106.76
  73. gpt-5.4-mini-2026-03-17xhigh · not in the catalog0.10106.91
  74. thinkingmachines/inklingxhigh0.05107.98
  75. claude-opus-4-5-20251101-32kunstated · not in the catalog0.05104.05
  76. o4-mini-2025-04-16high · not in the catalog0.05103.35
  77. deepseek/deepseek-v4-promax0.02107.02
  78. claude-opus-4-1-20250805-32kunstated · not in the catalog0.02set aside
  79. claude-sonnet-4-5-20250929-32kunstated · not in the catalog0.02101.18
  80. gpt-5-nano-2025-08-07high · not in the catalog0.02100.45
  81. gpt-5.5-instantunstated · not in the catalog0.0299.89
  82. google/gemini-2.5-prounstated0103.73
  83. google/gemini-3.5-flash-litehigh099.97
  84. o3-mini-2025-01-31high · not in the catalog0102.45
SimpleQA VerifiedEpoch AI Benchmarking Hub+1.03 · 0.99 · 106 runs

106 runs scored on it, 102 of them ranked, best score first, in the publisher's own unit. A ranked run is a door to its row.

  1. claude-fable-5-2max · not in the catalog0.94132.06
  2. gpt-6.2-astramax · not in the catalog0.79135.84
  3. google/gemini-4-carbonhigh0.78131.68
  4. google/gemini-4-argonhigh0.76124.90
  5. openai/gpt-6-astramax0.76132.41
  6. gemini-4-neonxhigh · not in the catalog0.75134.54
  7. openai/gpt-6.1-solmax0.74130.00
  8. google/gemini-3.1-pro-previewhigh0.73113.89
  9. claude-opus-5-5max · not in the catalog0.72128.09
  10. google/gemini-4-hydrogenxhigh0.71125.83
  11. claude-fable-5-1max · not in the catalog0.71125.12
  12. anthropic/claude-fable-5xhigh0.71set aside
  13. google/gemini-3.8-flashhigh0.70114.21
  14. openai/gpt-5.6-solmax0.70123.35
  15. google/gemini-3.7-flashhigh0.69116.01
  16. google/gemini-3-flash-previewhigh0.67113.70
  17. google/gemini-3.5-flashhigh0.66111.12
  18. google/gemini-3.6-flashhigh0.66110.95
  19. openai/gpt-5.5xhigh0.63120.29
  20. kimi-k3.1-pro-togethermax · not in the catalog0.62118.88
  21. openai/gpt-6-solmax0.61124.00
  22. meta/muse-spark-1.2xhigh0.60117.04
  23. anthropic/claude-opus-5max0.60122.24
  24. meta/muse-spark-1.1unstated0.58set aside
  25. openai/gpt-6.1-terramax0.57130.85
  26. muse-spark-open-816b-a42bxhigh · not in the catalog0.57113.92
  27. x-ai/grok-4.7xhigh0.56113.32
  28. qwen/qwen3.7-maxunstated0.56111.06
  29. claude-opus-4-8max · not in the catalog0.53116.89
  30. deepseek/deepseek-v4-pro-0813max0.53113.60
  31. qwen3.6-max-previewunstated · not in the catalog0.52106.75
  32. claude-opus-4-7xhigh · not in the catalog0.52113.14
  33. moonshotai/kimi-k3max0.51114.75
  34. gpt-5-2025-08-07high · not in the catalog0.50108.61
  35. o3-2025-04-16high · not in the catalog0.49102.96
  36. x-ai/grok-4.6high0.49114.02
  37. x-ai/grok-4.6xhigh0.49114.39
  38. qwen3-max-2025-09-23unstated · not in the catalog0.49100.03
  39. x-ai/grok-4.5high0.48111.55
  40. gpt-5.1-2025-11-13high · not in the catalog0.48109.94
  41. qwen/qwen3.8-max-0902xhigh0.47113.51
  42. claude-opus-4-6max · not in the catalog0.47111.69
  43. deepseek/deepseek-v4-promax0.47107.02
  44. claude-sonnet-5-5max · not in the catalog0.47122.13
  45. gpt-5.4-pro-2026-03-05xhigh · not in the catalog0.46117.92
  46. qwen3.8-maxxhigh · not in the catalog0.46116.39
  47. claude-opus-4-5-20251101-32kunstated · not in the catalog0.46104.05
  48. gpt-5.4-2026-03-05xhigh · not in the catalog0.45116.23
  49. doubao-seed-2.1-pro-260628high · not in the catalog0.45109.61
  50. qwen/qwen3.6-plusunstated0.44106.49
  51. openai/gpt-5.6-terramax0.43119.24
  52. deepseek/deepseek-v4.1-flashmax0.43116.49
  53. deepseek/deepseek-v4.1-flash-1017max0.42116.25
  54. doubao-seed-evolvinghigh · not in the catalog0.42114.76
  55. openai/gpt-6-lunamax0.41113.99
  56. o1-2024-12-17high · not in the catalog0.4198.27
  57. openai/gpt-5.6-lunamax0.41114.95
  58. z-ai/glm-5.3max0.41112.54
  59. qwen/qwen3-235b-a22b-thinking-2507unstated0.40104.10
  60. thinkingmachines/inklingxhigh0.40107.98
  61. doubao-seed-2.0-pro-260215high · not in the catalog0.39108.12
  62. gpt-5.2-2025-12-11xhigh · not in the catalog0.37113.39
  63. moonshotai/kimi-k2.7-codeunstated0.36107.73
  64. claude-sonnet-4-6high · not in the catalog0.35102.30
  65. moonshotai/kimi-k2.6unstated0.35110.82
  66. moonshotai/kimi-k2.5unstated0.34set aside
  67. gpt-5.2-2025-12-11high · not in the catalog0.34110.74
  68. z-ai/glm-5.2max0.34110.33
  69. z-ai/glm-5.1unstated0.34109.27
  70. anthropic/claude-sonnet-5max0.34112.43
  71. deepseek/deepseek-v4-flash-0731max0.34111.14
  72. x-ai/grok-4.3high0.33107.39
  73. anthropic/claude-sonnet-5xhigh0.33113.50
  74. claude-sonnet-4-6max · not in the catalog0.33101.17
  75. gpt-5.2-2025-12-11low · not in the catalog0.33104.89
  76. gpt-5.2-2025-12-11medium · not in the catalog0.33108.75
  77. z-ai/glm-4.7unstated0.32104.07
  78. doubao-seed-2.0-lite-260428high · not in the catalog0.32106.42
  79. gpt-4.1-2025-04-14unstated · not in the catalog0.3191.64
  80. claude-sonnet-4-5-20250929-59kunstated · not in the catalog0.31101.26
  81. grok-4.20-0309-reasoningunstated · not in the catalog0.30108.33
  82. doubao-seed-2.1-turbo-260628high · not in the catalog0.30108.84
  83. gpt-5.4-mini-2026-03-17high · not in the catalog0.29106.09
  84. openai/gpt-4o-2024-08-06unstated0.2682.76
  85. qwen3.5-plusunstated · not in the catalog0.25105.31
  86. claude-haiku-5-5max · not in the catalog0.24113.88
  87. claude-sonnet-4-5-20250929unstated · not in the catalog0.2493.21
  88. mistral-large-4-0-osshigh · not in the catalog0.22110.78
  89. gpt-5-mini-2025-08-07high · not in the catalog0.22104.57
  90. qwen3.5-flashunstated · not in the catalog0.2099.58
  91. mistralai/mistral-large-4-0high0.20110.63
  92. o4-mini-2025-04-16low · not in the catalog0.20100.61
  93. thinkingmachines/inkling-smallxhigh0.19106.54
  94. o4-mini-2025-04-16high · not in the catalog0.19103.35
  95. seed-1.6unstated · not in the catalog0.1797.70
  96. qwen/qwen3.6-flashunstated0.16100.95
  97. o3-mini-2025-01-31high · not in the catalog0.15102.45
  98. claude-haiku-4-5-20251001unstated · not in the catalog0.1390.99
  99. gpt-4.1-mini-2025-04-14unstated · not in the catalog0.1393.48
  100. claude-3-opus-20240229unstated · not in the catalog0.1378.88
  101. claude-haiku-4-5-20251001-32kunstated · not in the catalog0.1396.01
  102. gpt-5-nano-2025-08-07high · not in the catalog0.12100.45
  103. gpt-5.4-nano-2026-03-17high · not in the catalog0.12106.76
  104. google/gemma-4-31b-itunstated0.10set aside
  105. openai/gpt-4o-mini-2024-07-18unstated0.0880.10
  106. gpt-4.1-nano-2025-04-14unstated · not in the catalog0.0686.22
FrontierMath-2025-02-28-PrivateEpoch AI Benchmarking Hub+1.00 · 2.05 · 101 runs

101 runs scored on it, 95 of them ranked, best score first, in the publisher's own unit. A ranked run is a door to its row.

  1. gpt-5.5-pro-pre-releasehigh · not in the catalog0.52set aside
  2. gpt-5.5-pre-releasexhigh · not in the catalog0.52116.86
  3. gpt-5.5-pro-pre-releasexhigh · not in the catalog0.51117.38
  4. gpt-5.4-pro-2026-03-05xhigh · not in the catalog0.50117.92
  5. gpt-5.4-2026-03-05xhigh · not in the catalog0.48116.23
  6. claude-opus-4-8max · not in the catalog0.47116.89
  7. claude-opus-4-7xhigh · not in the catalog0.44113.14
  8. claude-opus-4-6max · not in the catalog0.41111.69
  9. gpt-5.2-2025-12-11xhigh · not in the catalog0.41113.39
  10. gpt-5.2-2025-12-11high · not in the catalog0.40110.74
  11. claude-opus-4-6-32kunstated · not in the catalog0.40111.03
  12. claude-opus-4-6-64kunstated · not in the catalog0.40111.92
  13. muse-sparkunstated · not in the catalog0.39110.41
  14. google/gemini-3.5-flashhigh0.39111.12
  15. moonshotai/kimi-k2.6unstated0.39110.82
  16. claude-opus-4-6unstated · not in the catalog0.38110.08
  17. gemini-3-pro-previewunstated · not in the catalog0.38110.74
  18. google/gemini-3.1-pro-previewunstated0.37111.66
  19. gpt-5.2-2025-12-11medium · not in the catalog0.37108.75
  20. google/gemini-3-flash-previewunstated0.36108.16
  21. z-ai/glm-5.1unstated0.33109.27
  22. gpt-5-2025-08-07high · not in the catalog0.32108.61
  23. claude-sonnet-4-6-16kunstated · not in the catalog0.32109.98
  24. gpt-5.1-2025-11-13high · not in the catalog0.31109.94
  25. gemini-2.5-deep-think-2025-08-01-webappunstated · not in the catalog0.29set aside
  26. gpt-5.4-mini-2026-03-17high · not in the catalog0.28106.09
  27. fireworks/kimi-k2p5unstated · not in the catalog0.28107.32
  28. gpt-5-2025-08-07medium · not in the catalog0.27108.12
  29. gpt-5-mini-2025-08-07high · not in the catalog0.27104.57
  30. gpt-5.1-2025-11-13medium · not in the catalog0.27105.41
  31. gpt-5.2-2025-12-11low · not in the catalog0.27104.89
  32. qwen/qwen3.6-plusunstated0.26106.49
  33. gpt-5.4-nano-2026-03-17high · not in the catalog0.26106.76
  34. o4-mini-2025-04-16high · not in the catalog0.25103.35
  35. qwen3.6-max-previewunstated · not in the catalog0.23106.75
  36. fireworks/deepseek-v3p2unstated · not in the catalog0.22set aside
  37. moonshotai/kimi-k2-thinkingunstated · not in the catalog0.21104.82
  38. qwen3.5-plusunstated · not in the catalog0.21105.31
  39. claude-opus-4-5-20251101unstated · not in the catalog0.2199.92
  40. claude-opus-4-5-20251101-32kunstated · not in the catalog0.21104.05
  41. claude-opus-4-5-20251101-16kunstated · not in the catalog0.20104.70
  42. gpt-5-mini-2025-08-07medium · not in the catalog0.20103.83
  43. grok-4-0709unstated · not in the catalog0.20104.16
  44. o4-mini-2025-04-16medium · not in the catalog0.19101.93
  45. o3-2025-04-16high · not in the catalog0.19102.96
  46. gpt-5.1-2025-11-13low · not in the catalog0.17100.64
  47. o3-2025-04-16medium · not in the catalog0.17101.11
  48. z-ai/glm-5unstated0.1699.96
  49. claude-sonnet-4-5-20250929-32kunstated · not in the catalog0.15101.18
  50. google/gemini-2.5-prounstated0.14103.73
  51. claude-sonnet-4-5-20250929-59kunstated · not in the catalog0.13101.26
  52. o3-mini-2025-01-31high · not in the catalog0.12102.45
  53. o4-mini-2025-04-16low · not in the catalog0.11100.61
  54. qwen/qwen3.6-flashunstated0.10100.95
  55. gemini-2.5-pro-preview-06-05unstated · not in the catalog0.10103.27
  56. o3-2025-04-16low · not in the catalog0.1099.37
  57. claude-sonnet-4-5-20250929unstated · not in the catalog0.0993.21
  58. o1-2024-12-17high · not in the catalog0.0998.27
  59. qwen/qwen3-235b-a22b-thinking-2507unstated · not in the catalog0.08101.29
  60. gpt-5-nano-2025-08-07high · not in the catalog0.08100.45
  61. o3-mini-2025-01-31medium · not in the catalog0.0897.94
  62. claude-opus-4-1-20250805-27kunstated · not in the catalog0.0797.29
  63. gpt-5-nano-2025-08-07medium · not in the catalog0.0799.03
  64. qwen3.5-flashunstated · not in the catalog0.0699.58
  65. claude-haiku-4-5-20251001-32kunstated · not in the catalog0.0696.01
  66. claude-opus-4-1-20250805unstated · not in the catalog0.0693.81
  67. grok-3-mini-betahigh · not in the catalog0.0697.03
  68. gpt-4.1-2025-04-14unstated · not in the catalog0.0691.64
  69. google/gemini-2.5-flashunstated0.05set aside
  70. claude-opus-4-20250514unstated · not in the catalog0.0492.48
  71. gpt-4.1-mini-2025-04-14unstated · not in the catalog0.0493.48
  72. claude-3-7-sonnet-20250219-16kunstated · not in the catalog0.0493.20
  73. claude-haiku-4-5-20251001unstated · not in the catalog0.0490.99
  74. claude-opus-4-20250514-27kunstated · not in the catalog0.0497.69
  75. claude-sonnet-4-20250514unstated · not in the catalog0.0490.16
  76. zai-org/glm-4.6unstated · not in the catalog0.0492.21
  77. grok-3-betaunstated · not in the catalog0.0494.65
  78. claude-3-7-sonnet-20250219-32kunstated · not in the catalog0.0394.40
  79. claude-3-7-sonnet-20250219unstated · not in the catalog0.0387.22
  80. claude-3-7-sonnet-20250219-64kunstated · not in the catalog0.0395.18
  81. grok-3-mini-betalow · not in the catalog0.0394.71
  82. zai-org/glm-4.7unstated · not in the catalog0.02set aside
  83. gpt-5.1-2025-11-13none · not in the catalog0.0291.90
  84. claude-3-5-sonnet-20241022unstated · not in the catalog0.0285.31
  85. deepseek-v3unstated · not in the catalog0.0284.96
  86. gemini-2.0-flash-001unstated · not in the catalog0.0289.75
  87. o1-mini-2024-09-12medium · not in the catalog0.0291.51
  88. qwen-plus-2025-04-28unstated · not in the catalog0.02set aside
  89. o1-mini-2024-09-12high · not in the catalog0.0192.53
  90. claude-3-5-sonnet-20240620unstated · not in the catalog0.0181.59
  91. gpt-4.1-nano-2025-04-14unstated · not in the catalog0.0186.22
  92. qwen-max-2025-01-25unstated · not in the catalog0.0185.11
  93. grok-2-1212unstated · not in the catalog0.0183.89
  94. llama-4-maverick-17b-128e-instruct-fp8unstated · not in the catalog0.0187.21
  95. mistral-medium-2505unstated · not in the catalog0.0089.41
  96. openai/gpt-4o-2024-08-06unstated0.0082.76
  97. openai/gpt-4o-2024-11-20unstated0.0080.37
  98. claude-3-5-haiku-20241022unstated · not in the catalog0.0080.42
  99. mistral-large-2411unstated · not in the catalog0.0081.24
  100. gemini-1.5-flash-002unstated · not in the catalog083.86
  101. llama-4-scout-17b-16e-instructunstated · not in the catalog082.99
pythonLiveBench+0.60 · 0.52 · 71 runs

71 runs scored on it, 71 of them ranked, best score first, in the publisher's own unit. A ranked run is a door to its row.

  1. deepseek/deepseek-v4.1-flashmax90116.49
  2. anthropic/claude-opus-5max75122.24
  3. deepseek/deepseek-v4-flash-vision-expunstated75116.36
  4. qwen/qwen3.8-27bunstated75112.72
  5. claude-fable-5-1max · not in the catalog70125.12
  6. claude-opus-5-5max · not in the catalog70128.09
  7. claude-opus-5-5xhigh · not in the catalog70125.14
  8. qwen3.8-flash-nextunstated · not in the catalog70113.12
  9. smaug-miniunstated · not in the catalog70114.73
  10. anthropic/claude-fable-5max65122.58
  11. moonshotai/kimi-k3unstated65116.54
  12. openai/gpt-6-astramax65132.41
  13. smaug-flashunstated · not in the catalog65116.63
  14. anthropic/claude-sonnet-5xhigh60113.50
  15. google/gemini-3.7-flashhigh60116.01
  16. openai/gpt-5.2-codexunstated60110.02
  17. openai/gpt-6.1-solmax60130.00
  18. openai/gpt-6.1-solxhigh60124.64
  19. claude-haiku-5-5max · not in the catalog60113.88
  20. mistral-large-4high · not in the catalog60109.81
  21. muse-wonder-1.0max · not in the catalog60120.86
  22. ox-alphamax · not in the catalog60106.05
  23. qwen3.8-maxunstated · not in the catalog60118.08
  24. smaug-agenticunstated · not in the catalog60116.30
  25. x-ai/grok-4.5unstated60114.74
  26. z-ai/glm-5.3unstated60112.92
  27. z-ai/glm-5.3-flashunstated60108.42
  28. meta/muse-spark-1.1xhigh55114.21
  29. meta/muse-spark-1.3xhigh55116.79
  30. openai/gpt-5.4-minixhigh55104.22
  31. openai/gpt-5.5xhigh55120.29
  32. openai/gpt-5.6-solmax55123.35
  33. openai/gpt-6-solmax55124.00
  34. claude-haiku-5-5xhigh · not in the catalog55112.88
  35. gpt-5.2-2025-12-11high · not in the catalog55110.74
  36. kimi-k2.6-thinkingunstated · not in the catalog55107.26
  37. x-ai/grok-4.6unstated55117.62
  38. x-ai/grok-4.7xhigh55113.32
  39. z-ai/glm-5.2unstated55109.40
  40. deepseek/deepseek-v4-flash-0731unstated50113.47
  41. deepseek/deepseek-v4-prounstated50111.64
  42. deepseek/deepseek-v4-pro-0813unstated50118.60
  43. google/gemini-3.1-pro-previewhigh50113.89
  44. google/gemini-3.5-flashhigh50111.12
  45. google/gemini-3.5-flash-litehigh5099.97
  46. google/gemini-3.8-flashhigh50114.21
  47. meta/muse-spark-1.2xhigh50117.04
  48. moonshotai/kimi-k2.7-codeunstated50107.73
  49. openai/gpt-5.4xhigh50119.02
  50. openai/gpt-5.4-nanoxhigh50110.30
  51. openai/gpt-5.6-terramax50119.24
  52. openai/gpt-6-lunamax50113.99
  53. thinkingmachines/inklingxhigh50107.98
  54. claude-opus-4-6-thinking-autohigh · not in the catalog50113.04
  55. claude-opus-4-8max · not in the catalog50116.89
  56. claude-sonnet-4-6-thinking-automedium · not in the catalog50114.06
  57. nvidia/nemotron-3-ultra-550b-a55bunstated45105.72
  58. openai/gpt-5.6-lunamax45114.95
  59. qwen/qwen3.6-plusunstated45106.49
  60. qwen/qwen3.7-maxunstated45111.06
  61. claude-opus-4-7xhigh · not in the catalog45113.14
  62. x-ai/grok-build-0.1unstated45106.25
  63. google/gemini-3.6-flashhigh40110.95
  64. qwen/qwen3.6-27bunstated40103.72
  65. claude-opus-4-5-20251101-thinking-64khigh · not in the catalog40110.65
  66. deepseek/deepseek-v4-flashunstated35102.96
  67. minimax/minimax-m3unstated35104.58
  68. claude-sonnet-5-5max · not in the catalog35122.13
  69. claude-sonnet-5-5xhigh · not in the catalog35119.88
  70. nemotron-3.5-lightning-30b-a3bunstated · not in the catalog3587.31
  71. x-ai/grok-4.3unstated15103.07
FrontierMath-Tiers-1-3-v2-PrivateEpoch AI Benchmarking Hub+0.58 · 2.02 · 128 runs

128 runs scored on it, 121 of them ranked, best score first, in the publisher's own unit. A ranked run is a door to its row.

  1. claude-fable-5-2max · not in the catalog0.95132.06
  2. openai/gpt-6-astramax0.94132.41
  3. openai/gpt-6.1-solmax0.94130.00
  4. gpt-6.2-astramax · not in the catalog0.93135.84
  5. claude-opus-5-5max · not in the catalog0.91128.09
  6. gemini-4-neonxhigh · not in the catalog0.91134.54
  7. openai/gpt-6.1-terramax0.91130.85
  8. google/gemini-4-carbonhigh0.91131.68
  9. claude-fable-5-1max · not in the catalog0.90125.12
  10. openai/gpt-6-solmax0.90124.00
  11. openai/gpt-5.6-solmax0.89123.35
  12. claude-sonnet-5-5max · not in the catalog0.89122.13
  13. google/gemini-4-hydrogenxhigh0.88125.83
  14. openai/gpt-5.5-proxhigh0.88122.66
  15. anthropic/claude-fable-5max0.87122.58
  16. google/gemini-4-argonhigh0.86124.90
  17. openai/gpt-5.6-terramax0.86119.24
  18. anthropic/claude-opus-5max0.86122.24
  19. openai/gpt-5.5xhigh0.85120.29
  20. gpt-5.4-pro-2026-03-05xhigh · not in the catalog0.82117.92
  21. openai/gpt-5.6-lunamax0.82114.95
  22. muse-wonder-1.0max · not in the catalog0.82120.86
  23. claude-opus-4-8max · not in the catalog0.80116.89
  24. openai/gpt-6-lunamax0.79113.99
  25. gpt-5.4-2026-03-05xhigh · not in the catalog0.79116.23
  26. kimi-k3.1-pro-togethermax · not in the catalog0.78118.88
  27. claude-haiku-5-5max · not in the catalog0.75113.88
  28. qwen3.8-maxxhigh · not in the catalog0.75116.39
  29. meta/muse-spark-1.3xhigh0.74116.79
  30. meta/muse-spark-1.3max0.74115.55
  31. gpt-5.2-pro-2025-12-11xhigh · not in the catalog0.74116.74
  32. moonshotai/kimi-k3max0.72114.75
  33. google/gemini-3.7-flashhigh0.72116.01
  34. deepseek/deepseek-v4.1-flash-1017max0.71116.25
  35. claude-opus-4-7max · not in the catalog0.70113.03
  36. muse-spark-open-816b-a42bxhigh · not in the catalog0.70113.92
  37. z-ai/glm-5.3max0.69112.54
  38. google/gemini-3.8-flashhigh0.68114.21
  39. gpt-5.2-2025-12-11xhigh · not in the catalog0.67113.39
  40. deepseek/deepseek-v4.1-flashmax0.67116.49
  41. claude-opus-4-6max · not in the catalog0.66111.69
  42. x-ai/grok-4.6xhigh0.66114.39
  43. anthropic/claude-sonnet-5max0.66112.43
  44. qwen/qwen3.8-max-0902xhigh0.66113.51
  45. deepseek/deepseek-v4-pro-0813max0.65113.60
  46. qwen/qwen3.7-maxunstated0.65111.06
  47. google/gemini-3.5-flashhigh0.63111.12
  48. google/gemini-3.1-pro-previewunstated0.60111.66
  49. z-ai/glm-5.2max0.59110.33
  50. google/gemini-3.6-flashhigh0.59110.95
  51. mistralai/mistral-large-4-0high0.59110.63
  52. deepseek/deepseek-v4-flash-0731max0.58111.14
  53. moonshotai/kimi-k2.6unstated0.57110.82
  54. x-ai/grok-4.5high0.57111.55
  55. gpt-5-pro-2025-10-06high · not in the catalog0.56109.23
  56. z-ai/glm-5.3-flashmax0.56108.45
  57. gpt-5-2025-08-07high · not in the catalog0.55108.61
  58. z-ai/glm-5.2low0.55105.42
  59. moonshotai/kimi-k2.7-codeunstated0.54107.73
  60. x-ai/grok-4.7xhigh0.53113.32
  61. google/gemini-3-flash-previewunstated0.51108.16
  62. gpt-5.4-mini-2026-03-17xhigh · not in the catalog0.51106.91
  63. gpt-5-mini-2025-08-07high · not in the catalog0.47104.57
  64. thinkingmachines/inkling-smallxhigh0.46106.54
  65. deepseek/deepseek-v4-promax0.45107.02
  66. gpt-5.4-nano-2026-03-17high · not in the catalog0.45106.76
  67. grok-4.20-0309-reasoningunstated · not in the catalog0.45108.33
  68. x-ai/grok-4.3high0.43107.39
  69. z-ai/glm-5.2none0.4296.22
  70. openai/gpt-5.6-lunalow0.41101.92
  71. openai/gpt-5.6-lunanone0.4095.93
  72. qwen/qwen3.6-plusunstated0.38106.49
  73. gpt-5-2025-08-07low · not in the catalog0.37105.22
  74. z-ai/glm-5.1unstated0.37109.27
  75. o4-mini-2025-04-16high · not in the catalog0.36103.35
  76. qwen/qwen3.6-27bunstated0.35103.72
  77. qwen/qwen3.7-plusnone0.34103.17
  78. claude-opus-4-5-20251101-32kunstated · not in the catalog0.34104.05
  79. qwen/qwen3.6-27bnone0.34100.32
  80. thinkingmachines/inklingxhigh0.33107.98
  81. o3-2025-04-16high · not in the catalog0.33102.96
  82. qwen/qwen3.6-plusnone0.32set aside
  83. qwen/qwen3.5-397b-a17bnone0.31103.55
  84. o3-2025-04-16medium · not in the catalog0.30101.11
  85. qwen/qwen3.5-397b-a17bunstated0.29104.40
  86. o4-mini-2025-04-16medium · not in the catalog0.29101.93
  87. google/gemini-3.1-flash-litehigh0.28102.13
  88. gpt-5.5-instantunstated · not in the catalog0.2699.89
  89. google/gemini-3.5-flash-litehigh0.2699.97
  90. z-ai/glm-5.1none0.25set aside
  91. google/gemini-2.5-prounstated0.25103.73
  92. gpt-5.4-mini-2026-03-17low · not in the catalog0.25set aside
  93. claude-sonnet-4-5-20250929-32kunstated · not in the catalog0.24101.18
  94. google/gemini-3.1-flash-litelow0.2294.94
  95. qwen/qwen3.6-flashnone0.22set aside
  96. google/gemini-3.1-flash-liteminimal0.2193.68
  97. qwen/qwen3.6-35b-a3bnone0.20100.22
  98. gpt-5.4-nano-2026-03-17low · not in the catalog0.2098.40
  99. gpt-5-nano-2025-08-07high · not in the catalog0.20100.45
  100. qwen/qwen3.7-flashunstated0.19102.16
  101. qwen/qwen3.7-flashnone0.19100.54
  102. o3-2025-04-16low · not in the catalog0.1999.37
  103. qwen3-max-2025-09-23unstated · not in the catalog0.19100.03
  104. o3-mini-2025-01-31high · not in the catalog0.19102.45
  105. gpt-5-2025-08-07minimal · not in the catalog0.1895.14
  106. gpt-5-mini-2025-08-07low · not in the catalog0.18set aside
  107. qwen3.5-flashnone · not in the catalog0.18set aside
  108. qwen/qwen3.6-35b-a3bunstated0.18102.04
  109. qwen/qwen3.6-flashunstated0.17100.95
  110. gpt-5.4-mini-2026-03-17none · not in the catalog0.1790.48
  111. o4-mini-2025-04-16low · not in the catalog0.16100.61
  112. o1-2024-12-17high · not in the catalog0.1598.27
  113. claude-opus-4-1-20250805-32kunstated · not in the catalog0.13set aside
  114. o3-mini-2025-01-31medium · not in the catalog0.1197.94
  115. o1-2024-12-17medium · not in the catalog0.1097.81
  116. qwen3.5-flashunstated · not in the catalog0.0999.58
  117. o1-2024-12-17low · not in the catalog0.0894.71
  118. gpt-4.1-mini-2025-04-14unstated · not in the catalog0.0793.48
  119. gpt-4.1-2025-04-14unstated · not in the catalog0.0691.64
  120. gpt-5-mini-2025-08-07minimal · not in the catalog0.0693.86
  121. gpt-5-nano-2025-08-07low · not in the catalog0.0692.74
  122. gpt-5.4-nano-2026-03-17none · not in the catalog0.0591.33
  123. o3-mini-2025-01-31low · not in the catalog0.0491.91
  124. gpt-5-nano-2025-08-07minimal · not in the catalog0.0288.08
  125. openai/gpt-4o-mini-2024-07-18unstated0.0180.10
  126. gpt-4-turbo-2024-04-09unstated · not in the catalog0.0180.07
  127. openai/gpt-4o-2024-08-06unstated0.0082.76
  128. gpt-3.5-turbo-0125unstated · not in the catalog069.92
FrontierMath-2025-02-28-PublicEpoch AI Benchmarking Hub+0.43 · 4.76 · 87 runs

87 runs scored on it, 85 of them ranked, best score first, in the publisher's own unit. A ranked run is a door to its row.

  1. anthropic/claude-fable-5max1122.58
  2. moonshotai/kimi-k2.6unstated0.90110.82
  3. claude-opus-4-6max · not in the catalog0.90111.69
  4. claude-opus-4-6-64kunstated · not in the catalog0.90111.92
  5. claude-opus-4-7xhigh · not in the catalog0.90113.14
  6. google/gemini-3.1-pro-previewunstated0.89111.66
  7. google/gemini-3.5-flashhigh0.80111.12
  8. claude-opus-4-6-32kunstated · not in the catalog0.80111.03
  9. claude-sonnet-4-6-16kunstated · not in the catalog0.80109.98
  10. gemini-3-pro-previewunstated · not in the catalog0.80110.74
  11. gpt-5.4-2026-03-05high · not in the catalog0.80115.98
  12. z-ai/glm-5.1unstated0.80109.27
  13. gpt-5-2025-08-07medium · not in the catalog0.70108.12
  14. google/gemini-3-flash-previewunstated0.60108.16
  15. gpt-5-2025-08-07high · not in the catalog0.60108.61
  16. gpt-5-pro-2025-10-06high · not in the catalog0.60109.23
  17. gpt-5.2-2025-12-11high · not in the catalog0.60110.74
  18. gpt-5.2-2025-12-11medium · not in the catalog0.60108.75
  19. gpt-5.4-nano-2026-03-17high · not in the catalog0.60106.76
  20. qwen/qwen3.6-plusunstated0.50106.49
  21. gpt-5.4-mini-2026-03-17high · not in the catalog0.50106.09
  22. qwen3.5-plusunstated · not in the catalog0.50105.31
  23. qwen3.6-max-previewunstated · not in the catalog0.50106.75
  24. google/gemini-2.5-prounstated0.40103.73
  25. claude-opus-4-5-20251101-16kunstated · not in the catalog0.40104.70
  26. gpt-5-mini-2025-08-07medium · not in the catalog0.40103.83
  27. gpt-5.2-2025-12-11low · not in the catalog0.40104.89
  28. moonshotai/kimi-k2-thinkingunstated · not in the catalog0.40104.82
  29. o3-mini-2025-01-31high · not in the catalog0.40102.45
  30. gemini-2.5-pro-preview-06-05unstated · not in the catalog0.30103.27
  31. gpt-5-mini-2025-08-07high · not in the catalog0.30104.57
  32. o4-mini-2025-04-16high · not in the catalog0.30103.35
  33. o4-mini-2025-04-16low · not in the catalog0.30100.61
  34. qwen/qwen3.6-flashunstated0.20100.95
  35. claude-opus-4-5-20251101unstated · not in the catalog0.2099.92
  36. gpt-5-nano-2025-08-07high · not in the catalog0.20100.45
  37. kimi-k2-thinking-turbounstated · not in the catalog0.20102.46
  38. o4-mini-2025-04-16medium · not in the catalog0.20101.93
  39. qwen/qwen3-235b-a22b-thinking-2507unstated · not in the catalog0.20101.29
  40. o3-mini-2025-01-31medium · not in the catalog0.1197.94
  41. gpt-4.1-mini-2025-04-14unstated · not in the catalog0.1093.48
  42. gpt-5-nano-2025-08-07medium · not in the catalog0.1099.03
  43. o3-2025-04-16high · not in the catalog0.10102.96
  44. o3-2025-04-16low · not in the catalog0.1099.37
  45. qwen3.5-flashunstated · not in the catalog0.1099.58
  46. z-ai/glm-5unstated0.0299.96
  47. openai/gpt-4o-2024-08-06unstated082.76
  48. openai/gpt-4o-2024-11-20unstated080.37
  49. claude-3-5-haiku-20241022unstated · not in the catalog080.42
  50. claude-3-5-sonnet-20240620unstated · not in the catalog081.59
  51. claude-3-5-sonnet-20241022unstated · not in the catalog085.31
  52. claude-3-7-sonnet-20250219unstated · not in the catalog087.22
  53. claude-3-7-sonnet-20250219-16kunstated · not in the catalog093.20
  54. claude-3-7-sonnet-20250219-32kunstated · not in the catalog094.40
  55. claude-3-7-sonnet-20250219-64kunstated · not in the catalog095.18
  56. claude-haiku-4-5-20251001-32kunstated · not in the catalog096.01
  57. claude-opus-4-1-20250805unstated · not in the catalog093.81
  58. claude-opus-4-1-20250805-16kunstated · not in the catalog096.39
  59. claude-opus-4-1-20250805-27kunstated · not in the catalog097.29
  60. claude-opus-4-20250514unstated · not in the catalog092.48
  61. claude-sonnet-4-20250514unstated · not in the catalog090.16
  62. claude-sonnet-4-5-20250929unstated · not in the catalog093.21
  63. deepseek-v3unstated · not in the catalog084.96
  64. deepseek-v3-0324unstated · not in the catalog090.12
  65. gemini-1.5-flash-002unstated · not in the catalog083.86
  66. gemini-2.0-flash-001unstated · not in the catalog089.75
  67. gemini-2.0-pro-exp-02-05unstated · not in the catalog090.84
  68. gpt-4.1-2025-04-14unstated · not in the catalog091.64
  69. gpt-4.1-nano-2025-04-14unstated · not in the catalog086.22
  70. grok-2-1212unstated · not in the catalog083.89
  71. grok-3-betaunstated · not in the catalog094.65
  72. grok-3-mini-betahigh · not in the catalog097.03
  73. grok-3-mini-betalow · not in the catalog094.71
  74. llama-4-maverick-17b-128e-instruct-fp8unstated · not in the catalog087.21
  75. llama-4-scout-17b-16e-instructunstated · not in the catalog082.99
  76. magistral-small-2506unstated · not in the catalog088.63
  77. mistral-large-2411unstated · not in the catalog081.24
  78. mistral-medium-2505unstated · not in the catalog089.41
  79. o1-2024-12-17high · not in the catalog098.27
  80. o1-mini-2024-09-12high · not in the catalog092.53
  81. o1-mini-2024-09-12medium · not in the catalog091.51
  82. o3-2025-04-16medium · not in the catalog0101.11
  83. qwen-max-2025-01-25unstated · not in the catalog085.11
  84. qwen-plus-2025-04-28unstated · not in the catalog0set aside
  85. qwen3-235b-a22bunstated · not in the catalog087.56
  86. zai-org/glm-4.6unstated · not in the catalog092.21
  87. z-ai/glm-4.5unstated0set aside
plot_unscramblingLiveBench+0.42 · 0.89 · 71 runs

71 runs scored on it, 71 of them ranked, best score first, in the publisher's own unit. A ranked run is a door to its row.

  1. openai/gpt-6-astramax86.29132.41
  2. openai/gpt-6.1-solmax84.38130.00
  3. openai/gpt-6.1-solxhigh81.94124.64
  4. openai/gpt-5.6-solmax79.05123.35
  5. anthropic/claude-fable-5max78.72122.58
  6. openai/gpt-6-solmax77.90124.00
  7. claude-opus-5-5max · not in the catalog77.48128.09
  8. claude-opus-5-5xhigh · not in the catalog77.16125.14
  9. claude-fable-5-1max · not in the catalog75.17125.12
  10. muse-wonder-1.0max · not in the catalog74.80120.86
  11. anthropic/claude-opus-5max74.73122.24
  12. google/gemini-3.1-pro-previewhigh74.13113.89
  13. openai/gpt-5.5xhigh74.09120.29
  14. google/gemini-3.8-flashhigh73.38114.21
  15. moonshotai/kimi-k3unstated72.58116.54
  16. x-ai/grok-4.7xhigh72.42113.32
  17. smaug-agenticunstated · not in the catalog71.07116.30
  18. openai/gpt-5.6-terramax69.68119.24
  19. meta/muse-spark-1.3xhigh68.38116.79
  20. claude-sonnet-5-5xhigh · not in the catalog67.79119.88
  21. google/gemini-3.5-flashhigh67.75111.12
  22. x-ai/grok-4.6unstated67.09117.62
  23. claude-opus-4-6-thinking-autohigh · not in the catalog66.48113.04
  24. claude-opus-4-5-20251101-thinking-64khigh · not in the catalog66.45110.65
  25. x-ai/grok-4.5unstated66.39114.74
  26. google/gemini-3.7-flashhigh66.36116.01
  27. openai/gpt-5.4xhigh65.90119.02
  28. deepseek/deepseek-v4-pro-0813unstated64.22118.60
  29. google/gemini-3.6-flashhigh63.69110.95
  30. meta/muse-spark-1.1xhigh63.03114.21
  31. meta/muse-spark-1.2xhigh61.72117.04
  32. claude-opus-4-8max · not in the catalog61.65116.89
  33. deepseek/deepseek-v4.1-flashmax61.57116.49
  34. claude-opus-4-7xhigh · not in the catalog61.41113.14
  35. z-ai/glm-5.2unstated60.73109.40
  36. smaug-flashunstated · not in the catalog60.31116.63
  37. z-ai/glm-5.3-flashunstated60.26108.42
  38. z-ai/glm-5.3unstated60.24112.92
  39. qwen/qwen3.7-maxunstated58.72111.06
  40. qwen3.8-maxunstated · not in the catalog58.56118.08
  41. gpt-5.2-2025-12-11high · not in the catalog58.43110.74
  42. deepseek/deepseek-v4-flash-0731unstated58.19113.47
  43. kimi-k2.6-thinkingunstated · not in the catalog58.09107.26
  44. deepseek/deepseek-v4-flash-vision-expunstated57.75116.36
  45. openai/gpt-6-lunamax57.48113.99
  46. claude-sonnet-4-6-thinking-automedium · not in the catalog56.98114.06
  47. qwen/qwen3.8-27bunstated56.54112.72
  48. deepseek/deepseek-v4-prounstated56.39111.64
  49. openai/gpt-5.2-codexunstated56.03110.02
  50. qwen3.8-flash-nextunstated · not in the catalog55.76113.12
  51. moonshotai/kimi-k2.7-codeunstated55.72107.73
  52. smaug-miniunstated · not in the catalog55.33114.73
  53. anthropic/claude-sonnet-5xhigh53.41113.50
  54. x-ai/grok-build-0.1unstated53.38106.25
  55. thinkingmachines/inklingxhigh53.21107.98
  56. ox-alphamax · not in the catalog53.08106.05
  57. qwen/qwen3.6-plusunstated52.47106.49
  58. openai/gpt-5.6-lunamax51.20114.95
  59. minimax/minimax-m3unstated50.17104.58
  60. google/gemini-3.5-flash-litehigh49.4699.97
  61. x-ai/grok-4.3unstated48.74103.07
  62. claude-sonnet-5-5max · not in the catalog48.62122.13
  63. nvidia/nemotron-3-ultra-550b-a55bunstated47.77105.72
  64. deepseek/deepseek-v4-flashunstated46.87102.96
  65. openai/gpt-5.4-minixhigh43.88104.22
  66. qwen/qwen3.6-27bunstated42.75103.72
  67. claude-haiku-5-5xhigh · not in the catalog42.72112.88
  68. mistral-large-4high · not in the catalog40.93109.81
  69. openai/gpt-5.4-nanoxhigh39.13110.30
  70. claude-haiku-5-5max · not in the catalog27.88113.88
  71. nemotron-3.5-lightning-30b-a3bunstated · not in the catalog22.8787.31
integrals_with_gameLiveBench+0.28 · 2.15 · 71 runs

71 runs scored on it, 71 of them ranked, best score first, in the publisher's own unit. A ranked run is a door to its row.

  1. openai/gpt-5.6-solmax100123.35
  2. openai/gpt-6-astramax100132.41
  3. openai/gpt-6.1-solmax100130.00
  4. claude-opus-5-5max · not in the catalog100128.09
  5. claude-sonnet-5-5xhigh · not in the catalog100119.88
  6. openai/gpt-5.5xhigh99120.29
  7. openai/gpt-6-solmax99124.00
  8. openai/gpt-6.1-solxhigh99124.64
  9. claude-fable-5-1max · not in the catalog99125.12
  10. claude-opus-5-5xhigh · not in the catalog99125.14
  11. muse-wonder-1.0max · not in the catalog98120.86
  12. anthropic/claude-fable-5max97122.58
  13. anthropic/claude-opus-5max97122.24
  14. claude-sonnet-5-5max · not in the catalog97122.13
  15. meta/muse-spark-1.3xhigh96116.79
  16. x-ai/grok-4.7xhigh96113.32
  17. openai/gpt-5.6-terramax95119.24
  18. deepseek/deepseek-v4-pro-0813unstated94118.60
  19. openai/gpt-5.4xhigh93119.02
  20. gpt-5.2-2025-12-11high · not in the catalog92110.74
  21. meta/muse-spark-1.2xhigh91117.04
  22. deepseek/deepseek-v4.1-flashmax90116.49
  23. claude-sonnet-4-6-thinking-automedium · not in the catalog90114.06
  24. mistral-large-4high · not in the catalog90109.81
  25. claude-haiku-5-5xhigh · not in the catalog89112.88
  26. claude-opus-4-8max · not in the catalog89116.89
  27. anthropic/claude-sonnet-5xhigh88113.50
  28. google/gemini-3.7-flashhigh88116.01
  29. x-ai/grok-4.6unstated85117.62
  30. claude-opus-4-7xhigh · not in the catalog84113.14
  31. meta/muse-spark-1.1xhigh83114.21
  32. openai/gpt-5.4-nanoxhigh82.83110.30
  33. qwen3.8-maxunstated · not in the catalog81118.08
  34. google/gemini-3.8-flashhigh80114.21
  35. nvidia/nemotron-3-ultra-550b-a55bunstated80105.72
  36. deepseek/deepseek-v4-prounstated78111.64
  37. google/gemini-3.1-pro-previewhigh78113.89
  38. claude-opus-4-5-20251101-thinking-64khigh · not in the catalog78110.65
  39. x-ai/grok-4.5unstated78114.74
  40. deepseek/deepseek-v4-flash-vision-expunstated76116.36
  41. smaug-flashunstated · not in the catalog76116.63
  42. smaug-miniunstated · not in the catalog76114.73
  43. z-ai/glm-5.2unstated76109.40
  44. openai/gpt-5.2-codexunstated75110.02
  45. openai/gpt-6-lunamax74113.99
  46. claude-opus-4-6-thinking-autohigh · not in the catalog73113.04
  47. thinkingmachines/inklingxhigh72107.98
  48. openai/gpt-5.6-lunamax70114.95
  49. z-ai/glm-5.3unstated69112.92
  50. google/gemini-3.5-flashhigh68111.12
  51. claude-haiku-5-5max · not in the catalog67113.88
  52. x-ai/grok-build-0.1unstated66106.25
  53. deepseek/deepseek-v4-flash-0731unstated65113.47
  54. qwen/qwen3.8-27bunstated65112.72
  55. google/gemini-3.6-flashhigh63110.95
  56. x-ai/grok-4.3unstated63103.07
  57. qwen/qwen3.6-plusunstated62106.49
  58. qwen/qwen3.7-maxunstated59111.06
  59. qwen3.8-flash-nextunstated · not in the catalog59113.12
  60. minimax/minimax-m3unstated56104.58
  61. moonshotai/kimi-k3unstated54116.54
  62. kimi-k2.6-thinkingunstated · not in the catalog54107.26
  63. qwen/qwen3.6-27bunstated52103.72
  64. smaug-agenticunstated · not in the catalog52116.30
  65. z-ai/glm-5.3-flashunstated45108.42
  66. ox-alphamax · not in the catalog39106.05
  67. deepseek/deepseek-v4-flashunstated37102.96
  68. moonshotai/kimi-k2.7-codeunstated37107.73
  69. openai/gpt-5.4-minixhigh37104.22
  70. google/gemini-3.5-flash-litehigh2699.97
  71. nemotron-3.5-lightning-30b-a3bunstated · not in the catalog2487.31
consecutive_eventsLiveBench+0.16 · 1.44 · 71 runs

71 runs scored on it, 71 of them ranked, best score first, in the publisher's own unit. A ranked run is a door to its row.

  1. muse-wonder-1.0max · not in the catalog98.53120.86
  2. claude-sonnet-4-6-thinking-automedium · not in the catalog92.68114.06
  3. anthropic/claude-fable-5max91.36122.58
  4. openai/gpt-6.1-solxhigh91.29124.64
  5. claude-sonnet-5-5xhigh · not in the catalog90.94119.88
  6. openai/gpt-6-astramax90.56132.41
  7. openai/gpt-6.1-solmax90.56130.00
  8. claude-fable-5-1max · not in the catalog90.56125.12
  9. claude-opus-5-5max · not in the catalog90.56128.09
  10. meta/muse-spark-1.3xhigh90.50116.79
  11. smaug-agenticunstated · not in the catalog90.42116.30
  12. claude-opus-5-5xhigh · not in the catalog90.37125.14
  13. deepseek/deepseek-v4-pro-0813unstated90.23118.60
  14. openai/gpt-5.6-solmax90.21123.35
  15. deepseek/deepseek-v4-flash-vision-expunstated90.05116.36
  16. moonshotai/kimi-k3unstated89.76116.54
  17. openai/gpt-6-solmax89.55124.00
  18. claude-opus-4-7xhigh · not in the catalog89.52113.14
  19. deepseek/deepseek-v4-flash-0731unstated89.44113.47
  20. openai/gpt-5.2-codexunstated89.02110.02
  21. gpt-5.2-2025-12-11high · not in the catalog88.91110.74
  22. openai/gpt-5.5xhigh88.82120.29
  23. deepseek/deepseek-v4.1-flashmax88.72116.49
  24. smaug-flashunstated · not in the catalog88.61116.63
  25. smaug-miniunstated · not in the catalog88.50114.73
  26. openai/gpt-5.6-terramax87.67119.24
  27. qwen3.8-maxunstated · not in the catalog87.14118.08
  28. openai/gpt-5.6-lunamax86.50114.95
  29. openai/gpt-5.4xhigh86.19119.02
  30. x-ai/grok-4.7xhigh85.73113.32
  31. google/gemini-3.1-pro-previewhigh85.24113.89
  32. qwen/qwen3.8-27bunstated84.93112.72
  33. minimax/minimax-m3unstated84.61104.58
  34. z-ai/glm-5.3-flashunstated84.30108.42
  35. meta/muse-spark-1.2xhigh82.55117.04
  36. mistral-large-4high · not in the catalog80.53109.81
  37. ox-alphamax · not in the catalog80.35106.05
  38. claude-opus-4-5-20251101-thinking-64khigh · not in the catalog79.36110.65
  39. z-ai/glm-5.2unstated79.28109.40
  40. x-ai/grok-4.6unstated78.15117.62
  41. anthropic/claude-opus-5max77.57122.24
  42. qwen3.8-flash-nextunstated · not in the catalog75.62113.12
  43. x-ai/grok-4.5unstated75.54114.74
  44. deepseek/deepseek-v4-prounstated75.42111.64
  45. anthropic/claude-sonnet-5xhigh74.74113.50
  46. z-ai/glm-5.3unstated72.31112.92
  47. qwen/qwen3.7-maxunstated71.80111.06
  48. meta/muse-spark-1.1xhigh71.09114.21
  49. claude-haiku-5-5xhigh · not in the catalog71.05112.88
  50. openai/gpt-6-lunamax70.49113.99
  51. qwen/qwen3.6-27bunstated70.39103.72
  52. thinkingmachines/inklingxhigh69.85107.98
  53. x-ai/grok-build-0.1unstated69.73106.25
  54. qwen/qwen3.6-plusunstated67.04106.49
  55. claude-opus-4-6-thinking-autohigh · not in the catalog63.47113.04
  56. openai/gpt-5.4-minixhigh62.97104.22
  57. google/gemini-3.7-flashhigh60.37116.01
  58. deepseek/deepseek-v4-flashunstated59.91102.96
  59. openai/gpt-5.4-nanoxhigh54.30110.30
  60. claude-opus-4-8max · not in the catalog52.91116.89
  61. kimi-k2.6-thinkingunstated · not in the catalog51.27107.26
  62. moonshotai/kimi-k2.7-codeunstated48.28107.73
  63. google/gemini-3.5-flashhigh47.99111.12
  64. google/gemini-3.6-flashhigh43.82110.95
  65. claude-sonnet-5-5max · not in the catalog40.62122.13
  66. x-ai/grok-4.3unstated28.03103.07
  67. google/gemini-3.5-flash-litehigh21.0999.97
  68. google/gemini-3.8-flashhigh20.61114.21
  69. nvidia/nemotron-3-ultra-550b-a55bunstated18.77105.72
  70. claude-haiku-5-5max · not in the catalog10.64113.88
  71. nemotron-3.5-lightning-30b-a3bunstated · not in the catalog2.5187.31
zebra_puzzleLiveBench+0.13 · 3.39 · 71 runs

71 runs scored on it, 71 of them ranked, best score first, in the publisher's own unit. A ranked run is a door to its row.

  1. anthropic/claude-fable-5max100122.58
  2. anthropic/claude-opus-5max100122.24
  3. deepseek/deepseek-v4-flash-0731unstated100113.47
  4. deepseek/deepseek-v4.1-flashmax100116.49
  5. moonshotai/kimi-k3unstated100116.54
  6. openai/gpt-5.5xhigh100120.29
  7. openai/gpt-5.6-solmax100123.35
  8. openai/gpt-5.6-terramax100119.24
  9. openai/gpt-6-astramax100132.41
  10. openai/gpt-6-solmax100124.00
  11. openai/gpt-6.1-solmax100130.00
  12. openai/gpt-6.1-solxhigh100124.64
  13. claude-fable-5-1max · not in the catalog100125.12
  14. claude-opus-4-8max · not in the catalog100116.89
  15. claude-opus-5-5max · not in the catalog100128.09
  16. claude-opus-5-5xhigh · not in the catalog100125.14
  17. claude-sonnet-5-5max · not in the catalog100122.13
  18. claude-sonnet-5-5xhigh · not in the catalog100119.88
  19. muse-wonder-1.0max · not in the catalog100120.86
  20. qwen3.8-maxunstated · not in the catalog100118.08
  21. deepseek/deepseek-v4-flash-vision-expunstated98.75116.36
  22. qwen3.8-flash-nextunstated · not in the catalog98.75113.12
  23. google/gemini-3.8-flashhigh98.25114.21
  24. smaug-agenticunstated · not in the catalog98.25116.30
  25. meta/muse-spark-1.3xhigh98116.79
  26. openai/gpt-5.4xhigh98119.02
  27. claude-haiku-5-5xhigh · not in the catalog98112.88
  28. claude-opus-4-7xhigh · not in the catalog98113.14
  29. smaug-flashunstated · not in the catalog98116.63
  30. openai/gpt-5.4-nanoxhigh97.62110.30
  31. deepseek/deepseek-v4-pro-0813unstated96.75118.60
  32. qwen/qwen3.8-27bunstated96.50112.72
  33. meta/muse-spark-1.1xhigh96114.21
  34. moonshotai/kimi-k2.7-codeunstated96107.73
  35. openai/gpt-6-lunamax96113.99
  36. claude-sonnet-4-6-thinking-automedium · not in the catalog96114.06
  37. x-ai/grok-4.6unstated95.50117.62
  38. meta/muse-spark-1.2xhigh95.25117.04
  39. google/gemini-3.7-flashhigh94.50116.01
  40. claude-haiku-5-5max · not in the catalog94113.88
  41. claude-opus-4-6-thinking-autohigh · not in the catalog94113.04
  42. smaug-miniunstated · not in the catalog94114.73
  43. x-ai/grok-4.5unstated94114.74
  44. openai/gpt-5.6-lunamax93.50114.95
  45. mistral-large-4high · not in the catalog93109.81
  46. deepseek/deepseek-v4-prounstated92111.64
  47. z-ai/glm-5.3unstated88.75112.92
  48. anthropic/claude-sonnet-5xhigh88113.50
  49. thinkingmachines/inklingxhigh88107.98
  50. x-ai/grok-4.7xhigh86113.32
  51. google/gemini-3.6-flashhigh85.75110.95
  52. google/gemini-3.1-pro-previewhigh85.25113.89
  53. gpt-5.2-2025-12-11high · not in the catalog84110.74
  54. ox-alphamax · not in the catalog79.50106.05
  55. z-ai/glm-5.3-flashunstated79.50108.42
  56. kimi-k2.6-thinkingunstated · not in the catalog78.50107.26
  57. claude-opus-4-5-20251101-thinking-64khigh · not in the catalog77.50110.65
  58. google/gemini-3.5-flashhigh77.25111.12
  59. qwen/qwen3.7-maxunstated74.50111.06
  60. nvidia/nemotron-3-ultra-550b-a55bunstated71.25105.72
  61. openai/gpt-5.2-codexunstated70110.02
  62. x-ai/grok-build-0.1unstated68.25106.25
  63. qwen/qwen3.6-plusunstated68106.49
  64. z-ai/glm-5.2unstated65.50109.40
  65. minimax/minimax-m3unstated61104.58
  66. openai/gpt-5.4-minixhigh60.37104.22
  67. x-ai/grok-4.3unstated57.75103.07
  68. qwen/qwen3.6-27bunstated53.75103.72
  69. deepseek/deepseek-v4-flashunstated49.25102.96
  70. google/gemini-3.5-flash-litehigh32.7599.97
  71. nemotron-3.5-lightning-30b-a3bunstated · not in the catalog17.2587.31
javascriptLiveBench-0.07 · 0.58 · 71 runs

71 runs scored on it, 71 of them ranked, best score first, in the publisher's own unit. A ranked run is a door to its row.

  1. deepseek/deepseek-v4.1-flashmax81.82116.49
  2. claude-opus-5-5max · not in the catalog81.82128.09
  3. anthropic/claude-opus-5max77.27122.24
  4. meta/muse-spark-1.1xhigh77.27114.21
  5. meta/muse-spark-1.3xhigh77.27116.79
  6. claude-sonnet-5-5max · not in the catalog77.27122.13
  7. qwen3.8-maxunstated · not in the catalog77.27118.08
  8. smaug-agenticunstated · not in the catalog77.27116.30
  9. google/gemini-3.8-flashhigh72.73114.21
  10. meta/muse-spark-1.2xhigh72.73117.04
  11. claude-opus-5-5xhigh · not in the catalog72.73125.14
  12. x-ai/grok-4.5unstated72.73114.74
  13. x-ai/grok-4.6unstated72.73117.62
  14. z-ai/glm-5.3unstated72.73112.92
  15. anthropic/claude-fable-5max68.18122.58
  16. anthropic/claude-sonnet-5xhigh68.18113.50
  17. deepseek/deepseek-v4-pro-0813unstated68.18118.60
  18. google/gemini-3.7-flashhigh68.18116.01
  19. moonshotai/kimi-k3unstated68.18116.54
  20. openai/gpt-5.2-codexunstated68.18110.02
  21. openai/gpt-5.4xhigh68.18119.02
  22. openai/gpt-5.6-terramax68.18119.24
  23. thinkingmachines/inklingxhigh68.18107.98
  24. claude-fable-5-1max · not in the catalog68.18125.12
  25. claude-haiku-5-5max · not in the catalog68.18113.88
  26. claude-opus-4-8max · not in the catalog68.18116.89
  27. mistral-large-4high · not in the catalog68.18109.81
  28. muse-wonder-1.0max · not in the catalog68.18120.86
  29. qwen3.8-flash-nextunstated · not in the catalog68.18113.12
  30. smaug-flashunstated · not in the catalog68.18116.63
  31. deepseek/deepseek-v4-flash-0731unstated63.64113.47
  32. deepseek/deepseek-v4-flash-vision-expunstated63.64116.36
  33. google/gemini-3.5-flashhigh63.64111.12
  34. google/gemini-3.6-flashhigh63.64110.95
  35. minimax/minimax-m3unstated63.64104.58
  36. moonshotai/kimi-k2.7-codeunstated63.64107.73
  37. openai/gpt-5.4-nanoxhigh63.64110.30
  38. openai/gpt-5.5xhigh63.64120.29
  39. openai/gpt-5.6-lunamax63.64114.95
  40. openai/gpt-5.6-solmax63.64123.35
  41. openai/gpt-6-astramax63.64132.41
  42. openai/gpt-6-lunamax63.64113.99
  43. openai/gpt-6-solmax63.64124.00
  44. openai/gpt-6.1-solmax63.64130.00
  45. openai/gpt-6.1-solxhigh63.64124.64
  46. claude-opus-4-6-thinking-autohigh · not in the catalog63.64113.04
  47. claude-opus-4-7xhigh · not in the catalog63.64113.14
  48. x-ai/grok-4.7xhigh63.64113.32
  49. z-ai/glm-5.2unstated63.64109.40
  50. z-ai/glm-5.3-flashunstated63.64108.42
  51. google/gemini-3.1-pro-previewhigh59.09113.89
  52. google/gemini-3.5-flash-litehigh59.0999.97
  53. qwen/qwen3.6-plusunstated59.09106.49
  54. qwen/qwen3.7-maxunstated59.09111.06
  55. qwen/qwen3.8-27bunstated59.09112.72
  56. claude-haiku-5-5xhigh · not in the catalog59.09112.88
  57. claude-opus-4-5-20251101-thinking-64khigh · not in the catalog59.09110.65
  58. gpt-5.2-2025-12-11high · not in the catalog59.09110.74
  59. kimi-k2.6-thinkingunstated · not in the catalog59.09107.26
  60. smaug-miniunstated · not in the catalog59.09114.73
  61. x-ai/grok-build-0.1unstated59.09106.25
  62. deepseek/deepseek-v4-flashunstated54.55102.96
  63. deepseek/deepseek-v4-prounstated54.55111.64
  64. nvidia/nemotron-3-ultra-550b-a55bunstated54.55105.72
  65. qwen/qwen3.6-27bunstated54.55103.72
  66. claude-sonnet-4-6-thinking-automedium · not in the catalog54.55114.06
  67. ox-alphamax · not in the catalog54.55106.05
  68. openai/gpt-5.4-minixhigh50104.22
  69. claude-sonnet-5-5xhigh · not in the catalog36.36119.88
  70. x-ai/grok-4.3unstated27.27103.07
  71. nemotron-3.5-lightning-30b-a3bunstated · not in the catalog18.1887.31
polyglot pass rateAider polyglot-0.23 · 1.58 · 69 runs

69 runs scored on it, 17 of them ranked, best score first, in the publisher's own unit. A ranked run is a door to its row.

  1. openai/gpt-5high88set aside
  2. openai/gpt-5medium86.70set aside
  3. openai/o3-prohigh84.90set aside
  4. gemini-2.5-pro-preview-06-05-(32k-think)unstated · not in the catalog83.10set aside
  5. openai/gpt-5low81.30set aside
  6. openai/o3high81.30set aside
  7. grok-4high · not in the catalog79.60set aside
  8. gemini-2.5-pro-preview-06-05-(default-think)unstated · not in the catalog79.10set aside
  9. o3-(high)-+-gpt-4.1unstated · not in the catalog78.20set aside
  10. openai/o3unstated76.90set aside
  11. gemini-2.5-pro-preview-05-06unstated · not in the catalog76.90102.43
  12. deepseek-v3.2-exp-(reasoner)unstated · not in the catalog74.20set aside
  13. gemini-2.5-pro-preview-03-25unstated · not in the catalog72.90set aside
  14. claude-opus-4-20250514-(32k-thinking)unstated · not in the catalog72set aside
  15. o4-minihigh · not in the catalog72set aside
  16. deepseek-r1-(0528)unstated · not in the catalog71.40set aside
  17. claude-opus-4-20250514-(no-think)unstated · not in the catalog70.70set aside
  18. deepseek-v3.2-exp-(chat)unstated · not in the catalog70.20set aside
  19. claude-3-7-sonnet-20250219-(32k-thinking-tokens)unstated · not in the catalog64.90set aside
  20. deepseek-r1-+-claude-3-5-sonnet-20241022unstated · not in the catalog64set aside
  21. o1-2024-12-17high · not in the catalog61.7098.27
  22. claude-sonnet-4-20250514-(32k-thinking)unstated · not in the catalog61.30set aside
  23. claude-3-7-sonnet-20250219-(no-thinking)unstated · not in the catalog60.40set aside
  24. o3-minihigh · not in the catalog60.40set aside
  25. qwen3-235b-a22b-diff,-no-think,-alibaba-apiunstated · not in the catalog59.60set aside
  26. moonshotai/kimi-k2unstated59.10set aside
  27. deepseek-r1unstated · not in the catalog56.9096.08
  28. claude-sonnet-4-20250514-(no-thinking)unstated · not in the catalog56.40set aside
  29. deepseek-v3-(0324)unstated · not in the catalog55.10set aside
  30. gemini-2.5-flash-preview-05-20-(24k-think)unstated · not in the catalog55.10set aside
  31. quasar-alphaunstated · not in the catalog54.70set aside
  32. o3-minimedium · not in the catalog53.80set aside
  33. grok-3-betaunstated · not in the catalog53.3094.65
  34. optimus-alphaunstated · not in the catalog52.90set aside
  35. openai/gpt-4.1unstated52.40set aside
  36. claude-3-5-sonnet-20241022unstated · not in the catalog51.6085.31
  37. grok-3-mini-betahigh · not in the catalog49.3097.03
  38. deepseek-chat-v3-(prev)unstated · not in the catalog48.40set aside
  39. gemini-2.5-flash-preview-04-17-(default)unstated · not in the catalog47.10set aside
  40. chatgpt-4o-latest-(2025-03-29)unstated · not in the catalog45.30set aside
  41. gpt-4.5-previewunstated · not in the catalog44.90set aside
  42. gemini-2.5-flash-preview-05-20-(no-think)unstated · not in the catalog44set aside
  43. openai/gpt-oss-120bhigh41.80set aside
  44. qwen/qwen3-32bunstated4096.21
  45. gemini-exp-1206unstated · not in the catalog38.20set aside
  46. gemini-2.0-pro-exp-02-05unstated · not in the catalog35.6090.84
  47. grok-3-mini-betalow · not in the catalog34.7094.71
  48. o1-mini-2024-09-12unstated · not in the catalog32.90set aside
  49. openai/gpt-4.1-miniunstated32.40set aside
  50. claude-3-5-haiku-20241022unstated · not in the catalog2880.42
  51. chatgpt-4o-latest-(2025-02-15)unstated · not in the catalog27.10set aside
  52. qwq-32b-+-qwen-2.5-coder-instructunstated · not in the catalog26.20set aside
  53. openai/gpt-4o-2024-08-06unstated23.1082.76
  54. gemini-2.0-flash-expunstated · not in the catalog22.20set aside
  55. qwen-max-2025-01-25unstated · not in the catalog21.8085.11
  56. qwq-32bunstated · not in the catalog20.9093.18
  57. openai/gpt-4o-2024-11-20unstated18.2080.37
  58. gemini-2.0-flash-thinking-exp-01-21unstated · not in the catalog18.2092.14
  59. deepseek-chat-v2.5unstated · not in the catalog17.80set aside
  60. qwen2.5-coder-32b-instructunstated · not in the catalog16.40set aside
  61. meta-llama/llama-4-maverickunstated15.60set aside
  62. yi-lightningunstated · not in the catalog12.90set aside
  63. command-a-03-2025-qualityunstated · not in the catalog12set aside
  64. codestral-25.01unstated · not in the catalog11.10set aside
  65. openhands-lm-32b-v0.1unstated · not in the catalog10.20set aside
  66. openai/gpt-4.1-nanounstated8.90set aside
  67. qwen2.5-coder-32b-instructunstated · not in the catalog8set aside
  68. google/gemma-3-27b-itunstated4.9085.05
  69. openai/gpt-4o-mini-2024-07-18unstated3.6080.10
logic_with_navigationLiveBench-0.30 · 0.81 · 71 runs

71 runs scored on it, 71 of them ranked, best score first, in the publisher's own unit. A ranked run is a door to its row.

  1. meta/muse-spark-1.2xhigh88117.04
  2. openai/gpt-6-astramax88132.41
  3. anthropic/claude-opus-5max86122.24
  4. anthropic/claude-sonnet-5xhigh86113.50
  5. openai/gpt-6.1-solmax86130.00
  6. claude-fable-5-1max · not in the catalog86125.12
  7. claude-opus-5-5max · not in the catalog86128.09
  8. qwen/qwen3.7-maxunstated84111.06
  9. smaug-agenticunstated · not in the catalog84116.30
  10. google/gemini-3.8-flashhigh82114.21
  11. openai/gpt-5.6-solmax82123.35
  12. openai/gpt-6.1-solxhigh82124.64
  13. claude-sonnet-5-5max · not in the catalog82122.13
  14. x-ai/grok-4.6unstated82117.62
  15. moonshotai/kimi-k3unstated80116.54
  16. openai/gpt-5.6-lunamax80114.95
  17. claude-opus-4-6-thinking-autohigh · not in the catalog80113.04
  18. claude-opus-5-5xhigh · not in the catalog80125.14
  19. claude-sonnet-5-5xhigh · not in the catalog80119.88
  20. muse-wonder-1.0max · not in the catalog80120.86
  21. z-ai/glm-5.2unstated80109.40
  22. anthropic/claude-fable-5max78122.58
  23. meta/muse-spark-1.1xhigh78114.21
  24. claude-opus-4-8max · not in the catalog78116.89
  25. google/gemini-3.6-flashhigh76110.95
  26. meta/muse-spark-1.3xhigh76116.79
  27. openai/gpt-5.5xhigh76120.29
  28. openai/gpt-5.6-terramax76119.24
  29. google/gemini-3.5-flashhigh74111.12
  30. google/gemini-3.7-flashhigh74116.01
  31. moonshotai/kimi-k2.7-codeunstated74107.73
  32. openai/gpt-6-solmax74124.00
  33. gpt-5.2-2025-12-11high · not in the catalog74110.74
  34. qwen3.8-maxunstated · not in the catalog74118.08
  35. google/gemini-3.1-pro-previewhigh72113.89
  36. smaug-flashunstated · not in the catalog72116.63
  37. x-ai/grok-4.5unstated72114.74
  38. deepseek/deepseek-v4-flash-0731unstated70113.47
  39. qwen/qwen3.6-plusunstated70106.49
  40. claude-opus-4-7xhigh · not in the catalog70113.14
  41. claude-sonnet-4-6-thinking-automedium · not in the catalog70114.06
  42. kimi-k2.6-thinkingunstated · not in the catalog70107.26
  43. qwen3.8-flash-nextunstated · not in the catalog70113.12
  44. smaug-miniunstated · not in the catalog70114.73
  45. x-ai/grok-build-0.1unstated70106.25
  46. z-ai/glm-5.3unstated70112.92
  47. deepseek/deepseek-v4-flash-vision-expunstated68116.36
  48. deepseek/deepseek-v4.1-flashmax68116.49
  49. google/gemini-3.5-flash-litehigh6899.97
  50. nvidia/nemotron-3-ultra-550b-a55bunstated68105.72
  51. openai/gpt-5.2-codexunstated68110.02
  52. openai/gpt-5.4xhigh68119.02
  53. qwen/qwen3.8-27bunstated68112.72
  54. claude-opus-4-5-20251101-thinking-64khigh · not in the catalog68110.65
  55. mistral-large-4high · not in the catalog68109.81
  56. deepseek/deepseek-v4-pro-0813unstated66118.60
  57. minimax/minimax-m3unstated66104.58
  58. thinkingmachines/inklingxhigh66107.98
  59. claude-haiku-5-5max · not in the catalog66113.88
  60. x-ai/grok-4.3unstated66103.07
  61. x-ai/grok-4.7xhigh66113.32
  62. deepseek/deepseek-v4-flashunstated64102.96
  63. deepseek/deepseek-v4-prounstated64111.64
  64. openai/gpt-5.4-nanoxhigh64110.30
  65. openai/gpt-6-lunamax62113.99
  66. qwen/qwen3.6-27bunstated62103.72
  67. z-ai/glm-5.3-flashunstated62108.42
  68. openai/gpt-5.4-minixhigh60104.22
  69. claude-haiku-5-5xhigh · not in the catalog56112.88
  70. ox-alphamax · not in the catalog52106.05
  71. nemotron-3.5-lightning-30b-a3bunstated · not in the catalog1887.31
OTIS Mock AIME 2024-2025Epoch AI Benchmarking Hub-0.39 · 2.55 · 319 runs

319 runs scored on it, 266 of them ranked, best score first, in the publisher's own unit. A ranked run is a door to its row.

  1. anthropic/claude-fable-5high1119.29
  2. google/gemini-4-argonhigh1124.90
  3. google/gemini-4-carbonhigh1131.68
  4. google/gemini-4-hydrogenxhigh1125.83
  5. openai/gpt-5.6-solmax1123.35
  6. openai/gpt-6-astramax1132.41
  7. openai/gpt-6-solmax1124.00
  8. openai/gpt-6.1-solmax1130.00
  9. openai/gpt-6.1-terramax1130.85
  10. qwen/qwen3.8-max-0902xhigh1113.51
  11. claude-fable-5-1max · not in the catalog1125.12
  12. claude-opus-5-5max · not in the catalog1128.09
  13. claude-sonnet-5-5max · not in the catalog1122.13
  14. gemini-4-neonxhigh · not in the catalog1134.54
  15. gpt-5.5-pre-releasexhigh · not in the catalog1116.86
  16. gpt-5.5-pro-pre-releasexhigh · not in the catalog1117.38
  17. gpt-6.2-astramax · not in the catalog1135.84
  18. kimi-k3.1-pro-togethermax · not in the catalog1118.88
  19. anthropic/claude-fable-5max1.00122.58
  20. openai/gpt-5.6-terramax1.00119.24
  21. claude-fable-5-2max · not in the catalog1.00132.06
  22. deepseek/deepseek-v4.1-flash-1017max0.99116.25
  23. mistral-large-4-0-osshigh · not in the catalog0.99110.78
  24. muse-wonder-1.0max · not in the catalog0.99120.86
  25. qwen3.8-maxxhigh · not in the catalog0.99116.39
  26. meta/muse-spark-1.3xhigh0.99116.79
  27. doubao-seed-evolvinghigh · not in the catalog0.99114.76
  28. x-ai/grok-4.6xhigh0.99114.39
  29. anthropic/claude-opus-5max0.99122.24
  30. google/gemini-3.8-flashhigh0.99114.21
  31. openai/gpt-6-lunamax0.99113.99
  32. claude-haiku-5-5xhigh · not in the catalog0.99112.88
  33. deepseek/deepseek-v4-pro-0813max0.99113.60
  34. deepseek/deepseek-v4.1-flashmax0.98116.49
  35. mistralai/mistral-large-4-0high0.98110.63
  36. openai/gpt-5.6-lunamax0.98114.95
  37. claude-opus-4-8max · not in the catalog0.98116.89
  38. muse-spark-open-816b-a42bxhigh · not in the catalog0.98113.92
  39. x-ai/grok-4.7xhigh0.98113.32
  40. claude-opus-4-7xhigh · not in the catalog0.98113.14
  41. anthropic/claude-fable-5low0.98110.20
  42. anthropic/claude-opus-5unstated0.98115.94
  43. claude-opus-4-8low · not in the catalog0.98111.54
  44. gpt-5.4-2026-03-05high · not in the catalog0.98115.98
  45. x-ai/grok-4.5high0.98111.55
  46. x-ai/grok-4.6high0.98114.02
  47. google/gemini-3.7-flashhigh0.97116.01
  48. moonshotai/kimi-k3max0.97114.75
  49. claude-haiku-5-5high · not in the catalog0.97set aside
  50. deepseek/deepseek-v4-promax0.97107.02
  51. moonshotai/kimi-k2.6unstated0.96110.82
  52. doubao-seed-2.1-turbo-260628high · not in the catalog0.96108.84
  53. gpt-5.2-2025-12-11high · not in the catalog0.96110.74
  54. gpt-5.2-2025-12-11xhigh · not in the catalog0.96113.39
  55. google/gemini-3.1-pro-previewunstated0.96111.66
  56. deepseek/deepseek-v4-prohigh0.96108.20
  57. google/gemini-3-flash-previewhigh0.96113.70
  58. google/gemini-3.1-pro-previewhigh0.96113.89
  59. google/gemini-3.5-flashhigh0.96111.12
  60. moonshotai/kimi-k2.7-codeunstated0.96107.73
  61. openai/gpt-5.6-sollow0.96110.85
  62. qwen/qwen3.7-maxunstated0.96111.06
  63. doubao-seed-2.1-pro-260628high · not in the catalog0.96109.61
  64. gpt-5.4-2026-03-05medium · not in the catalog0.96112.04
  65. gpt-5.4-2026-03-05xhigh · not in the catalog0.95116.23
  66. anthropic/claude-sonnet-5xhigh0.95113.50
  67. deepseek/deepseek-v4-flash-0731max0.94111.14
  68. claude-opus-4-6-64kunstated · not in the catalog0.94111.92
  69. google/gemini-3.6-flashhigh0.94110.95
  70. doubao-seed-2.0-pro-260215high · not in the catalog0.94108.12
  71. gpt-5.2-2025-12-11medium · not in the catalog0.94108.75
  72. z-ai/glm-5.3-flashmax0.94108.45
  73. anthropic/claude-opus-5low0.93109.13
  74. moonshotai/kimi-k3high0.93112.20
  75. qwen/qwen3.6-plusunstated0.93106.49
  76. qwen/qwen3.7-plusunstated0.93107.80
  77. x-ai/grok-4.3high0.93107.39
  78. z-ai/glm-5.1unstated0.93109.27
  79. claude-opus-4-6-32kunstated · not in the catalog0.93111.03
  80. google/gemini-3-flash-previewunstated0.93108.16
  81. grok-4.20-0309-reasoningunstated · not in the catalog0.92108.33
  82. fireworks/kimi-k2p5unstated · not in the catalog0.92107.32
  83. gemini-3-pro-previewunstated · not in the catalog0.91110.74
  84. gpt-5-2025-08-07high · not in the catalog0.91108.61
  85. qwen/qwen3.6-27bunstated0.91103.72
  86. claude-opus-4-6max · not in the catalog0.91111.69
  87. doubao-seed-2.0-lite-260428high · not in the catalog0.91106.42
  88. qwen3.6-max-previewunstated · not in the catalog0.91106.75
  89. z-ai/glm-5.3max0.91112.54
  90. thinkingmachines/inkling-smallxhigh0.90106.54
  91. muse-sparkunstated · not in the catalog0.89110.41
  92. google/gemini-3.5-flashlow0.89110.83
  93. openai/gpt-5.6-terralow0.89106.93
  94. qwen/qwen3.5-397b-a17bunstated0.89104.40
  95. thinkingmachines/inklingxhigh0.89107.98
  96. gpt-5.4-mini-2026-03-17xhigh · not in the catalog0.89106.91
  97. openai/gpt-oss-120bhigh · not in the catalog0.89set aside
  98. gpt-5.1-2025-11-13high · not in the catalog0.89109.94
  99. deepseek-reasonerunstated · not in the catalog0.88set aside
  100. gpt-5.4-nano-2026-03-17high · not in the catalog0.88106.76
  101. gpt-5-2025-08-07medium · not in the catalog0.87108.12
  102. gpt-5.4-mini-2026-03-17high · not in the catalog0.87106.09
  103. qwen/qwen3-235b-a22b-thinking-2507unstated0.87104.10
  104. qwen/qwen3.6-35b-a3bunstated0.87102.04
  105. qwen/qwen3.7-flashunstated0.87102.16
  106. claude-opus-4-7max · not in the catalog0.87113.03
  107. gpt-5-mini-2025-08-07high · not in the catalog0.87104.57
  108. nemotron-3-ultraunstated · not in the catalog0.87105.62
  109. qwen3.5-plusunstated · not in the catalog0.87105.31
  110. z-ai/glm-5.2max0.86110.33
  111. claude-opus-4-5-20251101-32kunstated · not in the catalog0.86104.05
  112. claude-sonnet-4-6-32kunstated · not in the catalog0.86set aside
  113. gpt-5.1-2025-11-13medium · not in the catalog0.86105.41
  114. openai/gpt-5.5low0.84107.86
  115. qwen/qwen3.6-flashunstated0.84100.95
  116. claude-opus-4-8none · not in the catalog0.84104.31
  117. gpt-5.4-2026-03-05low · not in the catalog0.84104.16
  118. o3-2025-04-16medium · not in the catalog0.84101.11
  119. qwen3.5-flashunstated · not in the catalog0.8499.58
  120. google/gemini-2.5-prounstated0.84103.73
  121. grok-4-0709unstated · not in the catalog0.84104.16
  122. o3-2025-04-16high · not in the catalog0.84102.96
  123. z-ai/glm-4.7unstated0.83104.07
  124. kimi-k2-thinking-turbounstated · not in the catalog0.83102.46
  125. google/gemini-3.6-flashlow0.82107.80
  126. google/gemma-4-26b-a4b-itminimal0.82set aside
  127. qwen/qwen3.5-397b-a17bnone0.82103.55
  128. claude-sonnet-4-6medium · not in the catalog0.82103.01
  129. claude-opus-4-5-20251101-16kunstated · not in the catalog0.82104.70
  130. o4-mini-2025-04-16high · not in the catalog0.82103.35
  131. gpt-5-nano-2025-08-07high · not in the catalog0.81100.45
  132. anthropic/claude-sonnet-5max0.80112.43
  133. google/gemini-3.1-flash-litehigh0.80102.13
  134. google/gemini-3.5-flashminimal0.80104.41
  135. google/gemini-3.6-flashminimal0.80105.55
  136. qwen/qwen3.7-plusnone0.80103.17
  137. z-ai/glm-5unstated0.8099.96
  138. gpt-5.2-2025-12-11low · not in the catalog0.79104.89
  139. gpt-5-mini-2025-08-07medium · not in the catalog0.78103.83
  140. qwen/qwen3.7-flashnone0.78100.54
  141. claude-sonnet-4-5-20250929-32kunstated · not in the catalog0.78101.18
  142. claude-sonnet-4-5-20250929-59kunstated · not in the catalog0.78101.26
  143. grok-3-mini-betahigh · not in the catalog0.7897.03
  144. o3-mini-2025-01-31high · not in the catalog0.77102.45
  145. claude-sonnet-4-6high · not in the catalog0.76102.30
  146. z-ai/glm-5.2low0.76105.42
  147. gpt-5-nano-2025-08-07medium · not in the catalog0.7499.03
  148. google/gemma-4-31b-itminimal0.73set aside
  149. o1-2024-12-17high · not in the catalog0.7398.27
  150. o1-2024-12-17medium · not in the catalog0.7397.81
  151. o4-mini-2025-04-16medium · not in the catalog0.73101.93
  152. qwen3-max-2025-09-23unstated · not in the catalog0.73100.03
  153. gemini-2.5-flash-preview-04-17unstated · not in the catalog0.73set aside
  154. google/gemini-3.5-flash-litehigh0.7199.97
  155. minimax/minimax-m3unstated0.71104.58
  156. claude-sonnet-4-20250514-32kunstated · not in the catalog0.71set aside
  157. claude-sonnet-4-5-20250929-16kunstated · not in the catalog0.71set aside
  158. claude-sonnet-4-6max · not in the catalog0.71101.17
  159. gemini-2.5-flash-preview-05-20unstated · not in the catalog0.71set aside
  160. qwen3-30b-a3b-thinking-2507unstated · not in the catalog0.70set aside
  161. qwen/qwen3.5-35b-a3bnone0.70set aside
  162. seed-1.6unstated · not in the catalog0.6997.70
  163. moonshotai/kimi-k3low0.69100.12
  164. openai/gpt-5.6-solnone0.69100.98
  165. qwen/qwen3.6-35b-a3bnone0.69100.22
  166. claude-opus-4-1-20250805-27kunstated · not in the catalog0.6997.29
  167. claude-sonnet-4-20250514-59kunstated · not in the catalog0.6999.17
  168. gpt-5.4-nano-2026-03-17low · not in the catalog0.6998.40
  169. gpt-5.5-instantunstated · not in the catalog0.6899.89
  170. seed-oss-36b-instructunstated · not in the catalog0.68set aside
  171. qwen/qwen3-32bunstated0.6796.21
  172. openai/gpt-5.6-lunalow0.67101.92
  173. qwen/qwen3.6-27bnone0.67100.32
  174. claude-haiku-4-5-20251001-32kunstated · not in the catalog0.6796.01
  175. deepseek/deepseek-r1-0528unstated0.6698.81
  176. qwen/qwen3-14bunstated0.66set aside
  177. openai/gpt-oss-20bmedium0.65set aside
  178. claude-opus-4-1-20250805-16kunstated · not in the catalog0.6496.39
  179. claude-opus-4-20250514-27kunstated · not in the catalog0.6497.69
  180. gpt-5.1-2025-11-13low · not in the catalog0.64100.64
  181. o3-mini-2025-01-31medium · not in the catalog0.6497.94
  182. qwen/qwen3-30b-a3bunstated0.63set aside
  183. qwen/qwen3-30b-a3b-instruct-2507unstated0.62set aside
  184. gpt-5.2-2025-12-11none · not in the catalog0.6296.53
  185. grok-3-mini-betalow · not in the catalog0.6294.71
  186. qwen/qwen3.5-9bnone0.62set aside
  187. google/gemini-3.5-flash-litelow0.6098.68
  188. claude-opus-4-20250514-16kunstated · not in the catalog0.60set aside
  189. o3-2025-04-16low · not in the catalog0.6099.37
  190. qwq-32bunstated · not in the catalog0.5993.18
  191. z-ai/glm-4.7-flashunstated0.58set aside
  192. openai/gpt-5.5none0.5897.11
  193. claude-3-7-sonnet-20250219-64kunstated · not in the catalog0.5895.18
  194. gemini-2.0-flash-thinking-exp-01-21unstated · not in the catalog0.5892.14
  195. gpt-5.4-2026-03-05none · not in the catalog0.5896.15
  196. o4-mini-2025-04-16low · not in the catalog0.58100.61
  197. qwen3-8bunstated · not in the catalog0.56set aside
  198. qwen3.5-4bnone · not in the catalog0.56set aside
  199. deepseek-r1-distill-qwen-32bunstated · not in the catalog0.56set aside
  200. gpt-5-mini-2025-08-07minimal · not in the catalog0.5693.86
  201. grok-3-betaunstated · not in the catalog0.5694.65
  202. qwen/qwen3.5-35b-a3bunstated0.54set aside
  203. openai/gpt-5.6-terranone0.5395.57
  204. claude-3-7-sonnet-20250219-32kunstated · not in the catalog0.5394.40
  205. claude-sonnet-4-20250514-16kunstated · not in the catalog0.53set aside
  206. deepseek-r1unstated · not in the catalog0.5396.08
  207. o1-2024-12-17low · not in the catalog0.5394.71
  208. qwen3-4b-instruct-2507unstated · not in the catalog0.52set aside
  209. deepseek-r1-distill-llama-70bunstated · not in the catalog0.5193.55
  210. google/gemini-3.5-flash-liteminimal0.5194.95
  211. openai/gpt-oss-20bhigh0.51set aside
  212. deepseek-r1-distill-qwen-14bunstated · not in the catalog0.5192.30
  213. deepseek/deepseek-chatunstated0.49set aside
  214. claude-opus-4-5-20251101unstated · not in the catalog0.4899.92
  215. o1-mini-2024-09-12high · not in the catalog0.4792.53
  216. deepseek/deepseek-v4-pronone0.4794.28
  217. claude-3-7-sonnet-20250219-16kunstated · not in the catalog0.4793.20
  218. gpt-5-2025-08-07minimal · not in the catalog0.4795.14
  219. gpt-5-nano-2025-08-07low · not in the catalog0.4792.74
  220. gpt-5.4-nano-2026-03-17none · not in the catalog0.4791.33
  221. gpt-4.1-mini-2025-04-14unstated · not in the catalog0.4593.48
  222. o1-mini-2024-09-12medium · not in the catalog0.4591.51
  223. google/gemini-3.1-flash-litelow0.4494.94
  224. o3-mini-2025-01-31low · not in the catalog0.4491.91
  225. deepseek-r1-0528-qwen3-8bunstated · not in the catalog0.44set aside
  226. qwen/qwen3.5-9bunstated0.43set aside
  227. claude-opus-4-20250514unstated · not in the catalog0.4292.48
  228. openai/gpt-oss-20blow0.40set aside
  229. openai/gpt-5.6-lunanone0.4095.93
  230. claude-opus-4-1-20250805unstated · not in the catalog0.4093.81
  231. gpt-4.1-2025-04-14unstated · not in the catalog0.3891.64
  232. google/gemini-3.1-flash-liteminimal0.3893.68
  233. deepseek-v3-0324unstated · not in the catalog0.3890.12
  234. gpt-4.5-preview-2025-02-27unstated · not in the catalog0.3890.75
  235. gpt-5.1-2025-11-13none · not in the catalog0.3891.90
  236. claude-haiku-4-5-20251001unstated · not in the catalog0.3690.99
  237. claude-sonnet-4-5-20250929unstated · not in the catalog0.3693.21
  238. gpt-5-nano-2025-08-07minimal · not in the catalog0.3688.08
  239. mistral-medium-2505unstated · not in the catalog0.3289.41
  240. gemini-2.0-flash-001unstated · not in the catalog0.3189.75
  241. o1-preview-2024-09-12unstated · not in the catalog0.3189.08
  242. mistral-small-3.2-2506unstated · not in the catalog0.30set aside
  243. magistral-small-2506unstated · not in the catalog0.3088.63
  244. claude-sonnet-4-20250514unstated · not in the catalog0.2990.16
  245. gpt-4.1-nano-2025-04-14unstated · not in the catalog0.2986.22
  246. z-ai/glm-5.2none0.2996.22
  247. magistral-small-2509unstated · not in the catalog0.28set aside
  248. minimax/minimax-m3none0.2790.84
  249. gpt-5.4-mini-2026-03-17none · not in the catalog0.2790.48
  250. qwen/qwen3-14bnone0.26set aside
  251. qwen/qwen3-30b-a3bnone0.26set aside
  252. z-ai/glm-4.7-flashnone0.25set aside
  253. qwen/qwen3-32bnone0.23set aside
  254. gemini-1.5-pro-002unstated · not in the catalog0.2386.80
  255. google/gemma-3-27b-itunstated0.2385.05
  256. qwen3-8bnone · not in the catalog0.22set aside
  257. claude-3-7-sonnet-20250219unstated · not in the catalog0.2287.22
  258. deepseek-r1-distill-qwen-1.5bunstated · not in the catalog0.21set aside
  259. llama-4-maverick-17b-128e-instruct-fp8unstated · not in the catalog0.2187.21
  260. qwen-plus-2025-01-25unstated · not in the catalog0.1884.76
  261. google/gemma-3-12b-itunstated0.17set aside
  262. gemini-1.5-flash-002unstated · not in the catalog0.1683.86
  263. qwen-max-2025-01-25unstated · not in the catalog0.1685.11
  264. deepseek-v3unstated · not in the catalog0.1684.96
  265. microsoft/phi-4unstated0.1484.64
  266. grok-2-1212unstated · not in the catalog0.1283.89
  267. llama-3.1-405b-instructunstated · not in the catalog0.1081.49
  268. mistralai/mistral-large-2407unstated0.0880.40
  269. claude-3-5-sonnet-20241022unstated · not in the catalog0.0885.31
  270. qwen2.5-72b-instructunstated · not in the catalog0.0883.11
  271. qwen3-1.7bnone · not in the catalog0.08set aside
  272. llama-4-scout-17b-16e-instructunstated · not in the catalog0.0882.99
  273. mistral-large-2411unstated · not in the catalog0.0881.24
  274. google/gemma-3-4b-itunstated0.07set aside
  275. qwen2.5-32b-instructunstated · not in the catalog0.0781.76
  276. openai/gpt-4o-mini-2024-07-18unstated0.0780.10
  277. gemini-1.5-pro-001unstated · not in the catalog0.0779.25
  278. gpt-4-turbo-2024-04-09unstated · not in the catalog0.0780.07
  279. mistral-small-3-2501unstated · not in the catalog0.07set aside
  280. claude-3-5-sonnet-20240620unstated · not in the catalog0.0781.59
  281. openai/gpt-4o-2024-08-06unstated0.0682.76
  282. openai/gpt-4o-2024-05-13unstated0.0681.01
  283. openai/gpt-4o-2024-11-20unstated0.0680.37
  284. qwen-turbo-2024-11-01unstated · not in the catalog0.0681.30
  285. mistral-small-2503unstated · not in the catalog0.0680.18
  286. mistral-small-2501unstated · not in the catalog0.0579.62
  287. meta-llama/llama-3.3-70b-instructunstated0.0579.22
  288. claude-3-opus-20240229unstated · not in the catalog0.0578.88
  289. gemini-1.5-flash-8b-001unstated · not in the catalog0.05set aside
  290. llama-3.1-tulu-3-70b-dpounstated · not in the catalog0.0479.20
  291. claude-3-5-haiku-20241022unstated · not in the catalog0.0480.42
  292. meta-llama-3-70b-instructunstated · not in the catalog0.0474.91
  293. gemini-1.5-flash-001unstated · not in the catalog0.0475.35
  294. mistral-small-3.1-2503unstated · not in the catalog0.04set aside
  295. meta-llama/llama-3.1-70b-instructunstated0.0477.86
  296. granite-4.0-microunstated · not in the catalog0.03set aside
  297. llama-3.2-90b-vision-instructunstated · not in the catalog0.0377.93
  298. claude-2.0unstated · not in the catalog0.0370.91
  299. claude-3-sonnet-20240229unstated · not in the catalog0.0373.46
  300. hermes-2-theta-llama-3-70bunstated · not in the catalog0.0374.21
  301. qwen2.5-7b-instructunstated · not in the catalog0.03set aside
  302. gpt-3.5-turbo-0125unstated · not in the catalog0.0269.92
  303. claude-2.1unstated · not in the catalog0.02set aside
  304. meta-llama-3-8b-instructunstated · not in the catalog0.0267.01
  305. mistral-large-2402unstated · not in the catalog0.0274.62
  306. claude-3-haiku-20240307unstated · not in the catalog0.0271.87
  307. meta-llama/llama-3.1-8b-instructunstated0.0272.89
  308. google/gemma-2-27b-itunstated0.0175.03
  309. gemini-1.0-pro-001unstated · not in the catalog0.0170.18
  310. gemma-3-1b-itunstated · not in the catalog0.01set aside
  311. gpt-4-0613unstated · not in the catalog0.0174.56
  312. deepseek-llm-67b-chatunstated · not in the catalog0.0166.23
  313. granite-4.0-1bunstated · not in the catalog0.01set aside
  314. meta-llama/llama-3.2-1b-instructunstated0.01set aside
  315. gemma-2-9b-itunstated · not in the catalog0.0172.14
  316. gpt-4-0314unstated · not in the catalog0.01set aside
  317. granite-4.0-350munstated · not in the catalog0.00set aside
  318. mistral-7b-instruct-v0.3unstated · not in the catalog0.0060.84
  319. llama-2-70b-chat-hfunstated · not in the catalog064.40
simplifyLiveBench-0.56 · 0.37 · 71 runs

71 runs scored on it, 71 of them ranked, best score first, in the publisher's own unit. A ranked run is a door to its row.

  1. google/gemini-3.6-flashhigh75.70110.95
  2. google/gemini-3.8-flashhigh75.40114.21
  3. google/gemini-3.7-flashhigh74.62116.01
  4. meta/muse-spark-1.3xhigh72.52116.79
  5. claude-sonnet-5-5xhigh · not in the catalog72.37119.88
  6. nvidia/nemotron-3-ultra-550b-a55bunstated72.28105.72
  7. anthropic/claude-fable-5max72.03122.58
  8. openai/gpt-6.1-solmax71.97130.00
  9. google/gemini-3.1-pro-previewhigh71.05113.89
  10. openai/gpt-6-astramax70.53132.41
  11. openai/gpt-5.6-solmax70.52123.35
  12. qwen3.8-flash-nextunstated · not in the catalog70.25113.12
  13. claude-fable-5-1max · not in the catalog70.17125.12
  14. x-ai/grok-4.5unstated70.17114.74
  15. openai/gpt-5.4xhigh70119.02
  16. x-ai/grok-4.7xhigh69.97113.32
  17. x-ai/grok-4.6unstated69.33117.62
  18. openai/gpt-6-solmax69.28124.00
  19. google/gemini-3.5-flashhigh69.10111.12
  20. meta/muse-spark-1.2xhigh68.73117.04
  21. openai/gpt-6.1-solxhigh68.17124.64
  22. google/gemini-3.5-flash-litehigh68.0299.97
  23. qwen3.8-maxunstated · not in the catalog67.35118.08
  24. deepseek/deepseek-v4.1-flashmax67.07116.49
  25. muse-wonder-1.0max · not in the catalog67.05120.86
  26. qwen/qwen3.8-27bunstated66.70112.72
  27. smaug-agenticunstated · not in the catalog66.62116.30
  28. moonshotai/kimi-k3unstated66.37116.54
  29. openai/gpt-5.5xhigh66.32120.29
  30. mistral-large-4high · not in the catalog66.18109.81
  31. z-ai/glm-5.3unstated65.85112.92
  32. meta/muse-spark-1.1xhigh65.70114.21
  33. claude-opus-4-7xhigh · not in the catalog65.50113.14
  34. smaug-miniunstated · not in the catalog65.38114.73
  35. deepseek/deepseek-v4-flash-vision-expunstated65.07116.36
  36. qwen/qwen3.7-maxunstated64.08111.06
  37. smaug-flashunstated · not in the catalog63.13116.63
  38. claude-opus-5-5xhigh · not in the catalog63125.14
  39. claude-sonnet-4-6-thinking-automedium · not in the catalog62.93114.06
  40. claude-haiku-5-5xhigh · not in the catalog62.78112.88
  41. openai/gpt-5.4-nanoxhigh62.75110.30
  42. x-ai/grok-build-0.1unstated62.60106.25
  43. claude-opus-4-8max · not in the catalog62116.89
  44. anthropic/claude-opus-5max61.58122.24
  45. deepseek/deepseek-v4-pro-0813unstated61.57118.60
  46. openai/gpt-5.6-terramax61.43119.24
  47. kimi-k2.6-thinkingunstated · not in the catalog61.42107.26
  48. anthropic/claude-sonnet-5xhigh60.65113.50
  49. openai/gpt-5.2-codexunstated60.57110.02
  50. thinkingmachines/inklingxhigh60.50107.98
  51. claude-opus-4-6-thinking-autohigh · not in the catalog59.15113.04
  52. openai/gpt-5.6-lunamax58.67114.95
  53. claude-opus-5-5max · not in the catalog58.67128.09
  54. deepseek/deepseek-v4-flash-0731unstated58.37113.47
  55. x-ai/grok-4.3unstated57.60103.07
  56. minimax/minimax-m3unstated56.62104.58
  57. deepseek/deepseek-v4-prounstated55.93111.64
  58. z-ai/glm-5.2unstated55.67109.40
  59. openai/gpt-6-lunamax55.43113.99
  60. claude-opus-4-5-20251101-thinking-64khigh · not in the catalog54.95110.65
  61. ox-alphamax · not in the catalog54.48106.05
  62. gpt-5.2-2025-12-11high · not in the catalog54.08110.74
  63. openai/gpt-5.4-minixhigh54.07104.22
  64. deepseek/deepseek-v4-flashunstated54.05102.96
  65. nemotron-3.5-lightning-30b-a3bunstated · not in the catalog52.6887.31
  66. qwen/qwen3.6-plusunstated51.57106.49
  67. claude-sonnet-5-5max · not in the catalog50.85122.13
  68. qwen/qwen3.6-27bunstated50.73103.72
  69. claude-haiku-5-5max · not in the catalog50.25113.88
  70. moonshotai/kimi-k2.7-codeunstated49.75107.73
  71. z-ai/glm-5.3-flashunstated46.95108.42
connectionsLiveBench-0.62 · 2.14 · 71 runs

71 runs scored on it, 71 of them ranked, best score first, in the publisher's own unit. A ranked run is a door to its row.

  1. deepseek/deepseek-v4-pro-0813unstated100118.60
  2. deepseek/deepseek-v4.1-flashmax100116.49
  3. google/gemini-3.1-pro-previewhigh100113.89
  4. google/gemini-3.5-flashhigh100111.12
  5. google/gemini-3.6-flashhigh100110.95
  6. google/gemini-3.7-flashhigh100116.01
  7. google/gemini-3.8-flashhigh100114.21
  8. meta/muse-spark-1.2xhigh100117.04
  9. moonshotai/kimi-k3unstated100116.54
  10. openai/gpt-5.4xhigh100119.02
  11. openai/gpt-5.5xhigh100120.29
  12. openai/gpt-5.6-solmax100123.35
  13. openai/gpt-6-astramax100132.41
  14. openai/gpt-6-lunamax100113.99
  15. openai/gpt-6-solmax100124.00
  16. openai/gpt-6.1-solmax100130.00
  17. openai/gpt-6.1-solxhigh100124.64
  18. smaug-agenticunstated · not in the catalog100116.30
  19. x-ai/grok-4.6unstated100117.62
  20. anthropic/claude-fable-5max99.33122.58
  21. anthropic/claude-opus-5max99.33122.24
  22. deepseek/deepseek-v4-flash-vision-expunstated99.33116.36
  23. claude-fable-5-1max · not in the catalog99.33125.12
  24. claude-opus-4-5-20251101-thinking-64khigh · not in the catalog99.33110.65
  25. claude-opus-4-6-thinking-autohigh · not in the catalog99.33113.04
  26. claude-opus-4-8max · not in the catalog99.33116.89
  27. claude-opus-5-5max · not in the catalog99.33128.09
  28. claude-opus-5-5xhigh · not in the catalog99.33125.14
  29. claude-sonnet-4-6-thinking-automedium · not in the catalog99.33114.06
  30. claude-sonnet-5-5max · not in the catalog99.33122.13
  31. smaug-flashunstated · not in the catalog99.33116.63
  32. gpt-5.2-2025-12-11high · not in the catalog99110.74
  33. openai/gpt-5.4-minixhigh98.98104.22
  34. claude-sonnet-5-5xhigh · not in the catalog98.50119.88
  35. deepseek/deepseek-v4-prounstated98111.64
  36. meta/muse-spark-1.1xhigh98114.21
  37. moonshotai/kimi-k2.7-codeunstated98107.73
  38. x-ai/grok-4.5unstated98114.74
  39. x-ai/grok-4.7xhigh98113.32
  40. deepseek/deepseek-v4-flash-0731unstated97.33113.47
  41. openai/gpt-5.6-lunamax96.50114.95
  42. qwen/qwen3.7-maxunstated96.50111.06
  43. minimax/minimax-m3unstated96.33104.58
  44. claude-haiku-5-5max · not in the catalog96113.88
  45. muse-wonder-1.0max · not in the catalog96120.86
  46. anthropic/claude-sonnet-5xhigh95.50113.50
  47. z-ai/glm-5.3unstated95.33112.92
  48. openai/gpt-5.2-codexunstated95110.02
  49. qwen3.8-maxunstated · not in the catalog94.50118.08
  50. openai/gpt-5.4-nanoxhigh94.39110.30
  51. meta/muse-spark-1.3xhigh94116.79
  52. x-ai/grok-4.3unstated94103.07
  53. z-ai/glm-5.2unstated94109.40
  54. claude-haiku-5-5xhigh · not in the catalog93.83112.88
  55. z-ai/glm-5.3-flashunstated93.67108.42
  56. openai/gpt-5.6-terramax93119.24
  57. claude-opus-4-7xhigh · not in the catalog92.33113.14
  58. google/gemini-3.5-flash-litehigh9299.97
  59. smaug-miniunstated · not in the catalog91.67114.73
  60. thinkingmachines/inklingxhigh91.17107.98
  61. qwen/qwen3.6-plusunstated90.50106.49
  62. qwen/qwen3.8-27bunstated90.50112.72
  63. qwen3.8-flash-nextunstated · not in the catalog90.17113.12
  64. deepseek/deepseek-v4-flashunstated89.50102.96
  65. kimi-k2.6-thinkingunstated · not in the catalog89.33107.26
  66. nvidia/nemotron-3-ultra-550b-a55bunstated86.67105.72
  67. x-ai/grok-build-0.1unstated84106.25
  68. qwen/qwen3.6-27bunstated77.17103.72
  69. ox-alphamax · not in the catalog71.33106.05
  70. mistral-large-4high · not in the catalog48109.81
  71. nemotron-3.5-lightning-30b-a3bunstated · not in the catalog3487.31
theory_of_mindLiveBench-0.80 · 0.75 · 71 runs

71 runs scored on it, 71 of them ranked, best score first, in the publisher's own unit. A ranked run is a door to its row.

  1. openai/gpt-5.4xhigh88.46119.02
  2. z-ai/glm-5.3unstated88.46112.92
  3. deepseek/deepseek-v4-flash-0731unstated86.54113.47
  4. openai/gpt-5.6-terramax86.54119.24
  5. openai/gpt-6.1-solmax86.54130.00
  6. openai/gpt-6.1-solxhigh86.54124.64
  7. claude-haiku-5-5max · not in the catalog86.54113.88
  8. claude-sonnet-5-5max · not in the catalog86.54122.13
  9. muse-wonder-1.0max · not in the catalog86.54120.86
  10. x-ai/grok-4.6unstated86.54117.62
  11. anthropic/claude-fable-5max84.61122.58
  12. deepseek/deepseek-v4-pro-0813unstated84.61118.60
  13. meta/muse-spark-1.3xhigh84.61116.79
  14. openai/gpt-5.5xhigh84.61120.29
  15. openai/gpt-5.6-solmax84.61123.35
  16. openai/gpt-6-astramax84.61132.41
  17. openai/gpt-6-solmax84.61124.00
  18. claude-opus-5-5max · not in the catalog84.61128.09
  19. claude-opus-5-5xhigh · not in the catalog84.61125.14
  20. x-ai/grok-4.7xhigh84.61113.32
  21. google/gemini-3.7-flashhigh82.69116.01
  22. moonshotai/kimi-k3unstated82.69116.54
  23. claude-opus-4-6-thinking-autohigh · not in the catalog82.69113.04
  24. x-ai/grok-4.5unstated82.69114.74
  25. anthropic/claude-sonnet-5xhigh80.77113.50
  26. deepseek/deepseek-v4-prounstated80.77111.64
  27. deepseek/deepseek-v4.1-flashmax80.77116.49
  28. google/gemini-3.1-pro-previewhigh80.77113.89
  29. google/gemini-3.5-flashhigh80.77111.12
  30. meta/muse-spark-1.2xhigh80.77117.04
  31. openai/gpt-5.4-nanoxhigh80.77110.30
  32. claude-fable-5-1max · not in the catalog80.77125.12
  33. claude-opus-4-7xhigh · not in the catalog80.77113.14
  34. claude-opus-4-8max · not in the catalog80.77116.89
  35. mistral-large-4high · not in the catalog80.77109.81
  36. qwen3.8-flash-nextunstated · not in the catalog80.77113.12
  37. anthropic/claude-opus-5max78.85122.24
  38. deepseek/deepseek-v4-flash-vision-expunstated78.85116.36
  39. google/gemini-3.6-flashhigh78.85110.95
  40. openai/gpt-5.2-codexunstated78.85110.02
  41. qwen/qwen3.7-maxunstated78.85111.06
  42. claude-opus-4-5-20251101-thinking-64khigh · not in the catalog78.85110.65
  43. gpt-5.2-2025-12-11high · not in the catalog78.85110.74
  44. ox-alphamax · not in the catalog78.85106.05
  45. qwen3.8-maxunstated · not in the catalog78.85118.08
  46. smaug-agenticunstated · not in the catalog78.85116.30
  47. google/gemini-3.8-flashhigh76.92114.21
  48. meta/muse-spark-1.1xhigh76.92114.21
  49. minimax/minimax-m3unstated76.92104.58
  50. openai/gpt-5.4-minixhigh76.92104.22
  51. claude-haiku-5-5xhigh · not in the catalog76.92112.88
  52. smaug-flashunstated · not in the catalog76.92116.63
  53. kimi-k2.6-thinkingunstated · not in the catalog75107.26
  54. z-ai/glm-5.2unstated75109.40
  55. deepseek/deepseek-v4-flashunstated73.08102.96
  56. openai/gpt-5.6-lunamax73.08114.95
  57. openai/gpt-6-lunamax73.08113.99
  58. claude-sonnet-4-6-thinking-automedium · not in the catalog73.08114.06
  59. z-ai/glm-5.3-flashunstated73.08108.42
  60. moonshotai/kimi-k2.7-codeunstated69.23107.73
  61. claude-sonnet-5-5xhigh · not in the catalog69.23119.88
  62. smaug-miniunstated · not in the catalog69.23114.73
  63. x-ai/grok-build-0.1unstated69.23106.25
  64. qwen/qwen3.6-plusunstated67.31106.49
  65. qwen/qwen3.6-27bunstated65.39103.72
  66. thinkingmachines/inklingxhigh65.39107.98
  67. nvidia/nemotron-3-ultra-550b-a55bunstated61.54105.72
  68. x-ai/grok-4.3unstated61.54103.07
  69. qwen/qwen3.8-27bunstated59.62112.72
  70. google/gemini-3.5-flash-litehigh5099.97
  71. nemotron-3.5-lightning-30b-a3bunstated · not in the catalog44.2387.31
code_completionLiveBench-0.87 · 0.68 · 71 runs

71 runs scored on it, 71 of them ranked, best score first, in the publisher's own unit. A ranked run is a door to its row.

  1. openai/gpt-5.2-codexunstated86.96110.02
  2. openai/gpt-5.6-lunamax86.96114.95
  3. claude-opus-5-5max · not in the catalog86.96128.09
  4. claude-opus-5-5xhigh · not in the catalog86.96125.14
  5. claude-sonnet-5-5max · not in the catalog86.96122.13
  6. openai/gpt-5.6-solmax84.78123.35
  7. claude-opus-4-8max · not in the catalog84.78116.89
  8. claude-sonnet-5-5xhigh · not in the catalog84.78119.88
  9. anthropic/claude-opus-5max82.61122.24
  10. deepseek/deepseek-v4.1-flashmax82.61116.49
  11. moonshotai/kimi-k3unstated82.61116.54
  12. openai/gpt-5.5xhigh82.61120.29
  13. openai/gpt-6.1-solxhigh82.61124.64
  14. claude-fable-5-1max · not in the catalog82.61125.12
  15. anthropic/claude-fable-5max80.44122.58
  16. meta/muse-spark-1.2xhigh80.44117.04
  17. meta/muse-spark-1.3xhigh80.44116.79
  18. openai/gpt-5.4xhigh80.44119.02
  19. openai/gpt-5.6-terramax80.44119.24
  20. openai/gpt-6-astramax80.44132.41
  21. openai/gpt-6-lunamax80.44113.99
  22. openai/gpt-6-solmax80.44124.00
  23. openai/gpt-6.1-solmax80.44130.00
  24. claude-opus-4-5-20251101-thinking-64khigh · not in the catalog80.44110.65
  25. smaug-agenticunstated · not in the catalog80.44116.30
  26. smaug-miniunstated · not in the catalog80.44114.73
  27. z-ai/glm-5.2unstated80.44109.40
  28. z-ai/glm-5.3unstated80.44112.92
  29. z-ai/glm-5.3-flashunstated80.44108.42
  30. anthropic/claude-sonnet-5xhigh78.26113.50
  31. deepseek/deepseek-v4-pro-0813unstated78.26118.60
  32. google/gemini-3.1-pro-previewhigh78.26113.89
  33. google/gemini-3.6-flashhigh78.26110.95
  34. meta/muse-spark-1.1xhigh78.26114.21
  35. claude-haiku-5-5max · not in the catalog78.26113.88
  36. claude-opus-4-7xhigh · not in the catalog78.26113.14
  37. claude-sonnet-4-6-thinking-automedium · not in the catalog78.26114.06
  38. kimi-k2.6-thinkingunstated · not in the catalog78.26107.26
  39. mistral-large-4high · not in the catalog78.26109.81
  40. muse-wonder-1.0max · not in the catalog78.26120.86
  41. ox-alphamax · not in the catalog78.26106.05
  42. x-ai/grok-4.7xhigh78.26113.32
  43. google/gemini-3.5-flashhigh76.09111.12
  44. google/gemini-3.5-flash-litehigh76.0999.97
  45. google/gemini-3.7-flashhigh76.09116.01
  46. moonshotai/kimi-k2.7-codeunstated76.09107.73
  47. qwen/qwen3.6-plusunstated76.09106.49
  48. claude-opus-4-6-thinking-autohigh · not in the catalog76.09113.04
  49. gpt-5.2-2025-12-11high · not in the catalog76.09110.74
  50. qwen3.8-flash-nextunstated · not in the catalog76.09113.12
  51. x-ai/grok-4.6unstated76.09117.62
  52. openai/gpt-5.4-minixhigh75.56104.22
  53. deepseek/deepseek-v4-flash-0731unstated73.91113.47
  54. qwen/qwen3.8-27bunstated73.91112.72
  55. claude-haiku-5-5xhigh · not in the catalog73.91112.88
  56. qwen3.8-maxunstated · not in the catalog73.91118.08
  57. smaug-flashunstated · not in the catalog73.91116.63
  58. google/gemini-3.8-flashhigh71.74114.21
  59. qwen/qwen3.6-27bunstated71.74103.72
  60. deepseek/deepseek-v4-prounstated69.56111.64
  61. nvidia/nemotron-3-ultra-550b-a55bunstated69.56105.72
  62. qwen/qwen3.7-maxunstated69.56111.06
  63. x-ai/grok-4.5unstated69.56114.74
  64. deepseek/deepseek-v4-flash-vision-expunstated67.39116.36
  65. minimax/minimax-m3unstated67.39104.58
  66. openai/gpt-5.4-nanoxhigh67.39110.30
  67. thinkingmachines/inklingxhigh67.39107.98
  68. x-ai/grok-build-0.1unstated67.39106.25
  69. deepseek/deepseek-v4-flashunstated65.22102.96
  70. x-ai/grok-4.3unstated65.22103.07
  71. nemotron-3.5-lightning-30b-a3bunstated · not in the catalog23.9187.31
paraphraseLiveBench-0.94 · 0.36 · 71 runs

71 runs scored on it, 71 of them ranked, best score first, in the publisher's own unit. A ranked run is a door to its row.

  1. google/gemini-3.8-flashhigh80114.21
  2. google/gemini-3.1-pro-previewhigh79.87113.89
  3. qwen3.8-flash-nextunstated · not in the catalog79.47113.12
  4. meta/muse-spark-1.3xhigh78.62116.79
  5. openai/gpt-6-astramax78.25132.41
  6. google/gemini-3.7-flashhigh78.07116.01
  7. x-ai/grok-4.7xhigh78.05113.32
  8. anthropic/claude-fable-5max77.65122.58
  9. nvidia/nemotron-3-ultra-550b-a55bunstated77.38105.72
  10. smaug-miniunstated · not in the catalog76.18114.73
  11. google/gemini-3.5-flashhigh75.52111.12
  12. qwen/qwen3.8-27bunstated74.90112.72
  13. moonshotai/kimi-k3unstated74.37116.54
  14. google/gemini-3.6-flashhigh74.32110.95
  15. meta/muse-spark-1.2xhigh74.30117.04
  16. muse-wonder-1.0max · not in the catalog74.07120.86
  17. qwen3.8-maxunstated · not in the catalog73.32118.08
  18. deepseek/deepseek-v4-flash-vision-expunstated72.83116.36
  19. openai/gpt-6.1-solmax72.58130.00
  20. qwen/qwen3.7-maxunstated72111.06
  21. x-ai/grok-4.6unstated71.78117.62
  22. openai/gpt-5.5xhigh71.73120.29
  23. openai/gpt-5.6-solmax71.52123.35
  24. claude-fable-5-1max · not in the catalog71.52125.12
  25. openai/gpt-6.1-solxhigh71.03124.64
  26. thinkingmachines/inklingxhigh70.85107.98
  27. deepseek/deepseek-v4.1-flashmax70.73116.49
  28. openai/gpt-6-solmax70.08124.00
  29. meta/muse-spark-1.1xhigh69.40114.21
  30. x-ai/grok-4.5unstated69.22114.74
  31. deepseek/deepseek-v4-pro-0813unstated68.63118.60
  32. smaug-agenticunstated · not in the catalog68.63116.30
  33. claude-opus-4-8max · not in the catalog67.87116.89
  34. openai/gpt-5.2-codexunstated67.05110.02
  35. openai/gpt-5.4-nanoxhigh66.65110.30
  36. claude-opus-4-7xhigh · not in the catalog65.77113.14
  37. anthropic/claude-opus-5max65.73122.24
  38. claude-opus-4-5-20251101-thinking-64khigh · not in the catalog65.67110.65
  39. smaug-flashunstated · not in the catalog65.57116.63
  40. google/gemini-3.5-flash-litehigh6599.97
  41. claude-opus-5-5xhigh · not in the catalog64.68125.14
  42. z-ai/glm-5.3unstated64.68112.92
  43. x-ai/grok-4.3unstated64.38103.07
  44. claude-opus-5-5max · not in the catalog64.27128.09
  45. gpt-5.2-2025-12-11high · not in the catalog64.10110.74
  46. mistral-large-4high · not in the catalog63.97109.81
  47. openai/gpt-5.4xhigh63.43119.02
  48. claude-opus-4-6-thinking-autohigh · not in the catalog62.82113.04
  49. claude-haiku-5-5xhigh · not in the catalog62.50112.88
  50. deepseek/deepseek-v4-flashunstated62.38102.96
  51. claude-sonnet-5-5xhigh · not in the catalog62.28119.88
  52. z-ai/glm-5.2unstated62.25109.40
  53. deepseek/deepseek-v4-flash-0731unstated61.70113.47
  54. kimi-k2.6-thinkingunstated · not in the catalog61.63107.26
  55. anthropic/claude-sonnet-5xhigh61.25113.50
  56. qwen/qwen3.6-plusunstated60.62106.49
  57. claude-sonnet-4-6-thinking-automedium · not in the catalog59.40114.06
  58. openai/gpt-5.4-minixhigh58.88104.22
  59. x-ai/grok-build-0.1unstated58.38106.25
  60. ox-alphamax · not in the catalog57.47106.05
  61. nemotron-3.5-lightning-30b-a3bunstated · not in the catalog57.3287.31
  62. openai/gpt-5.6-terramax57.03119.24
  63. deepseek/deepseek-v4-prounstated56.22111.64
  64. minimax/minimax-m3unstated55.93104.58
  65. claude-haiku-5-5max · not in the catalog50.22113.88
  66. openai/gpt-6-lunamax49.70113.99
  67. qwen/qwen3.6-27bunstated49.43103.72
  68. moonshotai/kimi-k2.7-codeunstated48.53107.73
  69. claude-sonnet-5-5max · not in the catalog48.22122.13
  70. z-ai/glm-5.3-flashunstated47.98108.42
  71. openai/gpt-5.6-lunamax47.82114.95
summarizeLiveBench-1.02 · 0.44 · 71 runs

71 runs scored on it, 71 of them ranked, best score first, in the publisher's own unit. A ranked run is a door to its row.

  1. google/gemini-3.1-pro-previewhigh88.23113.89
  2. google/gemini-3.8-flashhigh87.50114.21
  3. google/gemini-3.7-flashhigh84.77116.01
  4. qwen/qwen3.7-maxunstated83.80111.06
  5. meta/muse-spark-1.3xhigh83.40116.79
  6. google/gemini-3.5-flashhigh82.58111.12
  7. anthropic/claude-fable-5max81.70122.58
  8. openai/gpt-6.1-solmax81.25130.00
  9. meta/muse-spark-1.2xhigh80.62117.04
  10. openai/gpt-6-astramax79.55132.41
  11. qwen3.8-maxunstated · not in the catalog79.15118.08
  12. smaug-flashunstated · not in the catalog78.35116.63
  13. x-ai/grok-4.7xhigh78.17113.32
  14. claude-opus-4-8max · not in the catalog77.67116.89
  15. qwen3.8-flash-nextunstated · not in the catalog77.35113.12
  16. muse-wonder-1.0max · not in the catalog76.83120.86
  17. smaug-miniunstated · not in the catalog76.10114.73
  18. qwen/qwen3.8-27bunstated75.93112.72
  19. google/gemini-3.6-flashhigh75.85110.95
  20. openai/gpt-6.1-solxhigh75.53124.64
  21. nvidia/nemotron-3-ultra-550b-a55bunstated74.88105.72
  22. thinkingmachines/inklingxhigh74.85107.98
  23. z-ai/glm-5.3unstated74.55112.92
  24. meta/muse-spark-1.1xhigh74.30114.21
  25. openai/gpt-5.6-terramax73.17119.24
  26. x-ai/grok-4.5unstated73.15114.74
  27. openai/gpt-5.5xhigh72.32120.29
  28. claude-fable-5-1max · not in the catalog72.17125.12
  29. deepseek/deepseek-v4-flash-vision-expunstated72.10116.36
  30. smaug-agenticunstated · not in the catalog72.05116.30
  31. openai/gpt-5.4-nanoxhigh71.77110.30
  32. deepseek/deepseek-v4-flash-0731unstated71.50113.47
  33. anthropic/claude-sonnet-5xhigh71.22113.50
  34. claude-sonnet-5-5xhigh · not in the catalog70.33119.88
  35. deepseek/deepseek-v4.1-flashmax69.65116.49
  36. deepseek/deepseek-v4-prounstated69.50111.64
  37. openai/gpt-5.6-solmax69.43123.35
  38. moonshotai/kimi-k3unstated69.35116.54
  39. claude-opus-5-5xhigh · not in the catalog69.33125.14
  40. claude-opus-5-5max · not in the catalog69.10128.09
  41. deepseek/deepseek-v4-flashunstated68.85102.96
  42. google/gemini-3.5-flash-litehigh68.4799.97
  43. openai/gpt-5.4xhigh68.42119.02
  44. z-ai/glm-5.2unstated68.37109.40
  45. x-ai/grok-4.6unstated68.08117.62
  46. openai/gpt-6-solmax68124.00
  47. kimi-k2.6-thinkingunstated · not in the catalog67.50107.26
  48. x-ai/grok-build-0.1unstated67.37106.25
  49. claude-haiku-5-5xhigh · not in the catalog66.98112.88
  50. anthropic/claude-opus-5max66.43122.24
  51. claude-opus-4-7xhigh · not in the catalog66.28113.14
  52. deepseek/deepseek-v4-pro-0813unstated65.67118.60
  53. claude-opus-4-6-thinking-autohigh · not in the catalog65.15113.04
  54. openai/gpt-5.6-lunamax64.93114.95
  55. qwen/qwen3.6-plusunstated64.32106.49
  56. claude-opus-4-5-20251101-thinking-64khigh · not in the catalog63.72110.65
  57. openai/gpt-5.2-codexunstated63.38110.02
  58. gpt-5.2-2025-12-11high · not in the catalog63.20110.74
  59. claude-sonnet-4-6-thinking-automedium · not in the catalog61.65114.06
  60. mistral-large-4high · not in the catalog61.63109.81
  61. openai/gpt-5.4-minixhigh59.63104.22
  62. x-ai/grok-4.3unstated58.42103.07
  63. moonshotai/kimi-k2.7-codeunstated58.32107.73
  64. ox-alphamax · not in the catalog58.18106.05
  65. claude-sonnet-5-5max · not in the catalog58.17122.13
  66. z-ai/glm-5.3-flashunstated56.47108.42
  67. openai/gpt-6-lunamax55.32113.99
  68. minimax/minimax-m3unstated53.93104.58
  69. claude-haiku-5-5max · not in the catalog53.63113.88
  70. qwen/qwen3.6-27bunstated52.62103.72
  71. nemotron-3.5-lightning-30b-a3bunstated · not in the catalog50.4287.31
SWE-Bench verifiedEpoch AI Benchmarking Hub-1.06 · 0.66 · 33 runs

33 runs scored on it, 29 of them ranked, best score first, in the publisher's own unit. A ranked run is a door to its row.

  1. claude-opus-4-7max · not in the catalog0.83113.03
  2. gpt-5.5-pre-releasexhigh · not in the catalog0.81116.86
  3. google/gemini-3.5-flashhigh0.79111.12
  4. claude-opus-4-6unstated · not in the catalog0.79110.08
  5. z-ai/glm-5.2max0.79110.33
  6. deepseek/deepseek-v4-promax0.78107.02
  7. qwen/qwen3.7-maxunstated0.77111.06
  8. gpt-5.4-2026-03-05high · not in the catalog0.77115.98
  9. moonshotai/kimi-k2.6unstated0.77110.82
  10. claude-opus-4-5-20251101unstated · not in the catalog0.7799.92
  11. qwen3.6-max-previewunstated · not in the catalog0.77106.75
  12. google/gemini-3.1-pro-preview-customtoolsunstated0.76set aside
  13. google/gemini-3-flash-previewunstated0.75108.16
  14. claude-sonnet-4-6unstated · not in the catalog0.75set aside
  15. openai/gpt-5.3-codexhigh0.75set aside
  16. z-ai/glm-5.1unstated0.74109.27
  17. moonshotai/kimi-k2.5unstated0.74set aside
  18. gpt-5.2-2025-12-11high · not in the catalog0.74110.74
  19. gpt-5-2025-08-07high · not in the catalog0.74108.61
  20. claude-opus-4-1-20250805unstated · not in the catalog0.7393.81
  21. gemini-3-pro-previewunstated · not in the catalog0.73110.74
  22. z-ai/glm-5unstated0.7299.96
  23. gpt-5-2025-08-07medium · not in the catalog0.71108.12
  24. claude-sonnet-4-5-20250929unstated · not in the catalog0.7193.21
  25. claude-opus-4-20250514unstated · not in the catalog0.7192.48
  26. gpt-5.1-2025-11-13high · not in the catalog0.68109.94
  27. gpt-5-mini-2025-08-07medium · not in the catalog0.65103.83
  28. o3-2025-04-16medium · not in the catalog0.62101.11
  29. claude-3-7-sonnet-20250219unstated · not in the catalog0.6187.22
  30. qwen/qwen3.6-plusunstated0.58106.49
  31. google/gemini-2.5-prounstated0.58103.73
  32. gpt-4.1-2025-04-14unstated · not in the catalog0.4991.64
  33. openai/gpt-4o-2024-11-20unstated0.3180.37
GPQA diamondEpoch AI Benchmarking Hub-1.12 · 1.11 · 342 runs

342 runs scored on it, 266 of them ranked, best score first, in the publisher's own unit. A ranked run is a door to its row.

  1. gpt-6.2-astramax · not in the catalog0.97135.84
  2. google/gemini-4-hydrogenxhigh0.97125.83
  3. google/gemini-4-carbonhigh0.97131.68
  4. google/gemini-4-argonhigh0.96124.90
  5. gemini-4-neonxhigh · not in the catalog0.96134.54
  6. claude-fable-5-2-fallbackmax · not in the catalog0.96set aside
  7. openai/gpt-6-astramax0.96132.41
  8. claude-sonnet-5-5max · not in the catalog0.96122.13
  9. google/gemini-3.8-flashhigh0.95114.21
  10. openai/gpt-6.1-solmax0.95130.00
  11. google/gemini-3.7-flashhigh0.95116.01
  12. gpt-5.4-pro-2026-03-05xhigh · not in the catalog0.95117.92
  13. google/gemini-3.1-pro-previewhigh0.94113.89
  14. openai/gpt-6-solmax0.94124.00
  15. openai/gpt-6.1-terramax0.94130.85
  16. kimi-k3.1-pro-togethermax · not in the catalog0.94118.88
  17. google/gemini-3.6-flashhigh0.94110.95
  18. google/gemini-3.1-pro-previewunstated0.94111.66
  19. claude-opus-5-5-fallbackmax · not in the catalog0.94set aside
  20. gpt-5.5-pre-releasexhigh · not in the catalog0.94116.86
  21. x-ai/grok-4.6high0.94114.02
  22. gpt-5.5-pro-pre-releasexhigh · not in the catalog0.94117.38
  23. anthropic/claude-opus-5max0.94122.24
  24. claude-fable-5-2max · not in the catalog0.94132.06
  25. claude-fable-5-fallbackmax · not in the catalog0.94set aside
  26. openai/gpt-5.6-solmax0.93123.35
  27. x-ai/grok-4.5high0.93111.55
  28. openai/gpt-5.6-terramax0.93119.24
  29. gpt-5.4-2026-03-05xhigh · not in the catalog0.93116.23
  30. deepseek/deepseek-v4.1-flash-1017max0.93116.25
  31. x-ai/grok-4.6xhigh0.93114.39
  32. moonshotai/kimi-k3max0.93114.75
  33. doubao-seed-evolvinghigh · not in the catalog0.93114.76
  34. anthropic/claude-opus-5unstated0.93115.94
  35. google/gemini-3.5-flashhigh0.93111.12
  36. x-ai/grok-4.7xhigh0.93113.32
  37. qwen3.8-maxxhigh · not in the catalog0.93116.39
  38. gemini-3-pro-previewunstated · not in the catalog0.93110.74
  39. qwen/qwen3.8-max-0902xhigh0.92113.51
  40. moonshotai/kimi-k3high0.92112.20
  41. z-ai/glm-5.2max0.92110.33
  42. deepseek/deepseek-v4-pro-0813max0.92113.60
  43. openai/gpt-5.6-lunamax0.92114.95
  44. gpt-5.2-2025-12-11xhigh · not in the catalog0.91113.39
  45. deepseek/deepseek-v4-flash-0731max0.91111.14
  46. claude-opus-4-8max · not in the catalog0.91116.89
  47. deepseek/deepseek-v4-prohigh0.91108.20
  48. minimax/minimax-m3unstated0.91104.58
  49. qwen/qwen3.7-maxunstated0.91111.06
  50. z-ai/glm-5.3max0.91112.54
  51. moonshotai/kimi-k2.6unstated0.91110.82
  52. openai/gpt-5.5low0.91107.86
  53. claude-opus-5-5max · not in the catalog0.91128.09
  54. anthropic/claude-sonnet-5xhigh0.91113.50
  55. claude-opus-4-6-32kunstated · not in the catalog0.91111.03
  56. openai/gpt-6-lunamax0.90113.99
  57. claude-opus-4-7xhigh · not in the catalog0.90113.14
  58. mistral-large-4-0-osshigh · not in the catalog0.90110.78
  59. z-ai/glm-5.3-flashmax0.90108.45
  60. openai/gpt-5.6-sollow0.90110.85
  61. gpt-5.4-2026-03-05high · not in the catalog0.90115.98
  62. z-ai/glm-5.1unstated0.90109.27
  63. deepseek/deepseek-v4.1-flashmax0.90116.49
  64. muse-sparkunstated · not in the catalog0.90110.41
  65. deepseek/deepseek-v4-promax0.90107.02
  66. claude-haiku-5-5max · not in the catalog0.90113.88
  67. doubao-seed-2.1-turbo-260628high · not in the catalog0.90108.84
  68. google/gemini-3-flash-previewhigh0.89113.70
  69. doubao-seed-2.1-pro-260628high · not in the catalog0.89109.61
  70. grok-4.20-0309-reasoningunstated · not in the catalog0.89108.33
  71. google/gemini-3.5-flashlow0.89110.83
  72. gpt-5.4-2026-03-05medium · not in the catalog0.89112.04
  73. x-ai/grok-4.3high0.89107.39
  74. claude-opus-4-6-64kunstated · not in the catalog0.89111.92
  75. muse-spark-open-816b-a42bxhigh · not in the catalog0.89113.92
  76. thinkingmachines/inkling-smallxhigh0.89106.54
  77. qwen/qwen3.6-plusunstated0.88106.49
  78. claude-opus-4-6max · not in the catalog0.88111.69
  79. claude-opus-4-8low · not in the catalog0.88111.54
  80. thinkingmachines/inklingxhigh0.88107.98
  81. doubao-seed-2.0-pro-260215high · not in the catalog0.88108.12
  82. gpt-5.2-2025-12-11high · not in the catalog0.88110.74
  83. doubao-seed-2.0-lite-260428high · not in the catalog0.88106.42
  84. mistralai/mistral-large-4-0high0.88110.63
  85. anthropic/claude-opus-5low0.88109.13
  86. moonshotai/kimi-k2.7-codeunstated0.88107.73
  87. qwen/qwen3.7-plusunstated0.88107.80
  88. gpt-5.2-2025-12-11medium · not in the catalog0.88108.75
  89. z-ai/glm-5.2low0.88105.42
  90. z-ai/glm-5unstated0.8899.96
  91. gpt-5.1-2025-11-13high · not in the catalog0.88109.94
  92. fireworks/kimi-k2p5unstated · not in the catalog0.88107.32
  93. openai/gpt-5.6-terralow0.87106.93
  94. claude-sonnet-4-6-32kunstated · not in the catalog0.87set aside
  95. qwen3.6-max-previewunstated · not in the catalog0.87106.75
  96. grok-4-0709unstated · not in the catalog0.87104.16
  97. gpt-5.4-mini-2026-03-17xhigh · not in the catalog0.87106.91
  98. google/gemini-3.5-flashminimal0.86104.41
  99. google/gemini-3.6-flashlow0.86107.80
  100. qwen/qwen3.5-397b-a17bnone0.86103.55
  101. claude-opus-4-7max · not in the catalog0.86113.03
  102. gpt-5-2025-08-07high · not in the catalog0.86108.61
  103. claude-opus-4-5-20251101-32kunstated · not in the catalog0.86104.05
  104. anthropic/claude-fable-5max0.86122.58
  105. google/gemini-3.6-flashminimal0.86105.55
  106. qwen/qwen3.5-397b-a17bunstated0.86104.40
  107. qwen/qwen3.6-27bunstated0.86103.72
  108. claude-opus-4-5-20251101-16kunstated · not in the catalog0.85104.70
  109. claude-opus-4-8none · not in the catalog0.85104.31
  110. gpt-5-2025-08-07medium · not in the catalog0.85108.12
  111. nemotron-3-ultraunstated · not in the catalog0.85105.62
  112. google/gemini-2.5-prounstated0.85103.73
  113. gpt-5.1-2025-11-13medium · not in the catalog0.85105.41
  114. moonshotai/kimi-k3low0.85100.12
  115. qwen/qwen3.6-27bnone0.85100.32
  116. qwen/qwen3.6-35b-a3bnone0.85100.22
  117. gemini-2.5-pro-preview-06-05unstated · not in the catalog0.85103.27
  118. gpt-5.4-2026-03-05low · not in the catalog0.85104.16
  119. qwen3.5-plusunstated · not in the catalog0.85105.31
  120. kimi-k2-thinking-turbounstated · not in the catalog0.84102.46
  121. qwen/qwen3.6-35b-a3bunstated0.84102.04
  122. gemini-2.5-pro-exp-03-25unstated · not in the catalog0.84set aside
  123. gpt-5.4-mini-2026-03-17high · not in the catalog0.84106.09
  124. qwen/qwen3.5-35b-a3bunstated0.83set aside
  125. deepseek-reasonerunstated · not in the catalog0.83set aside
  126. anthropic/claude-fable-5high0.83119.29
  127. google/gemini-3.5-flash-litehigh0.8399.97
  128. qwen/qwen3.6-flashunstated0.83100.95
  129. claude-sonnet-4-6high · not in the catalog0.83102.30
  130. claude-sonnet-4-6medium · not in the catalog0.83103.01
  131. z-ai/glm-4.7unstated0.83104.07
  132. google/gemini-3-flash-previewunstated0.83108.16
  133. openai/gpt-5.6-solnone0.83100.98
  134. gpt-5.2-2025-12-11low · not in the catalog0.83104.89
  135. gpt-5.5-instantunstated · not in the catalog0.8399.89
  136. openai/gpt-5.6-lunalow0.82101.92
  137. qwen/qwen3.7-flashunstated0.82102.16
  138. claude-sonnet-4-5-20250929-59kunstated · not in the catalog0.82101.26
  139. qwen3.5-flashunstated · not in the catalog0.8299.58
  140. google/gemini-3.1-flash-litehigh0.82102.13
  141. qwen/qwen3.7-plusnone0.82103.17
  142. o3-2025-04-16high · not in the catalog0.82102.96
  143. claude-sonnet-4-5-20250929-32kunstated · not in the catalog0.82101.18
  144. minimax/minimax-m3none0.8190.84
  145. qwen/qwen3.5-35b-a3bnone0.81set aside
  146. qwen/qwen3.7-flashnone0.81100.54
  147. o3-2025-04-16medium · not in the catalog0.81101.11
  148. claude-opus-4-5-20251101unstated · not in the catalog0.8199.92
  149. anthropic/claude-sonnet-5max0.80112.43
  150. qwen/qwen3-235b-a22b-thinking-2507unstated0.80104.10
  151. o3-2025-04-16low · not in the catalog0.8099.37
  152. o4-mini-2025-04-16high · not in the catalog0.80103.35
  153. qwen/qwen3.5-9bunstated0.79set aside
  154. qwen/qwen3.5-9bnone0.79set aside
  155. anthropic/claude-fable-5low0.79110.20
  156. claude-sonnet-4-5-20250929-16kunstated · not in the catalog0.79set aside
  157. claude-sonnet-4-6max · not in the catalog0.79101.17
  158. claude-3-7-sonnet-20250219-64kunstated · not in the catalog0.7995.18
  159. gpt-5.4-nano-2026-03-17high · not in the catalog0.78106.76
  160. claude-sonnet-4-20250514-32kunstated · not in the catalog0.78set aside
  161. claude-sonnet-4-20250514-59kunstated · not in the catalog0.7899.17
  162. o4-mini-2025-04-16medium · not in the catalog0.78101.93
  163. seed-1.6unstated · not in the catalog0.7897.70
  164. openai/gpt-5.5none0.7797.11
  165. openai/gpt-5.6-terranone0.7795.57
  166. claude-opus-4-1-20250805-16kunstated · not in the catalog0.7796.39
  167. o3-mini-2025-01-31high · not in the catalog0.77102.45
  168. claude-3-7-sonnet-20250219-16kunstated · not in the catalog0.7793.20
  169. claude-3-7-sonnet-20250219-32kunstated · not in the catalog0.7794.40
  170. claude-opus-4-1-20250805-27kunstated · not in the catalog0.7797.29
  171. o1-2024-12-17high · not in the catalog0.7798.27
  172. deepseek/deepseek-r1-0528unstated0.7698.81
  173. claude-opus-4-20250514-16kunstated · not in the catalog0.76set aside
  174. grok-3-mini-betalow · not in the catalog0.7694.71
  175. google/gemini-3.5-flash-litelow0.7698.68
  176. google/gemma-4-31b-itminimal0.76set aside
  177. claude-sonnet-4-20250514-16kunstated · not in the catalog0.76set aside
  178. o1-2024-12-17medium · not in the catalog0.7697.81
  179. openai/gpt-oss-120bhigh · not in the catalog0.76set aside
  180. o4-mini-2025-04-16low · not in the catalog0.75100.61
  181. gpt-5-mini-2025-08-07high · not in the catalog0.75104.57
  182. gpt-5.4-2026-03-05none · not in the catalog0.7596.15
  183. grok-3-mini-betahigh · not in the catalog0.7597.03
  184. o3-mini-2025-01-31medium · not in the catalog0.7497.94
  185. google/gemini-3.1-flash-litelow0.7494.94
  186. google/gemini-3.5-flash-liteminimal0.7494.95
  187. o1-2024-12-17low · not in the catalog0.7494.71
  188. google/gemini-3.1-flash-liteminimal0.7493.68
  189. claude-sonnet-4-5-20250929unstated · not in the catalog0.7493.21
  190. deepseek/deepseek-v4-pronone0.7394.28
  191. google/gemma-4-26b-a4b-itminimal0.73set aside
  192. claude-opus-4-1-20250805unstated · not in the catalog0.7393.81
  193. gpt-5.2-2025-12-11none · not in the catalog0.7396.53
  194. qwen3-max-2025-09-23unstated · not in the catalog0.73100.03
  195. gpt-5.4-nano-2026-03-17low · not in the catalog0.7298.40
  196. gpt-5-2025-08-07minimal · not in the catalog0.7295.14
  197. gpt-5-mini-2025-08-07minimal · not in the catalog0.7293.86
  198. gpt-5-mini-2025-08-07medium · not in the catalog0.72103.83
  199. seed-oss-36b-instructunstated · not in the catalog0.72set aside
  200. deepseek/deepseek-chatunstated0.71set aside
  201. claude-haiku-4-5-20251001-32kunstated · not in the catalog0.7196.01
  202. z-ai/glm-5.2none0.7196.22
  203. qwen3-235b-a22bunstated · not in the catalog0.7187.56
  204. qwen3-30b-a3b-thinking-2507unstated · not in the catalog0.70set aside
  205. gpt-5-nano-2025-08-07high · not in the catalog0.69100.45
  206. deepseek-r1unstated · not in the catalog0.6996.08
  207. claude-opus-4-20250514unstated · not in the catalog0.6992.48
  208. gpt-4.5-preview-2025-02-27unstated · not in the catalog0.6990.75
  209. o3-mini-2025-01-31low · not in the catalog0.6891.91
  210. deepseek-v3-0324unstated · not in the catalog0.6890.12
  211. grok-3-betaunstated · not in the catalog0.6894.65
  212. gpt-5-nano-2025-08-07medium · not in the catalog0.6799.03
  213. llama-4-maverick-17b-128e-instruct-fp8unstated · not in the catalog0.6787.21
  214. gpt-4.1-2025-04-14unstated · not in the catalog0.6791.64
  215. claude-sonnet-4-20250514unstated · not in the catalog0.6790.16
  216. gemini-2.5-pro-preview-05-06unstated · not in the catalog0.67102.43
  217. gpt-5.1-2025-11-13none · not in the catalog0.6791.90
  218. claude-3-7-sonnet-20250219unstated · not in the catalog0.6687.22
  219. gpt-4.1-mini-2025-04-14unstated · not in the catalog0.6693.48
  220. qwen/qwen3-32bunstated0.6696.21
  221. gemini-2.0-pro-exp-02-05unstated · not in the catalog0.6690.84
  222. qwq-plusunstated · not in the catalog0.65set aside
  223. qwq-32bunstated · not in the catalog0.6593.18
  224. deepseek-r1-distill-qwen-32bunstated · not in the catalog0.64set aside
  225. gemini-2.0-flash-001unstated · not in the catalog0.6489.75
  226. gpt-5.4-mini-2026-03-17none · not in the catalog0.6490.48
  227. qwen/qwen3-14bunstated0.64set aside
  228. openai/gpt-5.6-lunanone0.6495.93
  229. o1-mini-2024-09-12high · not in the catalog0.6292.53
  230. qwen/qwen3-30b-a3bunstated0.62set aside
  231. openai/gpt-oss-20bmedium0.61set aside
  232. z-ai/glm-4.7-flashunstated0.61set aside
  233. claude-haiku-4-5-20251001unstated · not in the catalog0.6090.99
  234. mistral-medium-2505unstated · not in the catalog0.6089.41
  235. o1-mini-2024-09-12medium · not in the catalog0.6091.51
  236. gpt-5-nano-2025-08-07low · not in the catalog0.5892.74
  237. gemini-1.5-pro-002unstated · not in the catalog0.5786.80
  238. gemini-2.0-flash-thinking-exp-01-21unstated · not in the catalog0.5792.14
  239. qwen3-8bunstated · not in the catalog0.57set aside
  240. deepseek-v3unstated · not in the catalog0.5784.96
  241. qwen-max-2025-01-25unstated · not in the catalog0.5685.11
  242. microsoft/phi-4unstated0.5684.64
  243. magistral-small-2506unstated · not in the catalog0.5688.63
  244. deepseek-r1-distill-llama-70bunstated · not in the catalog0.5693.55
  245. qwen/qwen3-30b-a3b-instruct-2507unstated0.56set aside
  246. gpt-5.4-nano-2026-03-17none · not in the catalog0.5691.33
  247. claude-3-5-sonnet-20241022unstated · not in the catalog0.5585.31
  248. qwen/qwen3-32bnone0.54set aside
  249. claude-3-5-sonnet-20240620unstated · not in the catalog0.5481.59
  250. grok-2-1212unstated · not in the catalog0.5483.89
  251. qwen/qwen3-14bnone0.53set aside
  252. openai/gpt-oss-20blow0.53set aside
  253. qwen3-4bunstated · not in the catalog0.52set aside
  254. llama-4-scout-17b-16e-instructunstated · not in the catalog0.5282.99
  255. mistral-large-2411unstated · not in the catalog0.5181.24
  256. llama-3.1-405b-instructunstated · not in the catalog0.5181.49
  257. qwen/qwen3-30b-a3bnone0.50set aside
  258. o1-preview-2024-09-12unstated · not in the catalog0.5089.08
  259. openai/gpt-4o-2024-08-06unstated0.4982.76
  260. qwen2.5-72b-instructunstated · not in the catalog0.4983.11
  261. mistral-small-3.2-2506unstated · not in the catalog0.49set aside
  262. mistralai/mistral-large-2407unstated0.4980.40
  263. gpt-4.1-nano-2025-04-14unstated · not in the catalog0.4986.22
  264. openai/gpt-4o-2024-05-13unstated0.4981.01
  265. gpt-5-nano-2025-08-07minimal · not in the catalog0.4888.08
  266. qwen-plus-2025-01-25unstated · not in the catalog0.4884.76
  267. openai/gpt-4o-2024-11-20unstated0.4880.37
  268. google/gemma-3-27b-itunstated0.4885.05
  269. magistral-small-2509unstated · not in the catalog0.48set aside
  270. mistral-small-2503unstated · not in the catalog0.4780.18
  271. qwen3-8bnone · not in the catalog0.47set aside
  272. meta-llama/llama-3.3-70b-instructunstated0.4779.22
  273. gemini-1.5-flash-002unstated · not in the catalog0.4783.86
  274. mistral-small-3-2501unstated · not in the catalog0.47set aside
  275. claude-3-opus-20240229unstated · not in the catalog0.4778.88
  276. gpt-4-turbo-2024-04-09unstated · not in the catalog0.4780.07
  277. llama-3.1-tulu-3-70b-dpounstated · not in the catalog0.4679.20
  278. qwen2.5-32b-instructunstated · not in the catalog0.4681.76
  279. openai/gpt-oss-20bhigh0.46set aside
  280. gemini-1.5-pro-001unstated · not in the catalog0.4679.25
  281. qwen3-4b-instruct-2507unstated · not in the catalog0.46set aside
  282. mistral-small-2501unstated · not in the catalog0.4579.62
  283. z-ai/glm-4.7-flashnone0.45set aside
  284. deepseek-r1-distill-qwen-14bunstated · not in the catalog0.4592.30
  285. meta-llama/llama-3.1-70b-instructunstated0.4477.86
  286. qwen3-4bnone · not in the catalog0.44set aside
  287. wizardlm-2-8x22bunstated · not in the catalog0.43set aside
  288. gpt-4-1106-previewunstated · not in the catalog0.42set aside
  289. gpt-4-0125-previewunstated · not in the catalog0.42set aside
  290. mistral-small-3.1-2503unstated · not in the catalog0.42set aside
  291. qwen-turbo-2024-11-01unstated · not in the catalog0.4281.30
  292. llama-3.2-90b-vision-instructunstated · not in the catalog0.4177.93
  293. qwen2-72b-instructunstated · not in the catalog0.41set aside
  294. claude-3-sonnet-20240229unstated · not in the catalog0.4173.46
  295. meta-llama-3-70b-instructunstated · not in the catalog0.4174.91
  296. gemini-1.5-flash-001unstated · not in the catalog0.4075.35
  297. google/gemma-3-12b-itunstated0.39set aside
  298. mistral-large-2402unstated · not in the catalog0.3974.62
  299. claude-3-5-haiku-20241022unstated · not in the catalog0.3880.42
  300. qwen3-1.7bunstated · not in the catalog0.38set aside
  301. openai/gpt-4o-mini-2024-07-18unstated0.3880.10
  302. hermes-2-theta-llama-3-70bunstated · not in the catalog0.3774.21
  303. google/gemma-2-27b-itunstated0.3675.03
  304. claude-3-haiku-20240307unstated · not in the catalog0.3671.87
  305. gpt-4-0314unstated · not in the catalog0.36set aside
  306. qwen2.5-7b-instructunstated · not in the catalog0.35set aside
  307. claude-2.0unstated · not in the catalog0.3570.91
  308. open-mixtral-8x22bunstated · not in the catalog0.34set aside
  309. gemini-1.0-pro-001unstated · not in the catalog0.3470.18
  310. eurus-2-7b-primeunstated · not in the catalog0.34set aside
  311. deepseek-r1-distill-qwen-1.5bunstated · not in the catalog0.34set aside
  312. claude-2.1unstated · not in the catalog0.33set aside
  313. gemini-1.5-flash-8b-001unstated · not in the catalog0.33set aside
  314. dbrx-instructunstated · not in the catalog0.33set aside
  315. yi-1.5-34b-chatunstated · not in the catalog0.32set aside
  316. qwen1.5-32b-chatunstated · not in the catalog0.31set aside
  317. gpt-4-0613unstated · not in the catalog0.3174.56
  318. qwen3-1.7bnone · not in the catalog0.31set aside
  319. mixtral-8x7b-instruct-v0.1unstated · not in the catalog0.31set aside
  320. open-mistral-nemo-2407unstated · not in the catalog0.30set aside
  321. open-mixtral-8x7bunstated · not in the catalog0.30set aside
  322. qwen1.5-72b-chatunstated · not in the catalog0.29set aside
  323. granite-4.0-microunstated · not in the catalog0.28set aside
  324. gpt-3.5-turbo-1106unstated · not in the catalog0.28set aside
  325. phi-3-medium-128k-instructunstated · not in the catalog0.28set aside
  326. gemma-2-9b-itunstated · not in the catalog0.2772.14
  327. gpt-3.5-turbo-0125unstated · not in the catalog0.2769.92
  328. ministral-8b-2410unstated · not in the catalog0.27set aside
  329. meta-llama/llama-3.1-8b-instructunstated0.2772.89
  330. llama-2-70b-chat-hfunstated · not in the catalog0.2664.40
  331. meta-llama-3-8b-instructunstated · not in the catalog0.2667.01
  332. ministral-3b-2410unstated · not in the catalog0.25set aside
  333. deepseek-llm-67b-chatunstated · not in the catalog0.2566.23
  334. granite-4.0-1bunstated · not in the catalog0.24set aside
  335. meta-llama/llama-3.2-1b-instructunstated0.24set aside
  336. google/gemma-3-4b-itunstated0.23set aside
  337. gemma-3-1b-itunstated · not in the catalog0.20set aside
  338. mistral-7b-instruct-v0.3unstated · not in the catalog0.1560.84
  339. yi-34b-chatunstated · not in the catalog0.15set aside
  340. open-mistral-7bunstated · not in the catalog0.13set aside
  341. granite-4.0-350munstated · not in the catalog0.11set aside
  342. deepseek-r1-0528-qwen3-8bunstated · not in the catalog0.09set aside
MATH level 5Epoch AI Benchmarking Hub-1.25 · 2.51 · 108 runs

108 runs scored on it, 91 of them ranked, best score first, in the publisher's own unit. A ranked run is a door to its row.

  1. gpt-5-2025-08-07high · not in the catalog0.98108.61
  2. gpt-5-2025-08-07medium · not in the catalog0.98108.12
  3. gpt-5-mini-2025-08-07high · not in the catalog0.98104.57
  4. o4-mini-2025-04-16high · not in the catalog0.98103.35
  5. o3-2025-04-16high · not in the catalog0.98102.96
  6. claude-sonnet-4-5-20250929-32kunstated · not in the catalog0.98101.18
  7. qwen3-max-2025-09-23unstated · not in the catalog0.97100.03
  8. gpt-5-mini-2025-08-07medium · not in the catalog0.97103.83
  9. deepseek/deepseek-r1-0528unstated0.9798.81
  10. o3-mini-2025-01-31high · not in the catalog0.96102.45
  11. claude-haiku-4-5-20251001-32kunstated · not in the catalog0.9696.01
  12. gemini-2.5-pro-preview-05-06unstated · not in the catalog0.96102.43
  13. gemini-2.5-pro-preview-03-25unstated · not in the catalog0.96set aside
  14. gpt-5-nano-2025-08-07medium · not in the catalog0.9599.03
  15. o3-mini-2025-01-31medium · not in the catalog0.9597.94
  16. gpt-5-nano-2025-08-07high · not in the catalog0.95100.45
  17. o1-2024-12-17high · not in the catalog0.9598.27
  18. o1-2024-12-17medium · not in the catalog0.9497.81
  19. deepseek-r1unstated · not in the catalog0.9396.08
  20. claude-3-7-sonnet-20250219-64kunstated · not in the catalog0.9195.18
  21. grok-3-mini-betalow · not in the catalog0.9194.71
  22. claude-3-7-sonnet-20250219-32kunstated · not in the catalog0.9094.40
  23. deepseek-r1-distill-llama-70bunstated · not in the catalog0.9093.55
  24. o1-mini-2024-09-12high · not in the catalog0.8992.53
  25. grok-3-betaunstated · not in the catalog0.8994.65
  26. grok-3-mini-betahigh · not in the catalog0.8897.03
  27. gpt-4.1-mini-2025-04-14unstated · not in the catalog0.8793.48
  28. deepseek-r1-distill-qwen-14bunstated · not in the catalog0.8792.30
  29. claude-haiku-4-5-20251001unstated · not in the catalog0.8790.99
  30. claude-3-7-sonnet-20250219-16kunstated · not in the catalog0.8693.20
  31. claude-opus-4-20250514unstated · not in the catalog0.8592.48
  32. claude-sonnet-4-20250514unstated · not in the catalog0.8490.16
  33. o1-mini-2024-09-12medium · not in the catalog0.8491.51
  34. gemini-2.0-pro-exp-02-05unstated · not in the catalog0.8390.84
  35. gpt-4.1-2025-04-14unstated · not in the catalog0.8391.64
  36. gemini-2.0-flash-001unstated · not in the catalog0.8289.75
  37. o1-preview-2024-09-12unstated · not in the catalog0.8289.08
  38. mistral-medium-2505unstated · not in the catalog0.8289.41
  39. gpt-4.5-preview-2025-02-27unstated · not in the catalog0.7990.75
  40. deepseek-v3-0324unstated · not in the catalog0.7690.12
  41. google/gemma-3-27b-itunstated0.7485.05
  42. llama-4-maverick-17b-128e-instruct-fp8unstated · not in the catalog0.7387.21
  43. gemini-1.5-pro-002unstated · not in the catalog0.7086.80
  44. gpt-4.1-nano-2025-04-14unstated · not in the catalog0.7086.22
  45. qwen3-235b-a22bunstated · not in the catalog0.6987.56
  46. claude-3-7-sonnet-20250219unstated · not in the catalog0.6887.22
  47. qwen-max-2025-01-25unstated · not in the catalog0.6785.11
  48. qwen-plus-2025-01-25unstated · not in the catalog0.6584.76
  49. microsoft/phi-4unstated0.6584.64
  50. deepseek-v3unstated · not in the catalog0.6584.96
  51. grok-2-1212unstated · not in the catalog0.6483.89
  52. qwen2.5-72b-instructunstated · not in the catalog0.6383.11
  53. llama-4-scout-17b-16e-instructunstated · not in the catalog0.6282.99
  54. gemini-1.5-flash-002unstated · not in the catalog0.6283.86
  55. claude-3-5-sonnet-20241022unstated · not in the catalog0.5785.31
  56. qwen-turbo-2024-11-01unstated · not in the catalog0.5681.30
  57. qwen2.5-32b-instructunstated · not in the catalog0.5681.76
  58. openai/gpt-4o-2024-08-06unstated0.5382.76
  59. openai/gpt-4o-mini-2024-07-18unstated0.5380.10
  60. claude-3-5-sonnet-20240620unstated · not in the catalog0.5281.59
  61. openai/gpt-4o-2024-05-13unstated0.5181.01
  62. mistral-large-2411unstated · not in the catalog0.5081.24
  63. openai/gpt-4o-2024-11-20unstated0.5080.37
  64. llama-3.1-405b-instructunstated · not in the catalog0.5081.49
  65. mistral-small-2503unstated · not in the catalog0.4780.18
  66. gpt-4-turbo-2024-04-09unstated · not in the catalog0.4780.07
  67. claude-3-5-haiku-20241022unstated · not in the catalog0.4680.42
  68. mistralai/mistral-large-2407unstated0.4580.40
  69. mistral-small-2501unstated · not in the catalog0.4579.62
  70. llama-3.1-tulu-3-70b-dpounstated · not in the catalog0.4379.20
  71. meta-llama/llama-3.3-70b-instructunstated0.4279.22
  72. gemini-1.5-pro-001unstated · not in the catalog0.4179.25
  73. gpt-4-1106-previewunstated · not in the catalog0.40set aside
  74. llama-3.2-90b-vision-instructunstated · not in the catalog0.3977.93
  75. qwen2-72b-instructunstated · not in the catalog0.39set aside
  76. claude-3-opus-20240229unstated · not in the catalog0.3778.88
  77. meta-llama/llama-3.1-70b-instructunstated0.3777.86
  78. gpt-4-0125-previewunstated · not in the catalog0.35set aside
  79. google/gemma-2-27b-itunstated0.2875.03
  80. wizardlm-2-8x22bunstated · not in the catalog0.26set aside
  81. yi-1.5-34b-chatunstated · not in the catalog0.25set aside
  82. gemini-1.5-flash-001unstated · not in the catalog0.2575.35
  83. mistral-large-2402unstated · not in the catalog0.2474.62
  84. open-mixtral-8x22bunstated · not in the catalog0.24set aside
  85. gpt-4-0613unstated · not in the catalog0.2374.56
  86. meta-llama/llama-3.1-8b-instructunstated0.2372.89
  87. hermes-2-theta-llama-3-70bunstated · not in the catalog0.2374.21
  88. meta-llama-3-70b-instructunstated · not in the catalog0.2374.91
  89. gemma-2-9b-itunstated · not in the catalog0.2172.14
  90. claude-3-sonnet-20240229unstated · not in the catalog0.1873.46
  91. phi-3-medium-128k-instructunstated · not in the catalog0.18set aside
  92. gpt-3.5-turbo-1106unstated · not in the catalog0.16set aside
  93. ministral-8b-2410unstated · not in the catalog0.15set aside
  94. claude-3-haiku-20240307unstated · not in the catalog0.1571.87
  95. ministral-3b-2410unstated · not in the catalog0.14set aside
  96. claude-2.0unstated · not in the catalog0.1270.91
  97. dbrx-instructunstated · not in the catalog0.12set aside
  98. gpt-3.5-turbo-0125unstated · not in the catalog0.1269.92
  99. gemini-1.0-pro-001unstated · not in the catalog0.1170.18
  100. open-mistral-nemo-2407unstated · not in the catalog0.11set aside
  101. open-mixtral-8x7bunstated · not in the catalog0.10set aside
  102. mixtral-8x7b-instruct-v0.1unstated · not in the catalog0.09set aside
  103. deepseek-llm-67b-chatunstated · not in the catalog0.0666.23
  104. meta-llama-3-8b-instructunstated · not in the catalog0.0667.01
  105. yi-34b-chatunstated · not in the catalog0.05set aside
  106. open-mistral-7bunstated · not in the catalog0.04set aside
  107. mistral-7b-instruct-v0.3unstated · not in the catalog0.0460.84
  108. llama-2-70b-chat-hfunstated · not in the catalog0.0364.40
typosLiveBench-1.53 · 0.54 · 71 runs

71 runs scored on it, 71 of them ranked, best score first, in the publisher's own unit. A ranked run is a door to its row.

  1. anthropic/claude-fable-5max94122.58
  2. claude-fable-5-1max · not in the catalog94125.12
  3. anthropic/claude-opus-5max92122.24
  4. google/gemini-3.7-flashhigh90116.01
  5. google/gemini-3.8-flashhigh90114.21
  6. google/gemini-3.6-flashhigh88110.95
  7. openai/gpt-5.5xhigh88120.29
  8. google/gemini-3.5-flashhigh86111.12
  9. meta/muse-spark-1.3xhigh86116.79
  10. openai/gpt-5.6-terramax86119.24
  11. openai/gpt-6.1-solmax86130.00
  12. claude-sonnet-5-5max · not in the catalog86122.13
  13. qwen3.8-maxunstated · not in the catalog86118.08
  14. deepseek/deepseek-v4-flash-vision-expunstated84116.36
  15. minimax/minimax-m3unstated84104.58
  16. moonshotai/kimi-k3unstated84116.54
  17. openai/gpt-5.6-solmax84123.35
  18. openai/gpt-6.1-solxhigh84124.64
  19. qwen/qwen3.7-maxunstated84111.06
  20. claude-opus-4-6-thinking-autohigh · not in the catalog84113.04
  21. claude-sonnet-5-5xhigh · not in the catalog84119.88
  22. smaug-miniunstated · not in the catalog84114.73
  23. x-ai/grok-4.5unstated84114.74
  24. x-ai/grok-4.6unstated84117.62
  25. z-ai/glm-5.3unstated84112.92
  26. deepseek/deepseek-v4-flash-0731unstated82113.47
  27. deepseek/deepseek-v4-pro-0813unstated82118.60
  28. deepseek/deepseek-v4.1-flashmax82116.49
  29. google/gemini-3.1-pro-previewhigh82113.89
  30. openai/gpt-5.4xhigh82119.02
  31. openai/gpt-6-astramax82132.41
  32. qwen/qwen3.6-plusunstated82106.49
  33. claude-opus-5-5max · not in the catalog82128.09
  34. gpt-5.2-2025-12-11high · not in the catalog82110.74
  35. smaug-agenticunstated · not in the catalog82116.30
  36. deepseek/deepseek-v4-prounstated80111.64
  37. moonshotai/kimi-k2.7-codeunstated80107.73
  38. claude-opus-4-7xhigh · not in the catalog80113.14
  39. claude-opus-5-5xhigh · not in the catalog80125.14
  40. x-ai/grok-build-0.1unstated80106.25
  41. nvidia/nemotron-3-ultra-550b-a55bunstated78105.72
  42. openai/gpt-6-solmax78124.00
  43. claude-opus-4-5-20251101-thinking-64khigh · not in the catalog78110.65
  44. claude-opus-4-8max · not in the catalog78116.89
  45. kimi-k2.6-thinkingunstated · not in the catalog78107.26
  46. muse-wonder-1.0max · not in the catalog78120.86
  47. qwen3.8-flash-nextunstated · not in the catalog78113.12
  48. smaug-flashunstated · not in the catalog78116.63
  49. x-ai/grok-4.3unstated78103.07
  50. z-ai/glm-5.3-flashunstated78108.42
  51. anthropic/claude-sonnet-5xhigh76113.50
  52. qwen/qwen3.8-27bunstated76112.72
  53. thinkingmachines/inklingxhigh76107.98
  54. deepseek/deepseek-v4-flashunstated74102.96
  55. google/gemini-3.5-flash-litehigh7499.97
  56. meta/muse-spark-1.2xhigh74117.04
  57. ox-alphamax · not in the catalog74106.05
  58. z-ai/glm-5.2unstated74109.40
  59. claude-sonnet-4-6-thinking-automedium · not in the catalog72114.06
  60. openai/gpt-5.2-codexunstated70110.02
  61. openai/gpt-5.4-minixhigh70104.22
  62. openai/gpt-5.6-lunamax70114.95
  63. qwen/qwen3.6-27bunstated70103.72
  64. x-ai/grok-4.7xhigh70113.32
  65. openai/gpt-6-lunamax64113.99
  66. claude-haiku-5-5max · not in the catalog64113.88
  67. meta/muse-spark-1.1xhigh62114.21
  68. mistral-large-4high · not in the catalog60109.81
  69. nemotron-3.5-lightning-30b-a3bunstated · not in the catalog5887.31
  70. openai/gpt-5.4-nanoxhigh54110.30
  71. claude-haiku-5-5xhigh · not in the catalog54112.88
code_generationLiveBench-1.62 · 0.50 · 71 runs

71 runs scored on it, 71 of them ranked, best score first, in the publisher's own unit. A ranked run is a door to its row.

  1. claude-sonnet-5-5max · not in the catalog95.78122.13
  2. claude-sonnet-5-5xhigh · not in the catalog92.96119.88
  3. anthropic/claude-fable-5max91.55122.58
  4. claude-opus-5-5max · not in the catalog91.55128.09
  5. claude-opus-5-5xhigh · not in the catalog91.55125.14
  6. claude-fable-5-1max · not in the catalog90.14125.12
  7. claude-opus-4-7xhigh · not in the catalog85.92113.14
  8. smaug-agenticunstated · not in the catalog84.51116.30
  9. anthropic/claude-sonnet-5xhigh83.10113.50
  10. openai/gpt-5.6-solmax83.10123.35
  11. openai/gpt-6-solmax83.10124.00
  12. muse-wonder-1.0max · not in the catalog83.10120.86
  13. google/gemini-3.7-flashhigh81.69116.01
  14. meta/muse-spark-1.3xhigh81.69116.79
  15. openai/gpt-5.5xhigh81.69120.29
  16. anthropic/claude-opus-5max80.28122.24
  17. google/gemini-3.5-flashhigh80.28111.12
  18. moonshotai/kimi-k3unstated80.28116.54
  19. openai/gpt-5.2-codexunstated80.28110.02
  20. openai/gpt-6-astramax80.28132.41
  21. openai/gpt-6.1-solmax80.28130.00
  22. qwen/qwen3.6-plusunstated80.28106.49
  23. claude-opus-4-6-thinking-autohigh · not in the catalog80.28113.04
  24. claude-sonnet-4-6-thinking-automedium · not in the catalog80.28114.06
  25. smaug-flashunstated · not in the catalog80.28116.63
  26. openai/gpt-5.6-lunamax78.87114.95
  27. openai/gpt-6.1-solxhigh78.87124.64
  28. qwen/qwen3.7-maxunstated78.87111.06
  29. claude-haiku-5-5xhigh · not in the catalog78.87112.88
  30. claude-opus-4-5-20251101-thinking-64khigh · not in the catalog78.87110.65
  31. claude-opus-4-8max · not in the catalog78.87116.89
  32. kimi-k2.6-thinkingunstated · not in the catalog78.87107.26
  33. z-ai/glm-5.2unstated78.87109.40
  34. deepseek/deepseek-v4.1-flashmax77.47116.49
  35. google/gemini-3.6-flashhigh77.47110.95
  36. openai/gpt-6-lunamax77.47113.99
  37. qwen/qwen3.8-27bunstated77.47112.72
  38. claude-haiku-5-5max · not in the catalog77.47113.88
  39. x-ai/grok-4.6unstated77.47117.62
  40. z-ai/glm-5.3unstated77.47112.92
  41. z-ai/glm-5.3-flashunstated77.47108.42
  42. deepseek/deepseek-v4-flash-0731unstated76.06113.47
  43. deepseek/deepseek-v4-pro-0813unstated76.06118.60
  44. google/gemini-3.5-flash-litehigh76.0699.97
  45. meta/muse-spark-1.1xhigh76.06114.21
  46. openai/gpt-5.6-terramax76.06119.24
  47. gpt-5.2-2025-12-11high · not in the catalog76.06110.74
  48. mistral-large-4high · not in the catalog76.06109.81
  49. x-ai/grok-4.7xhigh76.06113.32
  50. google/gemini-3.1-pro-previewhigh74.65113.89
  51. meta/muse-spark-1.2xhigh74.65117.04
  52. openai/gpt-5.4xhigh74.65119.02
  53. thinkingmachines/inklingxhigh74.65107.98
  54. x-ai/grok-4.3unstated74.65103.07
  55. openai/gpt-5.4-nanoxhigh74.29110.30
  56. deepseek/deepseek-v4-flashunstated73.24102.96
  57. google/gemini-3.8-flashhigh73.24114.21
  58. ox-alphamax · not in the catalog73.24106.05
  59. moonshotai/kimi-k2.7-codeunstated71.83107.73
  60. nvidia/nemotron-3-ultra-550b-a55bunstated71.83105.72
  61. qwen/qwen3.6-27bunstated71.83103.72
  62. qwen3.8-maxunstated · not in the catalog71.83118.08
  63. deepseek/deepseek-v4-prounstated70.42111.64
  64. smaug-miniunstated · not in the catalog70.42114.73
  65. deepseek/deepseek-v4-flash-vision-expunstated69.01116.36
  66. minimax/minimax-m3unstated69.01104.58
  67. qwen3.8-flash-nextunstated · not in the catalog69.01113.12
  68. openai/gpt-5.4-minixhigh67.69104.22
  69. nemotron-3.5-lightning-30b-a3bunstated · not in the catalog67.6187.31
  70. x-ai/grok-4.5unstated67.61114.74
  71. x-ai/grok-build-0.1unstated63.38106.25
story_generationLiveBench-1.75 · 0.34 · 71 runs

71 runs scored on it, 71 of them ranked, best score first, in the publisher's own unit. A ranked run is a door to its row.

  1. google/gemini-3.8-flashhigh82.75114.21
  2. google/gemini-3.7-flashhigh82.25116.01
  3. qwen3.8-flash-nextunstated · not in the catalog81.37113.12
  4. claude-opus-4-8max · not in the catalog80.60116.89
  5. openai/gpt-5.4xhigh79.02119.02
  6. x-ai/grok-4.6unstated78.27117.62
  7. claude-fable-5-1max · not in the catalog78.10125.12
  8. smaug-miniunstated · not in the catalog78114.73
  9. meta/muse-spark-1.3xhigh77.48116.79
  10. google/gemini-3.1-pro-previewhigh77.25113.89
  11. claude-sonnet-5-5xhigh · not in the catalog77.08119.88
  12. smaug-agenticunstated · not in the catalog76.67116.30
  13. qwen3.8-maxunstated · not in the catalog76.52118.08
  14. qwen/qwen3.7-maxunstated76.28111.06
  15. openai/gpt-5.6-solmax75.92123.35
  16. google/gemini-3.6-flashhigh75.60110.95
  17. moonshotai/kimi-k3unstated75.37116.54
  18. google/gemini-3.5-flashhigh75.20111.12
  19. deepseek/deepseek-v4-pro-0813unstated74.93118.60
  20. x-ai/grok-4.7xhigh74.92113.32
  21. openai/gpt-5.2-codexunstated74.78110.02
  22. thinkingmachines/inklingxhigh74.18107.98
  23. muse-wonder-1.0max · not in the catalog74.17120.86
  24. openai/gpt-6-astramax73.98132.41
  25. deepseek/deepseek-v4-flash-vision-expunstated73.83116.36
  26. meta/muse-spark-1.2xhigh73.65117.04
  27. claude-haiku-5-5xhigh · not in the catalog73.60112.88
  28. x-ai/grok-4.5unstated73.58114.74
  29. qwen/qwen3.8-27bunstated73.10112.72
  30. deepseek/deepseek-v4.1-flashmax72.68116.49
  31. openai/gpt-5.5xhigh72.55120.29
  32. x-ai/grok-build-0.1unstated72.53106.25
  33. z-ai/glm-5.3unstated72.13112.92
  34. anthropic/claude-fable-5max71.70122.58
  35. claude-opus-5-5xhigh · not in the catalog71.18125.14
  36. claude-opus-5-5max · not in the catalog70.92128.09
  37. ox-alphamax · not in the catalog70.87106.05
  38. openai/gpt-6.1-solmax70.82130.00
  39. x-ai/grok-4.3unstated70.60103.07
  40. openai/gpt-6.1-solxhigh70.57124.64
  41. deepseek/deepseek-v4-flash-0731unstated70.50113.47
  42. smaug-flashunstated · not in the catalog69.98116.63
  43. claude-sonnet-5-5max · not in the catalog69.92122.13
  44. claude-opus-4-7xhigh · not in the catalog69.40113.14
  45. nvidia/nemotron-3-ultra-550b-a55bunstated69.23105.72
  46. meta/muse-spark-1.1xhigh69.15114.21
  47. openai/gpt-5.6-lunamax69.07114.95
  48. claude-sonnet-4-6-thinking-automedium · not in the catalog68.90114.06
  49. moonshotai/kimi-k2.7-codeunstated68.57107.73
  50. deepseek/deepseek-v4-prounstated67.75111.64
  51. openai/gpt-5.4-nanoxhigh67.65110.30
  52. mistral-large-4high · not in the catalog67.50109.81
  53. google/gemini-3.5-flash-litehigh67.4799.97
  54. deepseek/deepseek-v4-flashunstated67.27102.96
  55. openai/gpt-6-solmax66.93124.00
  56. kimi-k2.6-thinkingunstated · not in the catalog66.88107.26
  57. openai/gpt-5.6-terramax66.83119.24
  58. openai/gpt-5.4-minixhigh66.63104.22
  59. claude-opus-4-6-thinking-autohigh · not in the catalog66.13113.04
  60. claude-opus-4-5-20251101-thinking-64khigh · not in the catalog65.85110.65
  61. gpt-5.2-2025-12-11high · not in the catalog65.70110.74
  62. claude-haiku-5-5max · not in the catalog64.53113.88
  63. minimax/minimax-m3unstated63.55104.58
  64. openai/gpt-6-lunamax63.28113.99
  65. z-ai/glm-5.2unstated62.88109.40
  66. anthropic/claude-sonnet-5xhigh62.32113.50
  67. anthropic/claude-opus-5max61.32122.24
  68. qwen/qwen3.6-27bunstated60.13103.72
  69. z-ai/glm-5.3-flashunstated59.88108.42
  70. nemotron-3.5-lightning-30b-a3bunstated · not in the catalog59.3587.31
  71. qwen/qwen3.6-plusunstated56.87106.49
olympiadLiveBench-1.88 · 0.76 · 71 runs

71 runs scored on it, 71 of them ranked, best score first, in the publisher's own unit. A ranked run is a door to its row.

  1. claude-opus-5-5max · not in the catalog93.25128.09
  2. claude-fable-5-1max · not in the catalog92.97125.12
  3. anthropic/claude-fable-5max92.84122.58
  4. anthropic/claude-opus-5max92.80122.24
  5. claude-sonnet-5-5max · not in the catalog92.47122.13
  6. openai/gpt-6.1-solmax92.27130.00
  7. claude-opus-4-8max · not in the catalog92.23116.89
  8. claude-opus-4-6-thinking-autohigh · not in the catalog92.17113.04
  9. openai/gpt-6-astramax92.17132.41
  10. google/gemini-3.8-flashhigh92.16114.21
  11. claude-opus-5-5xhigh · not in the catalog92.15125.14
  12. google/gemini-3.1-pro-previewhigh92.10113.89
  13. google/gemini-3.5-flashhigh91.88111.12
  14. openai/gpt-6.1-solxhigh91.86124.64
  15. muse-wonder-1.0max · not in the catalog91.82120.86
  16. google/gemini-3.7-flashhigh91.79116.01
  17. meta/muse-spark-1.3xhigh91.74116.79
  18. claude-sonnet-5-5xhigh · not in the catalog91.72119.88
  19. openai/gpt-5.6-solmax91.69123.35
  20. x-ai/grok-4.7xhigh91.65113.32
  21. moonshotai/kimi-k3unstated91.65116.54
  22. smaug-agenticunstated · not in the catalog91.56116.30
  23. openai/gpt-5.6-terramax91.53119.24
  24. openai/gpt-5.4xhigh91.47119.02
  25. claude-opus-4-7xhigh · not in the catalog91.38113.14
  26. openai/gpt-6-solmax91.36124.00
  27. openai/gpt-5.5xhigh91.35120.29
  28. deepseek/deepseek-v4-pro-0813unstated91.29118.60
  29. x-ai/grok-4.6unstated91.21117.62
  30. qwen3.8-flash-nextunstated · not in the catalog91.17113.12
  31. qwen3.8-maxunstated · not in the catalog91.15118.08
  32. smaug-miniunstated · not in the catalog90.85114.73
  33. anthropic/claude-sonnet-5xhigh90.67113.50
  34. deepseek/deepseek-v4-prounstated90.62111.64
  35. google/gemini-3.6-flashhigh90.49110.95
  36. openai/gpt-6-lunamax90.38113.99
  37. moonshotai/kimi-k2.7-codeunstated90.30107.73
  38. smaug-flashunstated · not in the catalog90.20116.63
  39. deepseek/deepseek-v4-flash-vision-expunstated90.17116.36
  40. kimi-k2.6-thinkingunstated · not in the catalog90.03107.26
  41. z-ai/glm-5.3-flashunstated89.84108.42
  42. claude-opus-4-5-20251101-thinking-64khigh · not in the catalog89.46110.65
  43. mistral-large-4high · not in the catalog89.28109.81
  44. x-ai/grok-4.5unstated89.24114.74
  45. deepseek/deepseek-v4-flash-0731unstated89.08113.47
  46. deepseek/deepseek-v4.1-flashmax89.08116.49
  47. z-ai/glm-5.2unstated89.05109.40
  48. openai/gpt-5.6-lunamax88.65114.95
  49. gpt-5.2-2025-12-11high · not in the catalog88.57110.74
  50. openai/gpt-5.4-nanoxhigh87.98110.30
  51. claude-sonnet-4-6-thinking-automedium · not in the catalog87.86114.06
  52. meta/muse-spark-1.2xhigh87.75117.04
  53. qwen/qwen3.8-27bunstated87.73112.72
  54. z-ai/glm-5.3unstated87.51112.92
  55. meta/muse-spark-1.1xhigh87.50114.21
  56. openai/gpt-5.2-codexunstated87.00110.02
  57. claude-haiku-5-5xhigh · not in the catalog86.95112.88
  58. qwen/qwen3.7-maxunstated86.93111.06
  59. x-ai/grok-build-0.1unstated86.62106.25
  60. deepseek/deepseek-v4-flashunstated86.53102.96
  61. openai/gpt-5.4-minixhigh85.73104.22
  62. minimax/minimax-m3unstated85.61104.58
  63. thinkingmachines/inklingxhigh85.40107.98
  64. claude-haiku-5-5max · not in the catalog83.70113.88
  65. qwen/qwen3.6-plusunstated82.76106.49
  66. nvidia/nemotron-3-ultra-550b-a55bunstated82.58105.72
  67. qwen/qwen3.6-27bunstated82.32103.72
  68. x-ai/grok-4.3unstated82.26103.07
  69. ox-alphamax · not in the catalog81.95106.05
  70. google/gemini-3.5-flash-litehigh81.8099.97
  71. nemotron-3.5-lightning-30b-a3bunstated · not in the catalog58.9287.31
spatialLiveBench-3.10 · 0.85 · 71 runs

71 runs scored on it, 71 of them ranked, best score first, in the publisher's own unit. A ranked run is a door to its row.

  1. anthropic/claude-opus-5max100122.24
  2. anthropic/claude-sonnet-5xhigh100113.50
  3. google/gemini-3.6-flashhigh100110.95
  4. google/gemini-3.7-flashhigh100116.01
  5. google/gemini-3.8-flashhigh100114.21
  6. meta/muse-spark-1.1xhigh100114.21
  7. meta/muse-spark-1.3xhigh100116.79
  8. moonshotai/kimi-k3unstated100116.54
  9. openai/gpt-5.6-solmax100123.35
  10. openai/gpt-5.6-terramax100119.24
  11. qwen/qwen3.6-27bunstated100103.72
  12. claude-fable-5-1max · not in the catalog100125.12
  13. claude-opus-4-7xhigh · not in the catalog100113.14
  14. claude-sonnet-4-6-thinking-automedium · not in the catalog100114.06
  15. qwen3.8-flash-nextunstated · not in the catalog100113.12
  16. qwen3.8-maxunstated · not in the catalog100118.08
  17. smaug-agenticunstated · not in the catalog100116.30
  18. x-ai/grok-4.5unstated100114.74
  19. deepseek/deepseek-v4.1-flashmax98116.49
  20. google/gemini-3.1-pro-previewhigh98113.89
  21. nvidia/nemotron-3-ultra-550b-a55bunstated98105.72
  22. openai/gpt-5.4xhigh98119.02
  23. openai/gpt-5.5xhigh98120.29
  24. openai/gpt-6-astramax98132.41
  25. openai/gpt-6.1-solmax98130.00
  26. openai/gpt-6.1-solxhigh98124.64
  27. qwen/qwen3.6-plusunstated98106.49
  28. claude-opus-4-6-thinking-autohigh · not in the catalog98113.04
  29. claude-opus-4-8max · not in the catalog98116.89
  30. claude-opus-5-5max · not in the catalog98128.09
  31. claude-opus-5-5xhigh · not in the catalog98125.14
  32. claude-sonnet-5-5max · not in the catalog98122.13
  33. claude-sonnet-5-5xhigh · not in the catalog98119.88
  34. smaug-flashunstated · not in the catalog98116.63
  35. smaug-miniunstated · not in the catalog98114.73
  36. x-ai/grok-4.3unstated98103.07
  37. x-ai/grok-4.6unstated98117.62
  38. x-ai/grok-build-0.1unstated98106.25
  39. anthropic/claude-fable-5max96122.58
  40. deepseek/deepseek-v4-flashunstated96102.96
  41. deepseek/deepseek-v4-flash-vision-expunstated96116.36
  42. deepseek/deepseek-v4-pro-0813unstated96118.60
  43. google/gemini-3.5-flashhigh96111.12
  44. meta/muse-spark-1.2xhigh96117.04
  45. openai/gpt-5.6-lunamax96114.95
  46. openai/gpt-6-lunamax96113.99
  47. openai/gpt-6-solmax96124.00
  48. qwen/qwen3.7-maxunstated96111.06
  49. qwen/qwen3.8-27bunstated96112.72
  50. claude-opus-4-5-20251101-thinking-64khigh · not in the catalog96110.65
  51. gpt-5.2-2025-12-11high · not in the catalog96110.74
  52. muse-wonder-1.0max · not in the catalog96120.86
  53. ox-alphamax · not in the catalog96106.05
  54. z-ai/glm-5.3unstated96112.92
  55. z-ai/glm-5.3-flashunstated96108.42
  56. deepseek/deepseek-v4-prounstated94111.64
  57. minimax/minimax-m3unstated94104.58
  58. openai/gpt-5.2-codexunstated94110.02
  59. thinkingmachines/inklingxhigh94107.98
  60. claude-haiku-5-5xhigh · not in the catalog94112.88
  61. kimi-k2.6-thinkingunstated · not in the catalog94107.26
  62. mistral-large-4high · not in the catalog94109.81
  63. x-ai/grok-4.7xhigh94113.32
  64. z-ai/glm-5.2unstated94109.40
  65. moonshotai/kimi-k2.7-codeunstated92107.73
  66. claude-haiku-5-5max · not in the catalog92113.88
  67. nemotron-3.5-lightning-30b-a3bunstated · not in the catalog9287.31
  68. deepseek/deepseek-v4-flash-0731unstated90113.47
  69. google/gemini-3.5-flash-litehigh9099.97
  70. openai/gpt-5.4-minixhigh88104.22
  71. openai/gpt-5.4-nanoxhigh82110.30
AMPS_HardLiveBench-3.53 · 0.74 · 71 runs

71 runs scored on it, 71 of them ranked, best score first, in the publisher's own unit. A ranked run is a door to its row.

  1. anthropic/claude-opus-5max99.01122.24
  2. anthropic/claude-fable-5max99122.58
  3. google/gemini-3.8-flashhigh99114.21
  4. meta/muse-spark-1.3xhigh99116.79
  5. thinkingmachines/inklingxhigh99107.98
  6. claude-fable-5-1max · not in the catalog99125.12
  7. claude-opus-4-5-20251101-thinking-64khigh · not in the catalog99110.65
  8. claude-opus-5-5xhigh · not in the catalog99125.14
  9. muse-wonder-1.0max · not in the catalog99120.86
  10. qwen3.8-flash-nextunstated · not in the catalog99113.12
  11. x-ai/grok-4.5unstated99114.74
  12. z-ai/glm-5.3unstated99112.92
  13. anthropic/claude-sonnet-5xhigh98113.50
  14. deepseek/deepseek-v4-flashunstated98102.96
  15. deepseek/deepseek-v4-prounstated98111.64
  16. deepseek/deepseek-v4-pro-0813unstated98118.60
  17. deepseek/deepseek-v4.1-flashmax98116.49
  18. google/gemini-3.1-pro-previewhigh98113.89
  19. google/gemini-3.5-flashhigh98111.12
  20. google/gemini-3.6-flashhigh98110.95
  21. google/gemini-3.7-flashhigh98116.01
  22. openai/gpt-5.2-codexunstated98110.02
  23. openai/gpt-5.4xhigh98119.02
  24. openai/gpt-5.4-nanoxhigh98110.30
  25. openai/gpt-5.6-lunamax98114.95
  26. openai/gpt-5.6-solmax98123.35
  27. openai/gpt-5.6-terramax98119.24
  28. openai/gpt-6-astramax98132.41
  29. openai/gpt-6-lunamax98113.99
  30. openai/gpt-6-solmax98124.00
  31. openai/gpt-6.1-solmax98130.00
  32. openai/gpt-6.1-solxhigh98124.64
  33. qwen/qwen3.7-maxunstated98111.06
  34. qwen/qwen3.8-27bunstated98112.72
  35. claude-haiku-5-5xhigh · not in the catalog98112.88
  36. claude-opus-4-7xhigh · not in the catalog98113.14
  37. claude-opus-4-8max · not in the catalog98116.89
  38. claude-opus-5-5max · not in the catalog98128.09
  39. claude-sonnet-5-5max · not in the catalog98122.13
  40. claude-sonnet-5-5xhigh · not in the catalog98119.88
  41. mistral-large-4high · not in the catalog98109.81
  42. ox-alphamax · not in the catalog98106.05
  43. qwen3.8-maxunstated · not in the catalog98118.08
  44. smaug-agenticunstated · not in the catalog98116.30
  45. smaug-miniunstated · not in the catalog98114.73
  46. x-ai/grok-4.7xhigh98113.32
  47. z-ai/glm-5.2unstated98109.40
  48. deepseek/deepseek-v4-flash-0731unstated97113.47
  49. moonshotai/kimi-k2.7-codeunstated97107.73
  50. moonshotai/kimi-k3unstated97116.54
  51. openai/gpt-5.4-minixhigh97104.22
  52. openai/gpt-5.5xhigh97120.29
  53. qwen/qwen3.6-plusunstated97106.49
  54. claude-haiku-5-5max · not in the catalog97113.88
  55. claude-opus-4-6-thinking-autohigh · not in the catalog97113.04
  56. gpt-5.2-2025-12-11high · not in the catalog97110.74
  57. kimi-k2.6-thinkingunstated · not in the catalog97107.26
  58. nemotron-3.5-lightning-30b-a3bunstated · not in the catalog9787.31
  59. smaug-flashunstated · not in the catalog97116.63
  60. x-ai/grok-4.3unstated97103.07
  61. x-ai/grok-4.6unstated97117.62
  62. z-ai/glm-5.3-flashunstated97108.42
  63. nvidia/nemotron-3-ultra-550b-a55bunstated96105.72
  64. google/gemini-3.5-flash-litehigh9599.97
  65. qwen/qwen3.6-27bunstated93103.72
  66. meta/muse-spark-1.2xhigh89117.04
  67. deepseek/deepseek-v4-flash-vision-expunstated88116.36
  68. meta/muse-spark-1.1xhigh82114.21
  69. claude-sonnet-4-6-thinking-automedium · not in the catalog76114.06
  70. minimax/minimax-m3unstated75104.58
  71. x-ai/grok-build-0.1unstated66106.25
math_compLiveBench-3.85 · 0.65 · 71 runs

71 runs scored on it, 71 of them ranked, best score first, in the publisher's own unit. A ranked run is a door to its row.

  1. claude-haiku-5-5max · not in the catalog98.04113.88
  2. claude-opus-4-7xhigh · not in the catalog98.04113.14
  3. claude-opus-4-8max · not in the catalog98.04116.89
  4. deepseek/deepseek-v4-flashunstated97.06102.96
  5. deepseek/deepseek-v4-flash-vision-expunstated97.06116.36
  6. deepseek/deepseek-v4-pro-0813unstated97.06118.60
  7. meta/muse-spark-1.2xhigh97.06117.04
  8. meta/muse-spark-1.3xhigh97.06116.79
  9. openai/gpt-6-astramax97.06132.41
  10. openai/gpt-6-solmax97.06124.00
  11. openai/gpt-6.1-solmax97.06130.00
  12. openai/gpt-6.1-solxhigh97.06124.64
  13. qwen/qwen3.7-maxunstated97.06111.06
  14. thinkingmachines/inklingxhigh97.06107.98
  15. claude-fable-5-1max · not in the catalog97.06125.12
  16. claude-haiku-5-5xhigh · not in the catalog97.06112.88
  17. claude-opus-5-5max · not in the catalog97.06128.09
  18. claude-opus-5-5xhigh · not in the catalog97.06125.14
  19. claude-sonnet-5-5max · not in the catalog97.06122.13
  20. claude-sonnet-5-5xhigh · not in the catalog97.06119.88
  21. mistral-large-4high · not in the catalog97.06109.81
  22. muse-wonder-1.0max · not in the catalog97.06120.86
  23. smaug-flashunstated · not in the catalog97.06116.63
  24. x-ai/grok-4.5unstated97.06114.74
  25. x-ai/grok-4.6unstated97.06117.62
  26. x-ai/grok-4.7xhigh97.06113.32
  27. deepseek/deepseek-v4-flash-0731unstated96.08113.47
  28. deepseek/deepseek-v4-prounstated96.08111.64
  29. deepseek/deepseek-v4.1-flashmax96.08116.49
  30. google/gemini-3.1-pro-previewhigh96.08113.89
  31. google/gemini-3.7-flashhigh96.08116.01
  32. meta/muse-spark-1.1xhigh96.08114.21
  33. nvidia/nemotron-3-ultra-550b-a55bunstated96.08105.72
  34. openai/gpt-5.5xhigh96.08120.29
  35. kimi-k2.6-thinkingunstated · not in the catalog96.08107.26
  36. z-ai/glm-5.2unstated96.08109.40
  37. z-ai/glm-5.3unstated96.08112.92
  38. anthropic/claude-fable-5max95.10122.58
  39. anthropic/claude-sonnet-5xhigh95.10113.50
  40. google/gemini-3.5-flashhigh95.10111.12
  41. google/gemini-3.8-flashhigh95.10114.21
  42. moonshotai/kimi-k3unstated95.10116.54
  43. openai/gpt-5.2-codexunstated95.10110.02
  44. openai/gpt-5.4-nanoxhigh95.10110.30
  45. openai/gpt-5.6-solmax95.10123.35
  46. openai/gpt-5.6-terramax95.10119.24
  47. claude-opus-4-5-20251101-thinking-64khigh · not in the catalog95.10110.65
  48. claude-opus-4-6-thinking-autohigh · not in the catalog95.10113.04
  49. gpt-5.2-2025-12-11high · not in the catalog95.10110.74
  50. qwen3.8-maxunstated · not in the catalog95.10118.08
  51. x-ai/grok-4.3unstated95.10103.07
  52. x-ai/grok-build-0.1unstated95.10106.25
  53. anthropic/claude-opus-5max94.12122.24
  54. google/gemini-3.6-flashhigh94.12110.95
  55. moonshotai/kimi-k2.7-codeunstated94.12107.73
  56. openai/gpt-5.4xhigh94.12119.02
  57. openai/gpt-5.4-minixhigh94.12104.22
  58. openai/gpt-6-lunamax94.12113.99
  59. qwen/qwen3.8-27bunstated94.12112.72
  60. claude-sonnet-4-6-thinking-automedium · not in the catalog94.12114.06
  61. qwen3.8-flash-nextunstated · not in the catalog94.12113.12
  62. smaug-agenticunstated · not in the catalog94.12116.30
  63. smaug-miniunstated · not in the catalog94.12114.73
  64. qwen/qwen3.6-plusunstated93.14106.49
  65. z-ai/glm-5.3-flashunstated93.14108.42
  66. google/gemini-3.5-flash-litehigh92.1699.97
  67. openai/gpt-5.6-lunamax92.16114.95
  68. qwen/qwen3.6-27bunstated92.16103.72
  69. minimax/minimax-m3unstated91.18104.58
  70. ox-alphamax · not in the catalog91.18106.05
  71. nemotron-3.5-lightning-30b-a3bunstated · not in the catalog86.2887.31
tablereformatLiveBench-3.95 · 0.82 · 71 runs

71 runs scored on it, 71 of them ranked, best score first, in the publisher's own unit. A ranked run is a door to its row.

  1. deepseek/deepseek-v4-flash-0731unstated100113.47
  2. deepseek/deepseek-v4-prounstated100111.64
  3. deepseek/deepseek-v4.1-flashmax100116.49
  4. meta/muse-spark-1.1xhigh100114.21
  5. meta/muse-spark-1.2xhigh100117.04
  6. meta/muse-spark-1.3xhigh100116.79
  7. openai/gpt-5.2-codexunstated100110.02
  8. openai/gpt-5.4xhigh100119.02
  9. openai/gpt-5.4-minixhigh100104.22
  10. openai/gpt-5.5xhigh100120.29
  11. openai/gpt-5.6-lunamax100114.95
  12. openai/gpt-5.6-solmax100123.35
  13. openai/gpt-5.6-terramax100119.24
  14. openai/gpt-6-astramax100132.41
  15. openai/gpt-6-lunamax100113.99
  16. openai/gpt-6-solmax100124.00
  17. openai/gpt-6.1-solmax100130.00
  18. openai/gpt-6.1-solxhigh100124.64
  19. thinkingmachines/inklingxhigh100107.98
  20. gpt-5.2-2025-12-11high · not in the catalog100110.74
  21. mistral-large-4high · not in the catalog100109.81
  22. muse-wonder-1.0max · not in the catalog100120.86
  23. ox-alphamax · not in the catalog100106.05
  24. x-ai/grok-4.5unstated100114.74
  25. x-ai/grok-4.6unstated100117.62
  26. x-ai/grok-4.7xhigh100113.32
  27. x-ai/grok-build-0.1unstated100106.25
  28. anthropic/claude-sonnet-5xhigh98.04113.50
  29. deepseek/deepseek-v4-flashunstated98.04102.96
  30. deepseek/deepseek-v4-flash-vision-expunstated98.04116.36
  31. deepseek/deepseek-v4-pro-0813unstated98.04118.60
  32. google/gemini-3.1-pro-previewhigh98.04113.89
  33. google/gemini-3.5-flash-litehigh98.0499.97
  34. google/gemini-3.6-flashhigh98.04110.95
  35. google/gemini-3.7-flashhigh98.04116.01
  36. minimax/minimax-m3unstated98.04104.58
  37. moonshotai/kimi-k3unstated98.04116.54
  38. nvidia/nemotron-3-ultra-550b-a55bunstated98.04105.72
  39. openai/gpt-5.4-nanoxhigh98.04110.30
  40. qwen/qwen3.6-27bunstated98.04103.72
  41. qwen/qwen3.6-plusunstated98.04106.49
  42. qwen/qwen3.7-maxunstated98.04111.06
  43. claude-haiku-5-5max · not in the catalog98.04113.88
  44. claude-haiku-5-5xhigh · not in the catalog98.04112.88
  45. claude-opus-4-5-20251101-thinking-64khigh · not in the catalog98.04110.65
  46. claude-opus-4-6-thinking-autohigh · not in the catalog98.04113.04
  47. claude-opus-4-7xhigh · not in the catalog98.04113.14
  48. claude-opus-5-5max · not in the catalog98.04128.09
  49. claude-opus-5-5xhigh · not in the catalog98.04125.14
  50. claude-sonnet-5-5max · not in the catalog98.04122.13
  51. claude-sonnet-5-5xhigh · not in the catalog98.04119.88
  52. kimi-k2.6-thinkingunstated · not in the catalog98.04107.26
  53. qwen3.8-maxunstated · not in the catalog98.04118.08
  54. smaug-agenticunstated · not in the catalog98.04116.30
  55. smaug-flashunstated · not in the catalog98.04116.63
  56. x-ai/grok-4.3unstated98.04103.07
  57. google/gemini-3.5-flashhigh96.08111.12
  58. google/gemini-3.8-flashhigh96.08114.21
  59. qwen/qwen3.8-27bunstated96.08112.72
  60. claude-sonnet-4-6-thinking-automedium · not in the catalog96.08114.06
  61. qwen3.8-flash-nextunstated · not in the catalog96.08113.12
  62. smaug-miniunstated · not in the catalog96.08114.73
  63. z-ai/glm-5.2unstated96.08109.40
  64. z-ai/glm-5.3unstated96.08112.92
  65. z-ai/glm-5.3-flashunstated96.08108.42
  66. anthropic/claude-fable-5max94.12122.58
  67. anthropic/claude-opus-5max94.12122.24
  68. claude-fable-5-1max · not in the catalog94.12125.12
  69. claude-opus-4-8max · not in the catalog94.12116.89
  70. moonshotai/kimi-k2.7-codeunstated92.16107.73
  71. nemotron-3.5-lightning-30b-a3bunstated · not in the catalog86.2887.31

46 columns, hardest first; the words in the head reorder them. A thick span fits inside one standard deviation, and 12 do. A span wider than the shading sorts nothing among the ranked runs, and 5 are wider than the whole ranked range. An end without a cap ran past the axis. Difficulty and slope in the right column are on the fit standardised scale, where zero is the mean run; the marker is the same difficulty on the presented scale; runs is how many the column scored, which is the evidence behind its difficulty. A row opens onto every run scored on the column. A column is named board first because two publishers can name a benchmark the same thing and mean two different sets of questions. The boards themselves, with the licence and the metric each publisher states, are on the benchmarks page.

Each board on this axis is placed against the others through the runs it shares with them: Epoch AI Benchmarking Hub through 56, LiveBench through 37 and Aider polyglot through 19. A group of columns goes on the axis only where 2 runs or more were scored both in it and on the rest, because one shared run fixes where the group sits and not how far apart its runs are. HELM (GPQA - COT correct, IFEval - IFEval Strict Acc, MMLU-Pro - COT correct, Mean score, Omni-MATH - Acc, WildBench - WB Score) and Vectara hallucination leaderboard (factual consistency rate) share 1 run with the rest, zai-org/glm-4.6, and are excluded with the 161 runs scored only there. MTEB (SciFact) shares no run with the rest and is excluded with the 267 runs scored only there.

Over the 64 models on both scales, the two orderings agree at a rank correlation of 0.963, and 8 of them hold the same place on both.

11020304050601102030405060dashed: the same place on both0503020401place on the Epoch Capabilities Index, first at the leftplace on this fit, first at the topGPT-6.2 Astra: 1 here · 1 on the indexGPT-6.2 Astra1 here · 1 on the indexGemini 4 Carbon: 3 here · 2 on the indexGemini 4 Carbon3 here · 2 on the indexGPT-6 Astra: 2 here · 3 on the indexGPT-6 Astra2 here · 3 on the indexGPT-6.1 Sol: 5 here · 4 on the indexGPT-6.1 Sol5 here · 4 on the indexGPT-6.1 Terra: 4 here · 5 on the indexGPT-6.1 Terra4 here · 5 on the indexGemini 4 Hydrogen: 6 here · 6 on the indexGemini 4 Hydrogen6 here · 6 on the indexGemini 4 Argon: 7 here · 7 on the indexGemini 4 Argon7 here · 7 on the indexClaude Opus 5: 12 here · 8 on the indexClaude Opus 512 here · 8 on the indexClaude Fable 5: 11 here · 9 on the indexClaude Fable 511 here · 9 on the indexGPT-6 Sol: 8 here · 10 on the indexGPT-6 Sol8 here · 10 on the indexGPT-5.6 Sol: 9 here · 11 on the indexGPT-5.6 Sol9 here · 11 on the indexGPT-5.5 Pro: 10 here · 12 on the indexGPT-5.5 Pro10 here · 12 on the indexGPT-5.6 Terra: 14 here · 13 on the indexGPT-5.6 Terra14 here · 13 on the indexGPT-5.5: 13 here · 14 on the indexGPT-5.513 here · 14 on the indexDeepSeek V4.1 Flash 1017: 22 here · 15 on the indexDeepSeek V4.1 Flash 101722 here · 15 on the indexGemini 3.8 Flash: 26 here · 16 on the indexGemini 3.8 Flash26 here · 16 on the indexKimi K3: 20 here · 17 on the indexKimi K320 here · 17 on the indexGemini 3.7 Flash: 23 here · 18 on the indexGemini 3.7 Flash23 here · 18 on the indexMuse Spark 1.3: 19 here · 19 on the indexMuse Spark 1.319 here · 19 on the indexGPT-5.4: 15 here · 20 on the indexGPT-5.415 here · 20 on the indexGrok 4.6: 17 here · 21 on the indexGrok 4.617 here · 21 on the indexGLM-5.3: 32 here · 22 on the indexGLM-5.332 here · 22 on the indexDeepSeek V4.1 Flash: 21 here · 23 on the indexDeepSeek V4.1 Flash21 here · 23 on the indexClaude Sonnet 5: 29 here · 24 on the indexClaude Sonnet 529 here · 24 on the indexGPT-5.6 Luna: 24 here · 25 on the indexGPT-5.6 Luna24 here · 25 on the indexGPT-6 Luna: 28 here · 26 on the indexGPT-6 Luna28 here · 26 on the indexGrok 4.7: 31 here · 27 on the indexGrok 4.731 here · 27 on the indexDeepSeek V4 Pro 0813: 16 here · 28 on the indexDeepSeek V4 Pro 081316 here · 28 on the indexGemini 3.5 Flash: 34 here · 29 on the indexGemini 3.5 Flash34 here · 29 on the indexGemini 3.6 Flash: 36 here · 30 on the indexGemini 3.6 Flash36 here · 30 on the indexMuse Spark 1.2: 18 here · 31 on the indexMuse Spark 1.218 here · 31 on the indexGrok 4.5: 25 here · 32 on the indexGrok 4.525 here · 32 on the indexMuse Spark 1.1: 26 here · 33 on the indexMuse Spark 1.126 here · 33 on the indexQwen3.7-Max: 35 here · 34 on the indexQwen3.7-Max35 here · 34 on the indexMistral Large 4: 41 here · 34 on the indexMistral Large 441 here · 34 on the indexDeepSeek V4 Flash 0731: 30 here · 36 on the indexDeepSeek V4 Flash 073130 here · 36 on the indexGLM-5.3-Flash: 43 here · 37 on the indexGLM-5.3-Flash43 here · 37 on the indexMuse Spark: 38 here · 38 on the indexMuse Spark38 here · 38 on the indexGLM-5.2: 39 here · 39 on the indexGLM-5.239 here · 39 on the indexKimi K2.6: 37 here · 40 on the indexKimi K2.637 here · 40 on the indexKimi K2.7 Code: 46 here · 41 on the indexKimi K2.7 Code46 here · 41 on the indexInkling-Small: 47 here · 42 on the indexInkling-Small47 here · 42 on the indexGLM-5.1: 42 here · 43 on the indexGLM-5.142 here · 43 on the indexDeepSeek-V4-Pro: 33 here · 44 on the indexDeepSeek-V4-Pro33 here · 44 on the indexGPT-5.4 Mini: 52 here · 45 on the indexGPT-5.4 Mini52 here · 45 on the indexInkling: 44 here · 46 on the indexInkling44 here · 46 on the indexQwen3.5 397B-A17B: 51 here · 47 on the indexQwen3.5 397B-A17B51 here · 47 on the indexQwen3.7-Plus: 45 here · 48 on the indexQwen3.7-Plus45 here · 48 on the indexMiniMax-M3: 50 here · 49 on the indexMiniMax-M350 here · 49 on the indexNemotron 3 Ultra: 48 here · 50 on the indexNemotron 3 Ultra48 here · 50 on the indexDeepSeek-V4-Flash: 55 here · 51 on the indexDeepSeek-V4-Flash55 here · 51 on the indexQwen3.6 27B: 54 here · 52 on the indexQwen3.6 27B54 here · 52 on the indexGLM-5: 58 here · 53 on the indexGLM-558 here · 53 on the indexGPT-5.4 Nano: 40 here · 54 on the indexGPT-5.4 Nano40 here · 54 on the indexGemini 3.5 Flash-Lite: 57 here · 55 on the indexGemini 3.5 Flash-Lite57 here · 55 on the indexKimi K2 Thinking: 49 here · 56 on the indexKimi K2 Thinking49 here · 56 on the indexGemini 3.1 Flash-Lite: 56 here · 57 on the indexGemini 3.1 Flash-Lite56 here · 57 on the indexGLM-4.7: 53 here · 58 on the indexGLM-4.753 here · 58 on the indexDeepSeek-R1: 60 here · 59 on the indexDeepSeek-R160 here · 59 on the indexQwen3-235B-A22B: 62 here · 60 on the indexQwen3-235B-A22B62 here · 60 on the indexQwen3-32B: 59 here · 61 on the indexQwen3-32B59 here · 61 on the indexQwQ-32B: 61 here · 62 on the indexQwQ-32B61 here · 62 on the indexDeepSeek-V3: 63 here · 63 on the indexDeepSeek-V363 here · 63 on the indexPhi-4: 64 here · 64 on the indexPhi-464 here · 64 on the index
  1. 01GPT-5.4 Nano40 here · 54 on the index · 14 places apart
  2. 02Muse Spark 1.218 here · 31 on the index · 13 places apart
  3. 03DeepSeek V4 Pro 081316 here · 28 on the index · 12 places apart
  4. 04DeepSeek-V4-Pro33 here · 44 on the index · 11 places apart
  5. 05Gemini 3.8 Flash26 here · 16 on the index · 10 places apart

A model here is its strongest ranked run, so a run under the 3 column floor is not compared, and a place is counted among the 64 models on both scales rather than among everything either one ranks. Only the order compares: the two fits share a form and nothing else, so their numbers were never going to line up. Each numbered model is a door to its row in the ranked ledger. Computed at render from two committed documents, this fit and the index as read , and the same figure scripts/capability-index.mjs --against-eci prints. The index itself, with the interval Epoch publishes on every figure, is on its own board.

Epoch AI Benchmarking Hub data, by Epoch AI, under CC BY 4.0.

All 64 models on both scales
  1. GPT-6.2 Astra1 here1 on the index
  2. Gemini 4 Carbon3 here2 on the index
  3. GPT-6 Astra2 here3 on the index
  4. GPT-6.1 Sol5 here4 on the index
  5. GPT-6.1 Terra4 here5 on the index
  6. Gemini 4 Hydrogen6 here6 on the index
  7. Gemini 4 Argon7 here7 on the index
  8. Claude Opus 512 here8 on the index
  9. Claude Fable 511 here9 on the index
  10. GPT-6 Sol8 here10 on the index
  11. GPT-5.6 Sol9 here11 on the index
  12. GPT-5.5 Pro10 here12 on the index
  13. GPT-5.6 Terra14 here13 on the index
  14. GPT-5.513 here14 on the index
  15. DeepSeek V4.1 Flash 101722 here15 on the index
  16. Gemini 3.8 Flash26 here16 on the index
  17. Kimi K320 here17 on the index
  18. Gemini 3.7 Flash23 here18 on the index
  19. Muse Spark 1.319 here19 on the index
  20. GPT-5.415 here20 on the index
  21. Grok 4.617 here21 on the index
  22. GLM-5.332 here22 on the index
  23. DeepSeek V4.1 Flash21 here23 on the index
  24. Claude Sonnet 529 here24 on the index
  25. GPT-5.6 Luna24 here25 on the index
  26. GPT-6 Luna28 here26 on the index
  27. Grok 4.731 here27 on the index
  28. DeepSeek V4 Pro 081316 here28 on the index
  29. Gemini 3.5 Flash34 here29 on the index
  30. Gemini 3.6 Flash36 here30 on the index
  31. Muse Spark 1.218 here31 on the index
  32. Grok 4.525 here32 on the index
  33. Muse Spark 1.126 here33 on the index
  34. Qwen3.7-Max35 here34 on the index
  35. Mistral Large 441 here34 on the index
  36. DeepSeek V4 Flash 073130 here36 on the index
  37. GLM-5.3-Flash43 here37 on the index
  38. Muse Spark38 here38 on the index
  39. GLM-5.239 here39 on the index
  40. Kimi K2.637 here40 on the index
  41. Kimi K2.7 Code46 here41 on the index
  42. Inkling-Small47 here42 on the index
  43. GLM-5.142 here43 on the index
  44. DeepSeek-V4-Pro33 here44 on the index
  45. GPT-5.4 Mini52 here45 on the index
  46. Inkling44 here46 on the index
  47. Qwen3.5 397B-A17B51 here47 on the index
  48. Qwen3.7-Plus45 here48 on the index
  49. MiniMax-M350 here49 on the index
  50. Nemotron 3 Ultra48 here50 on the index
  51. DeepSeek-V4-Flash55 here51 on the index
  52. Qwen3.6 27B54 here52 on the index
  53. GLM-558 here53 on the index
  54. GPT-5.4 Nano40 here54 on the index
  55. Gemini 3.5 Flash-Lite57 here55 on the index
  56. Kimi K2 Thinking49 here56 on the index
  57. Gemini 3.1 Flash-Lite56 here57 on the index
  58. GLM-4.753 here58 on the index
  59. DeepSeek-R160 here59 on the index
  60. Qwen3-235B-A22B62 here60 on the index
  61. Qwen3-32B59 here61 on the index
  62. QwQ-32B61 here62 on the index
  63. DeepSeek-V363 here63 on the index
  64. Phi-464 here64 on the index
What this figure is

Somebody else's measurements, on a scale fit here.

Fit by Vitna over boards published by others. Every score behind it was produced by somebody else, under the licences named in app/data/boards.json, and Vitna ran none of these evaluations.

Mean 100, 15 to a standard deviation, over the runs in this document. This fit's own scale: not an Epoch Capabilities Index score, and not comparable to one. The orderings are.

The form is Epoch AI's, published in their MIT package and their paper: one capability per run, one difficulty and one slope per benchmark column, fit by maximum likelihood. The ordering this produces is checked against their own Capabilities Index over the models on both scales, and the check is the fourth exhibit above, computed from the committed documents rather than asserted.

Vitna's own question, of what Vitna has measured, still answers none. Every cell behind this scale was produced by somebody else under a licence that permits republishing it, and moving from a publisher's ordering to one fit here changes whose arithmetic it is, not whose work.

Fit over the mirror read , on document shape 2. It is re-derived from the committed boards on every mirror run and rewritten only when the ordering, the set of runs or the evidence behind one of them moves, so an unchanged day leaves this page exactly as it was.