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 | XHigh | 99.7 | 1 working of 1 attempt | 3017.2 | 584 / 0 / 0 | 100% / 0% / 0% | |
| 2 | XHigh | 99.4 | 1 working of 1 attempt | 2827.0 | 579 / 2 / 3 | 99% / <1% / 1% | |
| 3 | High | 99.1 | 1 working of 1 attempt | 2747.4 | 575 / 5 / 4 | 98% / 1% / 1% | |
| 4 | XHigh | 99.0 | 1 working of 1 attempt | 2733.6 | 577 / 0 / 7 | 99% / 0% / 1% | |
| 5 | XHigh | 98.0 | 1 working of 1 attempt | 2578.9 | 567 / 5 / 12 | 97% / 1% / 2% | |
| 6 | High | 96.6 | 1 working of 1 attempt | 2463.2 | 554 / 13 / 17 | 95% / 2% / 3% | |
| 7 | Low | 93.6 | 1 working of 1 attempt | 2309.0 | 529 / 24 / 31 | 91% / 4% / 5% | |
| 8 | Default | 91.7 | 1 working of 1 attempt | 2244.3 | 517 / 25 / 42 | 89% / 4% / 7% | |
| 9 | XHigh | 91.3 | 1 working of 1 attempt | 2231.6 | 513 / 28 / 43 | 88% / 5% / 7% | |
| 10 | Medium | 91.3 | 1 working of 1 attempt | 2231.6 | 515 / 24 / 45 | 88% / 4% / 8% | |
| 11 | Low | 90.9 | 1 working of 1 attempt | 2219.3 | 516 / 17 / 51 | 88% / 3% / 9% | |
| 12 | Medium | 90.5 | 1 working of 1 attempt | 2205.1 | 512 / 19 / 53 | 88% / 3% / 9% | |
| 13 | High | 90.5 | 1 working of 1 attempt | 2205.1 | 507 / 29 / 48 | 87% / 5% / 8% | |
| 14 | Medium | 90.4 | 1 working of 1 attempt | 2202.8 | 499 / 44 / 41 | 85% / 8% / 7% | |
| 15 | XHigh | 90.4 | 1 working of 1 attempt | 2202.8 | 511 / 20 / 53 | 88% / 3% / 9% | |
| 16 | XHigh | 90.4 | 1 working of 1 attempt | 2202.8 | 503 / 36 / 45 | 86% / 6% / 8% | |
| 17 | High | 90.3 | 1 working of 1 attempt | 2200.4 | 505 / 31 / 48 | 86% / 5% / 8% | |
| 18 | XHigh | 90.2 | 1 working of 1 attempt | 2195.9 | 499 / 41 / 44 | 85% / 7% / 8% | |
| 19 | Medium | 90.0 | 1 working of 1 attempt | 2191.3 | 503 / 31 / 50 | 86% / 5% / 9% | |
| 20 | Medium | 89.7 | 1 working of 1 attempt | 2182.4 | 504 / 25 / 55 | 86% / 4% / 9% | |
| 21 | Low | 89.4 | 1 working of 1 attempt | 2173.6 | 501 / 27 / 56 | 86% / 5% / 10% | |
| 22 | Medium | 89.0 | 1 working of 1 attempt | 2165.0 | 504 / 17 / 63 | 86% / 3% / 11% | |
| 23 | Max | 89.0 | 1 working of 1 attempt | 2165.0 | 493 / 39 / 52 | 84% / 7% / 9% | |
| 24 | XHigh | 88.9 | 1 working of 1 attempt | 2160.7 | 505 / 13 / 66 | 86% / 2% / 11% | |
| 25 | Medium | 88.4 | 1 working of 1 attempt | 2148.2 | 496 / 25 / 63 | 85% / 4% / 11% |
Underlying results
Individual player programs
Each row is one accepted player program for GB2-06: International Draughts; 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.
292 player programs.
| Model | Reasoning | Status | Score | Rating | W / D / L | Matches | Opponents | Notes | Generated |
|---|---|---|---|---|---|---|---|---|---|
Claude Fable 5.2E-24b55f22d86d7a18 | XHigh | Rated Interval validated | 99.7 | 3017 | 584 / 0 / 0 | 584 / 584 | 292 | — | 2026-11-09First try |
Claude Opus 5.5E-53134a8de9454448 | XHigh | Rated Interval validated | 99.4 | 2827 | 579 / 2 / 3 | 584 / 584 | 292 | — | 2026-09-22First try |
Gemini 4 CarbonE-e9aac1a0e7f7caa7 | High | Rated Interval validated | 99.1 | 2747 | 575 / 5 / 4 | 584 / 584 | 292 | — | 2026-11-12First try |
Gemini 4 HydrogenE-48bcbced49818817 | XHigh | Rated Interval validated | 99.0 | 2734 | 577 / 0 / 7 | 584 / 584 | 292 | — | 2026-11-12First try |
Claude Fable 5.1E-bba525f4f6adfed4 | XHigh | Rated Interval validated | 98.0 | 2579 | 567 / 5 / 12 | 584 / 584 | 292 | 1 capped draw | 2026-09-08First try |
Gemini 4 ArgonE-ec915524f0712927 | High | Rated Interval validated | 96.6 | 2463 | 554 / 13 / 17 | 584 / 584 | 292 | — | 2026-10-21Repaired |
Claude Fable 5.2E-75b7eb3d343354e6 | Low | Rated Interval validated | 93.6 | 2309 | 529 / 24 / 31 | 584 / 584 | 292 | 9 capped draws | 2026-11-09First try |
Pareto 26.10E-5d01b5fd5968de69 | Default | Rated Interval validated | 91.7 | 2244 | 517 / 25 / 42 | 584 / 584 | 292 | 3 capped draws | 2026-10-21First try |
Claude Haiku 5.5E-7508ffbcb30ce9d7 | XHigh | Rated Interval validated | 91.3 | 2232 | 513 / 28 / 43 | 584 / 584 | 292 | 6 capped draws | 2026-10-09First try |
GPT-6.1 Terra ProE-e1b1e3f73d88104c | Medium | Rated Interval validated | 91.3 | 2232 | 515 / 24 / 45 | 584 / 584 | 292 | 4 capped draws | 2026-11-01First try |
Kimi K3.1 ProE-65169852dc5bea55 | Low | Rated Interval validated | 90.9 | 2219 | 516 / 17 / 51 | 584 / 584 | 292 | 6 capped draws | 2026-10-24First try |
Claude Opus 5.5E-cb36bcb6ba10266b | Medium | Rated Interval validated | 90.5 | 2205 | 512 / 19 / 53 | 584 / 584 | 292 | 4 capped draws | 2026-09-22First try |
GLM-5.3E-256f22a4f85c8ce5 | High | Rated Interval validated | 90.5 | 2205 | 507 / 29 / 48 | 584 / 584 | 292 | 6 capped draws | 2026-09-03First try |
GPT-6.1 TerraE-312f19e7cdaaeff5 | XHigh | Rated Interval validated | 90.4 | 2203 | 511 / 20 / 53 | 584 / 584 | 292 | 6 capped draws | 2026-11-01First try |
GPT-6.1 TerraE-c4542a0a341b2146 | Medium | Rated Interval validated | 90.4 | 2203 | 499 / 44 / 41 | 584 / 584 | 292 | 13 capped draws | 2026-11-01First try |
GPT-6.1 Terra ProE-4b426f92084ee8ca | XHigh | Rated Interval validated | 90.4 | 2203 | 503 / 36 / 45 | 584 / 584 | 292 | 9 capped draws | 2026-11-01First try |
Kimi K3.1 ProE-02f59a1e4530ae4d | High | Rated Interval validated | 90.3 | 2200 | 505 / 31 / 48 | 584 / 584 | 292 | 7 capped draws | 2026-10-24First try |
Claude Sonnet 5.5E-33fb3ee55eb8f02f | XHigh | Rated Interval validated | 90.2 | 2196 | 499 / 41 / 44 | 584 / 584 | 292 | — | 2026-09-30First try |
Gemini 4 ArgonE-670f358c134cd627 | Medium | Rated Interval validated | 90.0 | 2191 | 503 / 31 / 50 | 584 / 584 | 292 | 7 capped draws | 2026-10-21First try |
GPT-6.1 SolE-a4495c1439ca4ab3 | Medium | Rated Interval validated | 89.7 | 2182 | 504 / 25 / 55 | 584 / 584 | 292 | 5 capped draws | 2026-10-01First try |
Nex N2.6E-1f2335b1989b8170 | Low | Rated Interval validated | 89.4 | 2174 | 501 / 27 / 56 | 584 / 584 | 292 | 4 capped draws | 2026-11-12First try |
Gemini 4 CarbonE-fc544518b11cd5de | Medium | Rated Interval validated | 89.0 | 2165 | 504 / 17 / 63 | 584 / 584 | 292 | 1 capped draw | 2026-11-12First try |
GLM-5.3E-206af7e7704349b5 | Max | Rated Interval validated | 89.0 | 2165 | 493 / 39 / 52 | 584 / 584 | 292 | — | 2026-10-09First try |
Grok 4.7E-c0e64450a9e18936 | XHigh | Rated Interval validated | 88.9 | 2161 | 505 / 13 / 66 | 584 / 584 | 292 | 1 capped draw | 2026-09-30Repaired |
Gemini 3.6 FlashE-905531e52a8460f5 | High | Rated Interval validated | 88.5 | 2150 | 506 / 6 / 72 | 584 / 584 | 292 | 2 capped draws | 2026-07-24Repaired |