By model and setting

Each model and reasoning setting appears once. If a model produced more than one player program for this game, the row stands for all of them: Programs counts the working attempts out of the counted attempts, Score and Raw rating average the programs (weighted by attempts; the small range is the lowest and highest program rating), and the combined record adds up their matches. Score is relative within this game (0–100). Scores here are working-program strength: failed generation attempts are left out and count as 0 only in a model's headline score.

GB2-01: Go - Reasoning Variants
Rank Model Reasoning Score Programs Raw rating Combined record (W / D / L)
1GPT-6.2 AstraXHigh99.21 working of 1 attempt2485.6451 / 0 / 5
2Claude Fable 5.2XHigh98.11 working of 1 attempt2327.3628 / 0 / 16
3Gemini 4 CarbonHigh96.81 working of 1 attempt2222.5618 / 3 / 27
4GPT-6 AstraXHigh96.71 working of 1 attempt2220.0618 / 0 / 28
5GPT-6.2 Sol ProMedium96.71 working of 1 attempt2216.3406 / 8 / 18
6GPT-5.4Medium96.71 working of 1 attempt2215.5609 / 14 / 23
7Gemini 4 CarbonLow96.61 working of 1 attempt2208.1615 / 0 / 31
8GPT-6.2 Sol ProXHigh96.01 working of 1 attempt2176.0409 / 2 / 23
9GPT-5.4XHigh94.61 working of 1 attempt2112.2591 / 21 / 34
10Gemini 4 ArgonHigh94.51 working of 1 attempt2108.1602 / 0 / 48
11GPT-6.2 Astra ProXHigh94.51 working of 1 attempt2107.2397 / 35 / 22
12GPT-6 Astra ProXHigh94.11 working of 1 attempt2091.7426 / 11 / 33
13GPT-6.2 SolMedium93.81 working of 1 attempt2077.8596 / 10 / 50
14Gemini 4 HydrogenXHigh93.41 working of 1 attempt2065.6592 / 0 / 56
15Claude Fable 5.2Medium93.31 working of 1 attempt2061.8592 / 0 / 58
16Claude Opus 5.5Medium92.51 working of 1 attempt2034.2560 / 45 / 41
17GPT-6 AstraLow92.31 working of 1 attempt2030.6577 / 25 / 52
18Claude Fable 5.1XHigh91.71 working of 1 attempt2012.3578 / 2 / 66
19Particle-1Max91.51 working of 1 attempt2004.9564 / 26 / 56
20Kimi K3.1 ProMax91.41 working of 1 attempt2003.4577 / 1 / 72
21Ernie 5.5 Flash PreviewDefault90.61 working of 1 attempt1982.1557 / 29 / 64
22Gemini 4 ArgonLow90.31 working of 1 attempt1974.0569 / 0 / 79
23Claude Opus 5.5Low89.81 working of 1 attempt1959.7549 / 27 / 70
24Gemini 3.5 FlashHigh89.71 working of 1 attempt1957.6549 / 26 / 71
25Muse Spark OpenXHigh89.61 working of 1 attempt1955.9560 / 0 / 84

Individual player programs

Each row is one accepted player program for GB2-01: Go; a model can have more than one. Score is the 0–100 result in this game, and its rating and W / D / L record show how it played. Scores are working-program strength: failed generation attempts have no row and count only in a model's headline score.

328 player programs.

ModelReasoningStatusScoreRatingW / D / LMatchesOpponentsNotesGenerated
GPT-6.2 AstraE-ded6677fc4d2c63cXHighRated Interval validated99.22486451 / 0 / 5456 / 456228—2026-11-17First try
Claude Fable 5.2E-8ee35c299845147fXHighRated Interval validated98.12327628 / 0 / 16644 / 644322—2026-11-09First try
Gemini 4 CarbonE-8f7c0faa1d26ca79HighRated Interval validated96.82222618 / 3 / 27648 / 6483243 capped draws2026-11-12First try
GPT-6 AstraE-fc5055140bf78475XHighRated Interval validated96.72220618 / 0 / 28646 / 646323—2026-09-05First try
GPT-6.2 Sol ProE-b29baf67617e0fd0MediumRated Interval validated96.72216406 / 8 / 18432 / 4322168 capped draws2026-11-18First try
GPT-5.4E-d4fa7dbb9458c464MediumRated Interval validated96.72216609 / 14 / 23646 / 64632314 capped draws2026-08-09First try
Gemini 4 CarbonE-3dddac17b1d0d79fLowRated Interval validated96.62208615 / 0 / 31646 / 646323—2026-11-12First try
GPT-6.2 Sol ProE-86f4db4fea47e907XHighRated Interval validated96.02176409 / 2 / 23434 / 4342172 capped draws2026-11-18First try
GPT-5.4E-9879a37f54e31cffXHighRated Interval validated94.62112591 / 21 / 34646 / 64632321 capped draws2026-08-09First try
Gemini 4 ArgonE-c9b7bf650530d8baHighRated Interval validated94.52108602 / 0 / 48650 / 650325—2026-10-21First try
GPT-6.2 Astra ProE-85dd76f643c70002XHighRated Interval validated94.52107397 / 35 / 22454 / 45422735 capped draws2026-11-18First try
Gemini 3.6 FlashE-7484f4e7d8863a3bMediumRated Interval validated94.12092590 / 15 / 43648 / 64832415 capped draws2026-07-24First try
GPT-6 Astra ProE-70601c965e785978XHighRated Interval validated94.12092426 / 11 / 33470 / 47023511 capped draws2026-11-17First try
GPT-6.2 SolE-02f27435ee4f7f39MediumRated Interval validated93.82078596 / 10 / 50656 / 65632810 capped draws2026-11-17First try
Gemini 4 HydrogenE-9e6063f70f796448XHighRated Interval validated93.42066592 / 0 / 56648 / 648324—2026-11-12First try
Claude Fable 5.2E-54829f6a69e69c0fMediumRated Interval validated93.32062592 / 0 / 58650 / 650325—2026-11-09First try
Claude Opus 5.5E-9e6850818d33c592MediumRated Interval validated92.52034560 / 45 / 41646 / 64632345 capped draws2026-09-22First try
GPT-6 AstraE-7fbf151da7860da4LowRated Interval validated92.32031577 / 25 / 52654 / 65432725 capped draws2026-09-05First try
Claude Fable 5.1E-443622d1ef9c6f19XHighRated Interval validated91.72012578 / 2 / 66646 / 6463232 capped draws2026-09-08First try
Particle-1E-2d3bce96a1836811MaxRated Interval validated91.52005564 / 26 / 56646 / 64632326 capped draws2026-11-03First try
Kimi K3.1 ProE-030c793cb8126246MaxRated Interval validated91.42003577 / 1 / 72650 / 6503251 capped draw2026-10-24First try
Claude Opus 5E-700f3dddd611df07XHighRated Interval validated91.11995571 / 6 / 69646 / 6463236 capped draws2026-07-25First try
Ernie 5.5 Flash PreviewE-9d9386c86e5364b7DefaultRated Interval validated90.61982557 / 29 / 64650 / 65032529 capped draws2026-11-12First try
Gemini 4 ArgonE-b29fd1d6479f1bc8LowRated Interval validated90.31974569 / 0 / 79648 / 648324—2026-10-21First try
Claude Opus 5.5E-c6c2699b24183df3LowRated Interval validated89.81960549 / 27 / 70646 / 64632327 capped draws2026-09-22First try