Leaderboard
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.
| Rank | Model | Reasoning | Score | Programs | Raw rating | Combined record (W / D / L) | W / D / L % |
|---|---|---|---|---|---|---|---|
| 1 |  Claude Fable 5.2 | XHigh | 97.6 | 1 working of 1 attempt | 2329.4 | 551 / 0 / 13 | 98% / 0% / 2% |
| 2 |  GPT-5.4 | Medium | 97.3 | 1 working of 1 attempt | 2303.7 | 545 / 8 / 11 | 97% / 1% / 2% |
| 3 | GPT-6 Astra | XHigh | 96.9 | 1 working of 1 attempt | 2269.6 | 546 / 0 / 18 | 97% / 0% / 3% |
| 4 |  Gemini 4 Argon | High | 94.9 | 1 working of 1 attempt | 2165.0 | 534 / 0 / 30 | 95% / 0% / 5% |
| 5 | GPT-5.4 | XHigh | 94.8 | 1 working of 1 attempt | 2161.4 | 526 / 15 / 23 | 93% / 3% / 4% |
| 6 | Claude Fable 5.2 | Medium | 93.4 | 1 working of 1 attempt | 2106.0 | 525 / 0 / 39 | 93% / 0% / 7% |
| 7 | Claude Opus 5.5 | Medium | 92.4 | 1 working of 1 attempt | 2072.2 | 499 / 40 / 25 | 88% / 7% / 4% |
| 8 | GPT-6 Astra | Low | 92.1 | 1 working of 1 attempt | 2061.7 | 505 / 24 / 35 | 90% / 4% / 6% |
| 9 |  Kimi K3.1 Pro | Max | 92.0 | 1 working of 1 attempt | 2059.1 | 516 / 1 / 47 | 91% / <1% / 8% |
| 10 | Claude Fable 5.1 | XHigh | 91.9 | 1 working of 1 attempt | 2056.6 | 515 / 2 / 47 | 91% / <1% / 8% |
| 11 | Gemini 4 Argon | Low | 91.7 | 1 working of 1 attempt | 2051.6 | 515 / 0 / 49 | 91% / 0% / 9% |
| 12 |  Particle-1 | Max | 91.3 | 1 working of 1 attempt | 2039.3 | 503 / 19 / 42 | 89% / 3% / 7% |
| 13 |  Muse Spark Open | XHigh | 91.1 | 1 working of 1 attempt | 2032.2 | 511 / 0 / 53 | 91% / 0% / 9% |
| 14 |  Pareto 26.10 | Default | 90.1 | 1 working of 1 attempt | 2005.1 | 505 / 0 / 59 | 90% / 0% / 10% |
| 15 | Gemini 3.5 Flash | High | 89.8 | 1 working of 1 attempt | 1998.6 | 493 / 21 / 50 | 87% / 4% / 9% |
| 16 | Gemini 4 Argon | Medium | 89.5 | 1 working of 1 attempt | 1992.3 | 502 / 0 / 62 | 89% / 0% / 11% |
| 17 | Claude Opus 5.5 | Low | 88.9 | 1 working of 1 attempt | 1978.0 | 487 / 23 / 54 | 86% / 4% / 10% |
| 18 | Claude Fable 5.2 | Low | 87.4 | 1 working of 1 attempt | 1943.7 | 489 / 1 / 74 | 87% / <1% / 13% |
| 19 | Claude Fable 5.1 | Low | 87.1 | 1 working of 1 attempt | 1938.3 | 486 / 4 / 74 | 86% / 1% / 13% |
| 20 | Muse Spark 1.2 | Medium | 84.7 | 1 working of 1 attempt | 1891.3 | 460 / 28 / 76 | 82% / 5% / 13% |
| 21 | Claude Fable 5 | XHigh | 84.1 | 1 working of 1 attempt | 1880.4 | 470 / 1 / 93 | 83% / <1% / 16% |
| 22 | Muse Wonder | XHigh | 83.0 | 1 working of 1 attempt | 1860.9 | 460 / 8 / 96 | 82% / 1% / 17% |
| 23 |  Grok 4.5 | High | 82.3 | 1 working of 1 attempt | 1849.4 | 402 / 116 / 46 | 71% / 21% / 8% |
| 24 | Claude Opus 5.5 | XHigh | 82.1 | 1 working of 1 attempt | 1846.5 | 454 / 10 / 100 | 80% / 2% / 18% |
| 25 | Grok 4.5 | Medium | 81.9 | 1 working of 1 attempt | 1843.7 | 433 / 50 / 81 | 77% / 9% / 14% |
Underlying results
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.
281 player programs.
| Model | Reasoning | Status | Score | Rating | W / D / L | Matches | Opponents | Notes | Generated |
|---|---|---|---|---|---|---|---|---|---|
Claude Fable 5.2E-8ee35c299845147f | XHigh | Rated Interval validated | 97.6 | 2329 | 551 / 0 / 13 | 564 / 564 | 282 | — | 2026-11-09First try |
GPT-5.4E-d4fa7dbb9458c464 | Medium | Rated Interval validated | 97.3 | 2304 | 545 / 8 / 11 | 564 / 564 | 282 | 8 capped draws | 2026-08-09First try |
GPT-6 AstraE-fc5055140bf78475 | XHigh | Rated Interval validated | 96.9 | 2270 | 546 / 0 / 18 | 564 / 564 | 282 | — | 2026-09-05First try |
Gemini 4 ArgonE-c9b7bf650530d8ba | High | Rated Interval validated | 94.9 | 2165 | 534 / 0 / 30 | 564 / 564 | 282 | — | 2026-10-21First try |
GPT-5.4E-9879a37f54e31cff | XHigh | Rated Interval validated | 94.8 | 2161 | 526 / 15 / 23 | 564 / 564 | 282 | 15 capped draws | 2026-08-09First try |
Claude Fable 5.2E-54829f6a69e69c0f | Medium | Rated Interval validated | 93.4 | 2106 | 525 / 0 / 39 | 564 / 564 | 282 | — | 2026-11-09First try |
Gemini 3.6 FlashE-7484f4e7d8863a3b | Medium | Rated Interval validated | 93.2 | 2097 | 517 / 13 / 34 | 564 / 564 | 282 | 13 capped draws | 2026-07-24First try |
Claude Opus 5.5E-9e6850818d33c592 | Medium | Rated Interval validated | 92.4 | 2072 | 499 / 40 / 25 | 564 / 564 | 282 | 40 capped draws | 2026-09-22First try |
GPT-6 AstraE-7fbf151da7860da4 | Low | Rated Interval validated | 92.1 | 2062 | 505 / 24 / 35 | 564 / 564 | 282 | 24 capped draws | 2026-09-05First try |
Kimi K3.1 ProE-030c793cb8126246 | Max | Rated Interval validated | 92.0 | 2059 | 516 / 1 / 47 | 564 / 564 | 282 | 1 capped draw | 2026-10-24First try |
Claude Fable 5.1E-443622d1ef9c6f19 | XHigh | Rated Interval validated | 91.9 | 2057 | 515 / 2 / 47 | 564 / 564 | 282 | 2 capped draws | 2026-09-08First try |
Gemini 4 ArgonE-b29fd1d6479f1bc8 | Low | Rated Interval validated | 91.7 | 2052 | 515 / 0 / 49 | 564 / 564 | 282 | — | 2026-10-21First try |
Claude Opus 5E-700f3dddd611df07 | XHigh | Rated Interval validated | 91.4 | 2042 | 510 / 6 / 48 | 564 / 564 | 282 | 6 capped draws | 2026-07-25First try |
Particle-1E-2d3bce96a1836811 | Max | Rated Interval validated | 91.3 | 2039 | 503 / 19 / 42 | 564 / 564 | 282 | 19 capped draws | 2026-11-03First try |
Muse Spark OpenE-482f21724d9e9898 | XHigh | Rated Interval validated | 91.1 | 2032 | 511 / 0 / 53 | 564 / 564 | 282 | — | 2026-10-20First try |
Pareto 26.10E-74fb208ee7158901 | Default | Rated Interval validated | 90.1 | 2005 | 505 / 0 / 59 | 564 / 564 | 282 | — | 2026-10-21First try |
Gemini 3.5 FlashE-1802f43944b4b6f0 | High | Rated Interval validated | 89.8 | 1999 | 493 / 21 / 50 | 564 / 564 | 282 | 21 capped draws | 2026-09-03First try |
Gemini 4 ArgonE-31ef2459454f5e17 | Medium | Rated Interval validated | 89.5 | 1992 | 502 / 0 / 62 | 564 / 564 | 282 | — | 2026-10-21First try |
Claude Opus 5.5E-c6c2699b24183df3 | Low | Rated Interval validated | 88.9 | 1978 | 487 / 23 / 54 | 564 / 564 | 282 | 23 capped draws | 2026-09-22First try |
Claude Opus 5E-865d68ab219fd7ee | None | Rated Interval validated | 88.8 | 1974 | 462 / 71 / 31 | 564 / 564 | 282 | 71 capped draws | 2026-07-25First try |
Claude Fable 5.2E-4bcaac6c35a144b7 | Low | Rated Interval validated | 87.4 | 1944 | 489 / 1 / 74 | 564 / 564 | 282 | 1 capped draw | 2026-11-09First try |
Claude Fable 5.1E-d04c4d8635b641f9 | Low | Rated Interval validated | 87.1 | 1938 | 486 / 4 / 74 | 564 / 564 | 282 | 4 capped draws | 2026-09-03First try |
Muse Spark 1.2E-052cdf1e5975b860 | Medium | Rated Interval validated | 84.7 | 1891 | 460 / 28 / 76 | 564 / 564 | 282 | 28 capped draws | 2026-08-13First try |
Claude Fable 5E-99c76fc062487714 | XHigh | Rated Interval validated | 84.1 | 1880 | 470 / 1 / 93 | 564 / 564 | 282 | 1 capped draw | 2026-09-03First try |
Muse WonderE-5c48ba07caee5554 | XHigh | Rated Interval validated | 83.0 | 1861 | 460 / 8 / 96 | 564 / 564 | 282 | 8 capped draws | 2026-10-12First try |