Reasoning view
GB2-02: Chess
Game profile
Chess
Chess is an 8x8 tactical piece-movement game with asymmetric pieces, castling, en passant, promotion, check, checkmate, and automatic draw rules.
Scores here compare generated programs on DuelLab's encoded rules for Chess; they are not a broad measure of human play strength.
Entrants
Every admitted unique code identity for GB2-02: Chess. Capped draws are rated; unilateral model faults are listed separately.
Showing 23 entrants.
| Entrant | Model | Status | Score | Rating | W / L / D | Rated / attempted | Opponents | Capped draws | Model faults | Admitted plugins | Repair | Generated |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
E-f6a30e7d9986c9b8 | Claude Fable 5 | Rated | 53.6 | 1718 | 93 / 1 / 69 | 163 / 163 | 82 | 0 | 0 | 1 | First pass | 2026-07-03 |
E-0454dbb9530f84f7 | Claude Opus 4.5 | Rated | 13.2 | 1490 | 5 / 8 / 151 | 164 / 164 | 82 | 0 | 0 | 1 | First pass | 2026-07-02 |
E-a81bd03e764818f6 | Claude Opus 4.8 | Rated | 60.3 | 1756 | 103 / 2 / 58 | 163 / 163 | 82 | 0 | 0 | 1 | First pass | 2026-07-03 |
E-e35d82f3fd09a1f4 | Claude Sonnet 5 | Rated | 24.7 | 1555 | 29 / 5 / 129 | 163 / 163 | 82 | 0 | 0 | 1 | First pass | 2026-07-03 |
E-12dcb25370550495 | DeepSeek V4 Flash | Rated | 12.0 | 1483 | 6 / 12 / 146 | 164 / 164 | 82 | 0 | 0 | 1 | Repaired | 2026-07-02 |
E-f2e6dd87c5656ee3 | DeepSeek V4 Flash | Rated | 7.5 | 1458 | 5 / 12 / 145 | 162 / 162 | 81 | 0 | 0 | 1 | First pass | 2026-07-02 |
E-5bccb9b671ce5eae | GPT 5 | Rated | 14.5 | 1497 | 10 / 15 / 139 | 164 / 164 | 82 | 0 | 0 | 1 | First pass | 2026-07-02 |
E-4aa582caf9d9f6da | GPT-5.4 | Rated | 32.9 | 1601 | 54 / 2 / 107 | 163 / 163 | 82 | 0 | 0 | 1 | First pass | 2026-07-02 |
E-59f362f57892ab54 | GPT-5.4 Mini | Rated | 12.2 | 1484 | 3 / 11 / 150 | 164 / 164 | 82 | 0 | 0 | 1 | First pass | 2026-07-02 |
E-7ef67fa468b6c12c | GPT-5.4 Mini | Rated | 18.8 | 1522 | 9 / 13 / 140 | 162 / 162 | 81 | 0 | 0 | 1 | First pass | 2026-07-02 |
E-1ce420518fc32de1 | GPT-5.4 Nano | Rated | 11.7 | 1482 | 2 / 11 / 149 | 162 / 162 | 81 | 0 | 0 | 1 | Repaired | 2026-07-09 |
E-b084ba147f956b49 | GPT-5.4 Nano | Rated | 18.6 | 1521 | 16 / 9 / 138 | 163 / 163 | 82 | 0 | 0 | 1 | Repaired | 2026-07-02 |
E-a30e455ba172d80e | GPT-5.6 Luna | Rated | 9.9 | 1472 | 6 / 11 / 145 | 162 / 162 | 81 | 0 | 0 | 1 | Repaired | 2026-07-10 |
E-33dc9365cfacf9c0 | GPT-5.6 Sol | Rated | 100.0 | 1980 | 147 / 4 / 11 | 162 / 162 | 81 | 0 | 0 | 1 | First pass | 2026-07-10 |
E-1b12482867c807c9 | GPT-5.6 Terra | Rated | 28.1 | 1574 | 37 / 7 / 118 | 162 / 162 | 81 | 0 | 0 | 1 | First pass | 2026-07-10 |
E-2404d10bab26a254 | Nemotron 3 Ultra 550B A55B | Rated | 7.7 | 1459 | 2 / 12 / 150 | 164 / 164 | 82 | 0 | 0 | 1 | Repaired | 2026-07-02 |
E-abd2cae3e3ff9bdb | Nemotron 3 Ultra 550B A55B | Rated | 9.0 | 1467 | 2 / 13 / 147 | 162 / 162 | 81 | 0 | 0 | 1 | Repaired | 2026-07-11 |
E-e5b4a3586049e1c9 | GPT-OSS 120B | Rated | 7.9 | 1460 | 0 / 19 / 144 | 163 / 163 | 82 | 0 | 0 | 1 | Repaired | 2026-07-02 |
E-fbf6af15f65f01d7 | Hy3 Preview | Rated | 8.2 | 1462 | 4 / 23 / 136 | 163 / 164 | 82 | 0 | 0 | 1 | Repaired | 2026-07-02 |
E-9077f1e8e006290b | MiMo-V2.5 | Rated | 11.6 | 1481 | 7 / 8 / 147 | 162 / 162 | 81 | 0 | 0 | 1 | Repaired | 2026-07-02 |
E-4442c0e8a06187bf | GLM-5.2 | Rated | 5.6 | 1448 | 5 / 24 / 133 | 162 / 162 | 81 | 0 | 0 | 1 | Repaired | 2026-07-11 |
E-98394109d97d67ee | GLM-5.2 | Rated | 10.1 | 1472 | 0 / 8 / 156 | 164 / 164 | 82 | 0 | 0 | 1 | Repaired | 2026-07-02 |
E-dd5764d86cd88052 | GLM-5.2 | Rated | 16.2 | 1507 | 21 / 9 / 132 | 162 / 162 | 81 | 0 | 0 | 1 | First pass | 2026-07-02 |
Leaderboard
GB2-02: Chess leaderboard
Entrants are ranked by relative per-game score (0–100). Raw rating is shown as an advanced per-game metric, alongside match record (wins/losses/draws) and a per-game uncertainty index (0–100, fixed scale from rating uncertainty).
Scroll sideways to see every column.
| Rank | Model | Score | Contributing programs | Raw Elo | W / L / D | Uncertainty |
|---|---|---|---|---|---|---|
| 1 |  GPT-5.6 Sol | 100.0 | 1 | 1979.8 | 147/4/11 | 0.0 |
| 2 |  Claude Opus 4.8 | 60.3 | 1 | 1755.8 | 103/2/58 | 0.0 |
| 3 | Claude Fable 5 | 53.6 | 1 | 1717.9 | 93/1/69 | 0.0 |
| 4 | GPT-5.4 | 32.9 | 1 | 1601.2 | 54/2/107 | 0.0 |
| 5 | GPT-5.6 Terra | 28.1 | 1 | 1574.1 | 37/7/118 | 0.0 |
| 6 | Claude Sonnet 5 | 24.7 | 1 | 1555.2 | 29/5/129 | 0.0 |
| 7 | GPT-5.4 Mini | 15.5 | 2 | 1503.0 | 12/24/290 | 0.0 |
| 8 | GPT-5.4 Nano | 15.2 | 2 | 1501.2 | 18/20/287 | 0.0 |
| 9 | GPT 5 | 14.5 | 1 | 1497.4 | 10/15/139 | 0.0 |
| 10 | Claude Opus 4.5 | 13.2 | 1 | 1490.2 | 5/8/151 | 0.0 |
| 11 |  MiMo-V2.5 | 11.6 | 1 | 1481.1 | 7/8/147 | 0.0 |
| 12 |  GLM-5.2 | 10.7 | 3 | 1475.8 | 26/41/421 | 0.0 |
| 13 | GPT-5.6 Luna | 9.9 | 1 | 1471.7 | 6/11/145 | 0.0 |
| 14 |  DeepSeek V4 Flash | 9.7 | 2 | 1470.4 | 11/24/291 | 0.0 |
| 15 |  Nemotron 3 Ultra 550B A55B | 8.4 | 2 | 1462.9 | 4/25/297 | 0.0 |
| 16 |  Hy3 Preview | 8.2 | 1 | 1462.0 | 4/23/136 | 0.0 |
| 17 | GPT-OSS 120B | 7.9 | 1 | 1459.9 | 0/19/144 | 0.0 |