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 | 98.1 | 1 working of 1 attempt | 2359.0 | 587 / 0 / 13 | 98% / 0% / 2% |
| 2 |  Gemini 4 Carbon | High | 97.4 | 1 working of 1 attempt | 2293.9 | 580 / 3 / 17 | 97% / 1% / 3% |
| 3 |  GPT-6 Astra | XHigh | 97.2 | 1 working of 1 attempt | 2278.6 | 580 / 0 / 20 | 97% / 0% / 3% |
| 4 | GPT-5.4 | Medium | 96.8 | 1 working of 1 attempt | 2250.4 | 573 / 8 / 19 | 96% / 1% / 3% |
| 5 | Gemini 4 Carbon | Low | 96.6 | 1 working of 1 attempt | 2241.6 | 576 / 0 / 24 | 96% / 0% / 4% |
| 6 | Gemini 4 Argon | High | 94.9 | 1 working of 1 attempt | 2153.0 | 564 / 0 / 36 | 94% / 0% / 6% |
| 7 | GPT-5.4 | XHigh | 94.7 | 1 working of 1 attempt | 2143.6 | 555 / 15 / 30 | 93% / 3% / 5% |
| 8 | Gemini 4 Hydrogen | XHigh | 93.5 | 1 working of 1 attempt | 2094.9 | 554 / 0 / 46 | 92% / 0% / 8% |
| 9 | Claude Fable 5.2 | Medium | 93.2 | 1 working of 1 attempt | 2084.5 | 552 / 0 / 48 | 92% / 0% / 8% |
| 10 | Claude Opus 5.5 | Medium | 93.0 | 1 working of 1 attempt | 2079.4 | 531 / 40 / 29 | 89% / 7% / 5% |
| 11 | GPT-6 Astra | Low | 92.7 | 1 working of 1 attempt | 2067.0 | 536 / 25 / 39 | 89% / 4% / 7% |
| 12 |  Kimi K3.1 Pro | Max | 92.4 | 1 working of 1 attempt | 2057.3 | 546 / 1 / 53 | 91% / <1% / 9% |
| 13 | Claude Fable 5.1 | XHigh | 91.9 | 1 working of 1 attempt | 2041.2 | 542 / 2 / 56 | 90% / <1% / 9% |
| 14 |  Particle-1 | Max | 91.6 | 1 working of 1 attempt | 2034.4 | 532 / 19 / 49 | 89% / 3% / 8% |
| 15 | Gemini 4 Argon | Low | 91.5 | 1 working of 1 attempt | 2032.2 | 541 / 0 / 59 | 90% / 0% / 10% |
| 16 |  Muse Spark Open | XHigh | 90.5 | 1 working of 1 attempt | 2002.7 | 534 / 0 / 66 | 89% / 0% / 11% |
| 17 |  Pareto 26.10 | Default | 90.5 | 1 working of 1 attempt | 2002.7 | 534 / 0 / 66 | 89% / 0% / 11% |
| 18 | Ernie 5.5 Flash Preview | Default | 90.4 | 1 working of 1 attempt | 2000.7 | 524 / 19 / 57 | 87% / 3% / 10% |
| 19 | Claude Opus 5.5 | Low | 89.9 | 1 working of 1 attempt | 1986.9 | 518 / 24 / 58 | 86% / 4% / 10% |
| 20 | Gemini 3.5 Flash | High | 89.6 | 1 working of 1 attempt | 1981.1 | 518 / 21 / 61 | 86% / 4% / 10% |
| 21 | Gemini 4 Argon | Medium | 89.6 | 1 working of 1 attempt | 1979.2 | 528 / 0 / 72 | 88% / 0% / 12% |
| 22 | Ernie Light Dt 1.0 Intl | Enabled | 88.9 | 1 working of 1 attempt | 1964.4 | 524 / 0 / 76 | 87% / 0% / 13% |
| 23 | Gemini 4 Carbon | Medium | 88.3 | 1 working of 1 attempt | 1950.1 | 520 / 0 / 80 | 87% / 0% / 13% |
| 24 | Claude Fable 5.2 | Low | 87.3 | 1 working of 1 attempt | 1928.0 | 513 / 1 / 86 | 86% / <1% / 14% |
| 25 | Claude Fable 5.1 | Low | 87.0 | 1 working of 1 attempt | 1921.5 | 509 / 5 / 86 | 85% / 1% / 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.
299 player programs.
| Model | Reasoning | Status | Score | Rating | W / D / L | Matches | Opponents | Notes | Generated |
|---|---|---|---|---|---|---|---|---|---|
Claude Fable 5.2E-8ee35c299845147f | XHigh | Rated Interval validated | 98.1 | 2359 | 587 / 0 / 13 | 600 / 600 | 300 | — | 2026-11-09First try |
Gemini 4 CarbonE-8f7c0faa1d26ca79 | High | Rated Interval validated | 97.4 | 2294 | 580 / 3 / 17 | 600 / 600 | 300 | 3 capped draws | 2026-11-12First try |
GPT-6 AstraE-fc5055140bf78475 | XHigh | Rated Interval validated | 97.2 | 2279 | 580 / 0 / 20 | 600 / 600 | 300 | — | 2026-09-05First try |
GPT-5.4E-d4fa7dbb9458c464 | Medium | Rated Interval validated | 96.8 | 2250 | 573 / 8 / 19 | 600 / 600 | 300 | 8 capped draws | 2026-08-09First try |
Gemini 4 CarbonE-3dddac17b1d0d79f | Low | Rated Interval validated | 96.6 | 2242 | 576 / 0 / 24 | 600 / 600 | 300 | — | 2026-11-12First try |
Gemini 4 ArgonE-c9b7bf650530d8ba | High | Rated Interval validated | 94.9 | 2153 | 564 / 0 / 36 | 600 / 600 | 300 | — | 2026-10-21First try |
GPT-5.4E-9879a37f54e31cff | XHigh | Rated Interval validated | 94.7 | 2144 | 555 / 15 / 30 | 600 / 600 | 300 | 15 capped draws | 2026-08-09First try |
Gemini 3.6 FlashE-7484f4e7d8863a3b | Medium | Rated Interval validated | 93.6 | 2098 | 548 / 13 / 39 | 600 / 600 | 300 | 13 capped draws | 2026-07-24First try |
Gemini 4 HydrogenE-9e6063f70f796448 | XHigh | Rated Interval validated | 93.5 | 2095 | 554 / 0 / 46 | 600 / 600 | 300 | — | 2026-11-12First try |
Claude Fable 5.2E-54829f6a69e69c0f | Medium | Rated Interval validated | 93.2 | 2084 | 552 / 0 / 48 | 600 / 600 | 300 | — | 2026-11-09First try |
Claude Opus 5.5E-9e6850818d33c592 | Medium | Rated Interval validated | 93.0 | 2079 | 531 / 40 / 29 | 600 / 600 | 300 | 40 capped draws | 2026-09-22First try |
GPT-6 AstraE-7fbf151da7860da4 | Low | Rated Interval validated | 92.7 | 2067 | 536 / 25 / 39 | 600 / 600 | 300 | 25 capped draws | 2026-09-05First try |
Kimi K3.1 ProE-030c793cb8126246 | Max | Rated Interval validated | 92.4 | 2057 | 546 / 1 / 53 | 600 / 600 | 300 | 1 capped draw | 2026-10-24First try |
Claude Fable 5.1E-443622d1ef9c6f19 | XHigh | Rated Interval validated | 91.9 | 2041 | 542 / 2 / 56 | 600 / 600 | 300 | 2 capped draws | 2026-09-08First try |
Particle-1E-2d3bce96a1836811 | Max | Rated Interval validated | 91.6 | 2034 | 532 / 19 / 49 | 600 / 600 | 300 | 19 capped draws | 2026-11-03First try |
Claude Opus 5E-700f3dddd611df07 | XHigh | Rated Interval validated | 91.5 | 2032 | 538 / 6 / 56 | 600 / 600 | 300 | 6 capped draws | 2026-07-25First try |
Gemini 4 ArgonE-b29fd1d6479f1bc8 | Low | Rated Interval validated | 91.5 | 2032 | 541 / 0 / 59 | 600 / 600 | 300 | — | 2026-10-21First try |
Muse Spark OpenE-482f21724d9e9898 | XHigh | Rated Interval validated | 90.5 | 2003 | 534 / 0 / 66 | 600 / 600 | 300 | — | 2026-10-20First try |
Pareto 26.10E-74fb208ee7158901 | Default | Rated Interval validated | 90.5 | 2003 | 534 / 0 / 66 | 600 / 600 | 300 | — | 2026-10-21First try |
Ernie 5.5 Flash PreviewE-9d9386c86e5364b7 | Default | Rated Interval validated | 90.4 | 2001 | 524 / 19 / 57 | 600 / 600 | 300 | 19 capped draws | 2026-11-12First try |
Claude Opus 5.5E-c6c2699b24183df3 | Low | Rated Interval validated | 89.9 | 1987 | 518 / 24 / 58 | 600 / 600 | 300 | 24 capped draws | 2026-09-22First try |
Gemini 3.5 FlashE-1802f43944b4b6f0 | High | Rated Interval validated | 89.6 | 1981 | 518 / 21 / 61 | 600 / 600 | 300 | 21 capped draws | 2026-09-03First try |
Gemini 4 ArgonE-31ef2459454f5e17 | Medium | Rated Interval validated | 89.6 | 1979 | 528 / 0 / 72 | 600 / 600 | 300 | — | 2026-10-21First try |
Claude Opus 5E-865d68ab219fd7ee | None | Rated Interval validated | 89.3 | 1974 | 490 / 73 / 37 | 600 / 600 | 300 | 73 capped draws | 2026-07-25First try |
Ernie Light Dt 1.0 IntlE-0a2fd8caf734ba5c | Enabled | Rated Interval validated | 88.9 | 1964 | 524 / 0 / 76 | 600 / 600 | 300 | — | 2026-11-12First try |