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) |
|---|---|---|---|---|---|---|
| 1 |  Claude Opus 5.5 | XHigh | 96.0 | 1 working of 1 attempt | 2142.9 | 449 / 25 / 6 |
| 2 | Claude Sonnet 5.5 | XHigh | 95.9 | 1 working of 1 attempt | 2137.7 | 450 / 22 / 8 |
| 3 | Claude Opus 5.5 | Medium | 95.8 | 1 working of 1 attempt | 2127.7 | 453 / 14 / 13 |
| 4 |  GPT-6 Astra | XHigh | 95.3 | 1 working of 1 attempt | 2104.4 | 445 / 25 / 10 |
| 5 | Claude Fable 5.1 | XHigh | 95.1 | 1 working of 1 attempt | 2095.6 | 445 / 23 / 12 |
| 6 |  Gemini 4 Argon | High | 94.9 | 1 working of 1 attempt | 2087.1 | 433 / 45 / 2 |
| 7 | GPT-6.1 Sol | XHigh | 94.7 | 1 working of 1 attempt | 2078.9 | 439 / 31 / 10 |
| 8 |  Pareto 26.10 Preview | Provider | 91.6 | 1 working of 1 attempt | 1970.7 | 419 / 38 / 23 |
| 9 | Claude Fable 5.1 | Medium | 91.4 | 1 working of 1 attempt | 1965.4 | 419 / 36 / 25 |
| 10 |  Grok 4.7 | XHigh | 89.1 | 1 working of 1 attempt | 1908.1 | 400 / 50 / 30 |
| 11 | GPT-6 Sol | XHigh | 83.6 | 1 working of 1 attempt | 1806.7 | 333 / 128 / 19 |
| 12 | Claude Fable 5.1 | Low | 83.4 | 1 working of 1 attempt | 1803.6 | 340 / 112 / 28 |
| 13 | Claude Opus 5 | XHigh | 83.4 | 2 working of 2 attempts | 1810.5 program range 1744–1877 | 699 / 186 / 75 |
| 14 | Grok 4.6 | XHigh | 83.3 | 1 working of 1 attempt | 1801.2 | 361 / 67 / 51 |
| 15 |  Kimi K3.1 Pro | Low | 82.6 | 1 working of 1 attempt | 1790.1 | 337 / 109 / 34 |
| 16 | Grok 4.7 | Medium | 81.2 | 1 working of 1 attempt | 1770.2 | 331 / 107 / 42 |
| 17 |  DeepSeek V4.1 Flash 1017 | Max | 81.0 | 1 working of 1 attempt | 1767.5 | 335 / 97 / 48 |
| 18 | GPT-6 Astra | Medium | 81.0 | 1 working of 1 attempt | 1767.5 | 304 / 159 / 17 |
| 19 |  MiMo-V2.6-Pro | Enabled | 80.8 | 1 working of 1 attempt | 1764.7 | 338 / 89 / 53 |
| 20 | Claude Opus 5.5 | Low | 80.2 | 1 working of 1 attempt | 1756.7 | 325 / 109 / 46 |
| 21 | Claude Fable 5 | XHigh | 80.0 | 1 working of 1 attempt | 1754.0 | 316 / 125 / 39 |
| 22 | GPT-6.1 Sol | Medium | 79.7 | 1 working of 1 attempt | 1750.1 | 310 / 134 / 36 |
| 23 | Kimi K3.1 Pro | Max | 79.7 | 1 working of 1 attempt | 1750.1 | 305 / 144 / 31 |
| 24 | Pareto 26.10 | Provider | 79.5 | 1 working of 1 attempt | 1747.5 | 285 / 182 / 13 |
| 25 | Claude Opus 4.8 | XHigh | 79.2 | 1 working of 1 attempt | 1743.7 | 285 / 179 / 16 |
Underlying results
Individual player programs
Each row is one accepted player program for GB2-02: Chess; 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.
241 player programs.
| Model | Reasoning | Status | Score | Rating | W / D / L | Matches | Opponents | Notes | Generated |
|---|---|---|---|---|---|---|---|---|---|
Claude Opus 5.5E-8da2a605b97075fa | XHigh | Rated Interval validated | 96.0 | 2143 | 449 / 25 / 6 | 480 / 480 | 240 | — | 2026-09-22First try |
Claude Sonnet 5.5E-25c4c1579034e616 | XHigh | Rated Interval validated | 95.9 | 2138 | 450 / 22 / 8 | 480 / 480 | 240 | — | 2026-09-30First try |
Claude Opus 5.5E-4692bc19babebbb1 | Medium | Rated Interval validated | 95.8 | 2128 | 453 / 14 / 13 | 480 / 480 | 240 | — | 2026-09-22Repaired |
GPT-6 AstraE-c91ee6859ab8877e | XHigh | Rated Interval validated | 95.3 | 2104 | 445 / 25 / 10 | 480 / 480 | 240 | — | 2026-09-05First try |
Claude Fable 5.1E-f86f2f46e2c71b4a | XHigh | Rated Interval validated | 95.1 | 2096 | 445 / 23 / 12 | 480 / 480 | 240 | — | 2026-09-08First try |
Gemini 4 ArgonE-35eb3b86b76e7c9f | High | Rated Interval validated | 94.9 | 2087 | 433 / 45 / 2 | 480 / 480 | 240 | — | 2026-10-21Repaired |
GPT-6.1 SolE-755187947384baf1 | XHigh | Rated Interval validated | 94.7 | 2079 | 439 / 31 / 10 | 480 / 480 | 240 | — | 2026-10-01First try |
Pareto 26.10 PreviewE-e13381315ea87cb7 | Provider | Rated Interval validated | 91.6 | 1971 | 419 / 38 / 23 | 480 / 480 | 240 | — | 2026-10-09First try |
Claude Fable 5.1E-f4d4ba39a6f2270e | Medium | Rated Interval validated | 91.4 | 1965 | 419 / 36 / 25 | 480 / 480 | 240 | — | 2026-09-03First try |
Grok 4.7E-ba03a6f2135ea911 | XHigh | Rated Interval validated | 89.1 | 1908 | 400 / 50 / 30 | 480 / 480 | 240 | — | 2026-09-30First try |
Claude Opus 5E-fcdd98d74e80134a | XHigh | Rated Interval validated | 87.6 | 1877 | 398 / 39 / 43 | 480 / 480 | 240 | — | 2026-07-25First try |
GPT-6 SolE-6b0e5cea9d2e9834 | XHigh | Rated Interval validated | 83.6 | 1807 | 333 / 128 / 19 | 480 / 480 | 240 | — | 2026-09-22First try |
Claude Fable 5.1E-85e618bbeae3eac9 | Low | Rated Interval validated | 83.4 | 1804 | 340 / 112 / 28 | 480 / 480 | 240 | — | 2026-09-03First try |
Grok 4.6E-892d7d5eef11e96c | XHigh | Rated | 83.3 | 1801 | 361 / 67 / 51 | 479 / 480 | 240 | — | 2026-09-03First try |
Kimi K3.1 ProE-313ef2e01b0b5aa0 | Low | Rated Interval validated | 82.6 | 1790 | 337 / 109 / 34 | 480 / 480 | 240 | — | 2026-10-24First try |
Ox AlphaE-f1feaabe79bde601 | Max | Rated Interval validated | 81.4 | 1773 | 332 / 107 / 41 | 480 / 480 | 240 | — | 2026-08-22First try |
Grok 4.7E-f95475f736abba79 | Medium | Rated Interval validated | 81.2 | 1770 | 331 / 107 / 42 | 480 / 480 | 240 | — | 2026-09-30First try |
DeepSeek V4.1 Flash 1017E-5e795839a2bce09c | Max | Rated Interval validated | 81.0 | 1767 | 335 / 97 / 48 | 480 / 480 | 240 | — | 2026-10-20First try |
GPT-6 AstraE-db1b6aef6e22ec35 | Medium | Rated Interval validated | 81.0 | 1767 | 304 / 159 / 17 | 480 / 480 | 240 | — | 2026-09-05First try |
MiMo-V2.6-ProE-1f38c6901db3b289 | Enabled | Rated Interval validated | 80.8 | 1765 | 338 / 89 / 53 | 480 / 480 | 240 | — | 2026-10-09First try |
Claude Opus 5.5E-62dc1bc5d810f032 | Low | Rated Interval validated | 80.2 | 1757 | 325 / 109 / 46 | 480 / 480 | 240 | — | 2026-09-22First try |
Claude Fable 5E-81d43b992e6c0688 | XHigh | Rated Interval validated | 80.0 | 1754 | 316 / 125 / 39 | 480 / 480 | 240 | — | 2026-09-03First try |
GPT-6.1 SolE-b47e7dbaa385511b | Medium | Rated Interval validated | 79.7 | 1750 | 310 / 134 / 36 | 480 / 480 | 240 | — | 2026-10-01Repaired |
Kimi K3.1 ProE-720c521b1c9dc2f9 | Max | Rated Interval validated | 79.7 | 1750 | 305 / 144 / 31 | 480 / 480 | 240 | — | 2026-10-24First try |
Pareto 26.10E-8654127bce1e8642 | Provider | Rated Interval validated | 79.5 | 1748 | 285 / 182 / 13 | 480 / 480 | 240 | — | 2026-10-21First try |