Reasoning view
GB2-06: International Draughts
Game profile
International Draughts
International Draughts is a 10x10 capture game with mandatory maximum captures, backward captures by men, flying kings, promotion, and automatic draw rules.
Scores here compare player programs using DuelLab's encoded rules for International Draughts; they are not a broad measure of human play strength.
By model and setting
GB2-06: International Draughts by model and setting
Player programs are ranked by relative per-game score (0–100). Raw rating is shown as an advanced metric, alongside wins, draws, losses, and a per-game uncertainty index.
| Rank | Model | Score | Contributing programs | Raw Elo | W / D / L | Uncertainty |
|---|---|---|---|---|---|---|
| 1 |  GPT-5.6 Sol | 93.2 | 1 | 2004.1 | 83 / 6 / 1 | 8.7 |
| 2 |  Gemini 3.6 Flash | 91.6 | 2 | 1975.6 | 248 / 13 / 37 | 0.0 |
| 3 | GPT-5.4 | 89.3 | 1 | 1956.2 | 87 / 3 / 6 | 7.0 |
| 4 |  Claude Fable 5 | 86.4 | 1 | 1929.4 | 57 / 5 / 6 | 16.4 |
| 5 | GPT-5.6 Luna | 83.1 | 1 | 1884.5 | 72 / 8 / 9 | 9.0 |
| 6 | GPT-5.5 | 82.5 | 1 | 1884.0 | 54 / 3 / 11 | 16.4 |
| 7 | Gemini 3.5 Flash | 80.8 | 1 | 1864.5 | 52 / 1 / 13 | 17.3 |
| 8 | Claude Opus 4.8 | 79.5 | 1 | 1849.6 | 52 / 2 / 8 | 19.2 |
| 9 | GPT-5.6 Terra | 74.2 | 1 | 1782.5 | 50 / 0 / 24 | 14.0 |
| 10 | GPT 5 | 67.7 | 1 | 1705.1 | 44 / 6 / 26 | 13.2 |
| 11 | GPT-OSS 120B | 67.3 | 1 | 1701.3 | 43 / 6 / 25 | 14.0 |
| 12 | Claude Opus 4.5 | 60.9 | 1 | 1609.5 | 90 / 16 / 64 | 0.0 |
| 13 |  Inkling | 60.5 | 1 | 1606.4 | 78 / 8 / 68 | 0.0 |
| 14 |  MiMo-V2.5 | 58.6 | 1 | 1600.8 | 33 / 5 / 26 | 18.3 |
| 15 |  Grok 4.5 | 56.1 | 1 | 1552.2 | 87 / 12 / 75 | 0.0 |
| 16 | Inkling Small | 55.4 | 1 | 1610.2 | 14 / 0 / 2 | 77.5 |
| 17 | Ox Alpha | 52.1 | 3 | 1577.0 | 28 / 6 / 8 | 85.3 |
| 18 | O3 | 51.2 | 4 | 1496.4 | 286 / 17 / 280 | 0.0 |
| 19 |  Qwen3.8 Max | 47.9 | 1 | 1524.6 | 8 / 0 / 7 | 81.2 |
| 20 | Gemini 3.5 Flash Lite | 47.0 | 2 | 1446.5 | 129 / 12 / 147 | 0.0 |
| 21 |  Step 3.7 Flash | 46.6 | 1 | 1450.1 | 38 / 2 / 50 | 8.7 |
| 22 |  DeepSeek V4 Pro | 43.6 | 1 | 1412.3 | 48 / 2 / 54 | 5.0 |
| 23 |  Nemotron 3 Ultra 550B A55B | 43.3 | 1 | 1413.6 | 25 / 6 / 50 | 11.5 |
| 24 | Claude Sonnet 5 | 33.3 | 1 | 1292.3 | 23 / 5 / 64 | 8.1 |
| 25 | Gemini 3.1 Flash Lite | 32.5 | 1 | 1285.1 | 27 / 0 / 56 | 10.8 |
| 26 | DeepSeek V4 Flash | 31.5 | 1 | 1275.7 | 21 / 1 / 50 | 14.8 |
| 27 |  Mistral Medium 3.5 | 31.1 | 1 | 1269.4 | 26 / 0 / 54 | 11.8 |
| 28 |  Hy3 Preview | 30.1 | 1 | 1258.0 | 23 / 0 / 55 | 12.5 |
Underlying results
Individual player programs
Each row is one accepted player program for GB2-06: International Draughts. A model can appear more than once when it produced more than one program. Score is the normalized 0–100 result; Elo and W / D / L show the underlying play record. Confidence and evidence can be blank when too few compatible matches are available. Draws at the move limit count; one-sided model faults are listed separately.
Showing 36 player programs.
| Player ID | Model | Status | Score | Elo | Confidence | W / D / L | Rated / attempted | Opponents | Capped draws | Faults / players | Generation |
|---|---|---|---|---|---|---|---|---|---|---|---|
| E-499fbc92ee0778fb | Claude Fable 5 | Rated | 86.4 | 1929 | — | 57 / 5 / 6 | 68 / 68 | 32 | 0 | 0 / 1 | Repaired · 2026-07-02 |
| E-41f8f2b491917557 | Claude Opus 4.5 | Waiting | — | — | — | 0 / 0 / 0 | 0 / 0 | 0 | 0 | 0 / 1 | Repaired · 2026-07-02 |
| E-df9bde92610963b7 | Claude Opus 4.5 | Rated | 60.9 | 1609 | — | 90 / 16 / 64 | 170 / 170 | 60 | 0 | 0 / 1 | First try · 2026-07-21 |
| E-e804041031295d93 | Claude Opus 4.8 | Rated | 79.5 | 1850 | — | 52 / 2 / 8 | 62 / 62 | 30 | 0 | 0 / 1 | First try · 2026-07-03 |
| E-c4133ea4f4d4dfb9 | Claude Sonnet 5 | Rated | 33.3 | 1292 | — | 23 / 5 / 64 | 92 / 92 | 42 | 0 | 0 / 1 | First try · 2026-08-09 |
| E-5f5fd61f4544b8d7 | DeepSeek V4 Flash | Rated | 31.5 | 1276 | — | 21 / 1 / 50 | 72 / 72 | 34 | 0 | 0 / 1 | First try · 2026-07-02 |
| E-c9778645f1bbd12c | DeepSeek V4 Pro | Rated | 43.6 | 1412 | — | 48 / 2 / 54 | 104 / 104 | 51 | 0 | 0 / 1 | First try · 2026-07-02 |
| E-6238c7d8dc9e77d9 | Gemini 3.1 Flash Lite | Rated | 32.5 | 1285 | — | 27 / 0 / 56 | 83 / 83 | 40 | 0 | 0 / 1 | Repaired · 2026-07-02 |
| E-5dcb27eaa0273049 | Gemini 3.5 Flash | Rated | 80.8 | 1865 | — | 52 / 1 / 13 | 66 / 66 | 32 | 0 | 0 / 1 | Repaired · 2026-07-02 |
| E-09a450a1726f909a | Gemini 3.5 Flash Lite | Rated | 23.2 | 1164 | — | 36 / 0 / 106 | 142 / 142 | 50 | 0 | 0 / 1 | First try · 2026-07-24 |
| E-48cc2611d5aa8816 | Gemini 3.5 Flash Lite | Rated | 70.8 | 1729 | — | 93 / 12 / 41 | 146 / 146 | 53 | 0 | 0 / 1 | Repaired · 2026-07-24 |
| E-280a7de63c992141 | Gemini 3.6 Flash | Rated | 83.1 | 1875 | — | 117 / 11 / 28 | 156 / 156 | 62 | 0 | 0 / 1 | Repaired · 2026-07-24 |
| E-905531e52a8460f5 | Gemini 3.6 Flash | Rated | 100.0 | 2077 | — | 131 / 2 / 9 | 142 / 142 | 54 | 0 | 0 / 1 | Repaired · 2026-07-24 |
| E-1b082700b3692175 | GPT 5 | Rated | 67.7 | 1705 | — | 44 / 6 / 26 | 76 / 76 | 36 | 0 | 0 / 1 | Repaired · 2026-07-02 |
| E-5032a25edce1eb13 | GPT-5.4 | Rated | 89.3 | 1956 | — | 87 / 3 / 6 | 96 / 96 | 43 | 0 | 0 / 1 | First try · 2026-08-09 |
| E-4175a77ccf4c269b | GPT-5.5 | Rated | 82.5 | 1884 | — | 54 / 3 / 11 | 68 / 68 | 33 | 0 | 0 / 1 | First try · 2026-07-02 |
| E-d8cf92ac05965d5e | GPT-5.6 Luna | Rated | 83.1 | 1884 | — | 72 / 8 / 9 | 89 / 90 | 42 | 0 | 0 / 1 | First try · 2026-08-09 |
| E-edb238a0d9a72c9f | GPT-5.6 Sol | Rated | 93.2 | 2004 | — | 83 / 6 / 1 | 90 / 90 | 43 | 0 | 0 / 1 | First try · 2026-08-09 |
| E-e6571a10c1120fab | GPT-5.6 Terra | Rated | 74.2 | 1783 | — | 50 / 0 / 24 | 74 / 74 | 36 | 0 | 0 / 1 | First try · 2026-07-10 |
| E-6c35f5ff426e7ada | Mistral Medium 3.5 | Rated | 31.1 | 1269 | — | 26 / 0 / 54 | 80 / 80 | 39 | 0 | 0 / 1 | Repaired · 2026-07-02 |
| E-ba2fb1c121873708 | Nemotron 3 Ultra 550B A55B | Rated | 43.3 | 1414 | — | 25 / 6 / 50 | 81 / 81 | 41 | 0 | 0 / 1 | Repaired · 2026-07-11 |
| E-2c94ff7a30958259 | O3 | Rated | 57.5 | 1570 | — | 82 / 4 / 62 | 148 / 148 | 50 | 0 | 0 / 1 | First try · 2026-07-03 |
| E-35751e26cd4e995d | O3 | Rated | 52.9 | 1516 | — | 82 / 3 / 64 | 149 / 149 | 51 | 0 | 0 / 1 | First try · 2026-07-03 |
| E-432424671c9fea1c | O3 | Rated | 28.6 | 1228 | — | 35 / 6 / 103 | 144 / 144 | 51 | 0 | 0 / 1 | First try · 2026-07-02 |
| E-ead4229a85e5d554 | O3 | Rated | 65.9 | 1671 | — | 87 / 4 / 51 | 142 / 142 | 49 | 0 | 0 / 1 | First try · 2026-07-03 |
| E-a97b527d9b41a80c | GPT-OSS 120B | Rated | 67.3 | 1701 | — | 43 / 6 / 25 | 74 / 74 | 36 | 0 | 0 / 1 | Repaired · 2026-07-02 |
| E-7a5171930c689e38 | Qwen3.8 Max | Limited data | 47.9 | 1525 | — | 8 / 0 / 7 | 15 / 15 | 9 | 0 | 0 / 1 | First try · 2026-08-18 |
| E-2f1a60fc993600a0 | Ox Alpha | Rated | 57.0 | 1635 | — | 12 / 1 / 1 | 14 / 14 | 7 | 0 | 0 / 1 | Repaired · 2026-08-22 |
| E-4d01a918377d78de | Ox Alpha | Rated | 57.4 | 1640 | — | 12 / 2 / 0 | 14 / 14 | 7 | 0 | 0 / 1 | First try · 2026-08-22 |
| E-7c6550006514213b | Ox Alpha | Rated | 41.9 | 1456 | — | 4 / 3 / 7 | 14 / 14 | 7 | 0 | 0 / 1 | First try · 2026-08-22 |
| E-2d684425ca56be18 | Step 3.7 Flash | Rated | 46.6 | 1450 | — | 38 / 2 / 50 | 90 / 90 | 44 | 0 | 0 / 1 | Repaired · 2026-07-02 |
| E-3627e3dbf7a48738 | Hy3 Preview | Rated | 30.1 | 1258 | — | 23 / 0 / 55 | 78 / 78 | 37 | 0 | 0 / 1 | First try · 2026-07-02 |
| E-56e54327930d2f64 | Inkling | Rated | 60.5 | 1606 | — | 78 / 8 / 68 | 154 / 154 | 53 | 0 | 0 / 1 | Repaired · 2026-07-24 |
| E-686068814c2242e8 | Inkling Small | Limited data | 55.4 | 1610 | — | 14 / 0 / 2 | 16 / 16 | 9 | 0 | 0 / 1 | First try · 2026-08-18 |
| E-5a1e23bce371a184 | Grok 4.5 | Rated | 56.1 | 1552 | — | 87 / 12 / 75 | 174 / 174 | 61 | 0 | 0 / 1 | First try · 2026-07-24 |
| E-51421c7ae2af8f7b | MiMo-V2.5 | Rated | 58.6 | 1601 | — | 33 / 5 / 26 | 64 / 64 | 32 | 0 | 0 / 1 | Repaired · 2026-07-02 |