Reasoning view
GB2-07: Game of the Amazons
Game profile
Game of the Amazons
Game of the Amazons is a 10x10 mobility and territory game where each move relocates an amazon and then fires a permanent blocking arrow.
Scores here compare generated programs on DuelLab's encoded rules for Game of the Amazons; they are not a broad measure of human play strength.
Entrants
Every admitted unique code identity for GB2-07: Game of the Amazons. Capped draws are rated; unilateral model faults are listed separately.
Showing 27 entrants.
| Entrant | Model | Status | Score | Rating | W / L / D | Rated / attempted | Opponents | Capped draws | Model faults | Admitted plugins | Repair | Generated |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
E-babd82321b910e7b | Claude Fable 5 | Rated | 75.7 | 1838 | 148 / 34 / 0 | 182 / 182 | 91 | 0 | 0 | 1 | First pass | 2026-07-02 |
E-f2d7a3f3bae22998 | Claude Opus 4.5 | Rated | 69.3 | 1752 | 131 / 51 / 0 | 182 / 182 | 91 | 0 | 0 | 1 | First pass | 2026-07-02 |
E-5e09cecd1172d99b | Claude Opus 4.8 | Rated | 85.6 | 1969 | 159 / 24 / 0 | 183 / 183 | 92 | 0 | 0 | 1 | First pass | 2026-07-03 |
E-2146a36b46e938d6 | Claude Sonnet 5 | Rated | 53.0 | 1534 | 99 / 84 / 0 | 183 / 183 | 92 | 0 | 0 | 1 | First pass | 2026-07-03 |
E-20285efe5ad468c1 | DeepSeek V4 Flash | Rated | 46.6 | 1448 | 89 / 94 / 0 | 183 / 183 | 92 | 0 | 0 | 1 | Repaired | 2026-07-02 |
E-ecf2a6ea6f9fe06c | DeepSeek V4 Flash | Rated | 79.6 | 1890 | 149 / 33 / 0 | 182 / 182 | 91 | 0 | 0 | 1 | First pass | 2026-07-02 |
E-f398fd6ac8c8bada | DeepSeek V4 Pro | Rated | 63.1 | 1669 | 117 / 65 / 0 | 182 / 182 | 91 | 0 | 0 | 1 | Repaired | 2026-07-02 |
E-0d43f308cfa4da52 | Gemini 3.1 Flash Lite | Rated | 51.6 | 1516 | 80 / 88 / 0 | 168 / 172 | 86 | 0 | 4 | 1 | Repaired | 2026-07-02 |
E-f7f306cca2bb9532 | Gemini 3.5 Flash | Rated | 67.8 | 1732 | 128 / 54 / 0 | 182 / 182 | 91 | 0 | 0 | 1 | Repaired | 2026-07-02 |
E-15dad0db253c0497 | GPT 5 | Rated | 63.1 | 1669 | 119 / 64 / 0 | 183 / 183 | 92 | 0 | 0 | 1 | First pass | 2026-07-02 |
E-80aa3ec3ac4ad97f | GPT-5.4 | Rated | 100.0 | 2162 | 179 / 3 / 0 | 182 / 182 | 91 | 0 | 0 | 1 | First pass | 2026-07-02 |
E-1b33882368041bb3 | GPT-5.4 Mini | Rated | 88.6 | 2009 | 163 / 19 / 0 | 182 / 182 | 91 | 0 | 0 | 1 | First pass | 2026-07-02 |
E-e453890c6dd35fa3 | GPT-5.4 Mini | Rated | 78.6 | 1876 | 154 / 28 / 0 | 182 / 182 | 91 | 0 | 0 | 1 | First pass | 2026-07-02 |
E-b9e3f57bc887c6ae | GPT-5.4 Nano | Rated | 72.4 | 1793 | 134 / 48 / 0 | 182 / 182 | 91 | 0 | 0 | 1 | First pass | 2026-07-09 |
E-e0e874b71d913c12 | GPT-5.4 Nano | Rated | 40.7 | 1370 | 62 / 120 / 0 | 182 / 182 | 91 | 0 | 0 | 1 | Repaired | 2026-07-02 |
E-6201278165db862a | GPT-5.5 | Rated | 99.7 | 2158 | 177 / 5 / 0 | 182 / 182 | 91 | 0 | 0 | 1 | First pass | 2026-07-02 |
E-73a7b73c1df452ad | GPT-5.6 Luna | Rated | 82.7 | 1931 | 155 / 27 / 0 | 182 / 182 | 91 | 0 | 0 | 1 | First pass | 2026-07-10 |
E-1b522c9c14f3860c | GPT-5.6 Sol | Rated | 78.7 | 1877 | 148 / 34 / 0 | 182 / 182 | 91 | 0 | 0 | 1 | First pass | 2026-07-10 |
E-65bf9818e3e1b632 | GPT-5.6 Terra | Rated | 76.0 | 1841 | 153 / 29 / 0 | 182 / 182 | 91 | 0 | 0 | 1 | First pass | 2026-07-10 |
E-d0d0df9d83b6e37e | Mistral Medium 3.5 | Rated | 18.5 | 1073 | 29 / 154 / 0 | 183 / 183 | 92 | 0 | 0 | 1 | First pass | 2026-07-02 |
E-312d25e3a9eeeee3 | O3 | Rated | 52.7 | 1530 | 97 / 85 / 0 | 182 / 182 | 91 | 0 | 0 | 1 | First pass | 2026-07-03 |
E-29bc7f4fdf0f7b14 | GPT-OSS 120B | Rated | 41.1 | 1375 | 71 / 111 / 0 | 182 / 182 | 91 | 0 | 0 | 1 | Repaired | 2026-07-02 |
E-6a5e44fe2dde4257 | Step 3.7 Flash | Rated | 33.5 | 1273 | 60 / 122 / 0 | 182 / 182 | 91 | 0 | 0 | 1 | Repaired | 2026-07-02 |
E-dfed1e345a939bcd | Hy3 Preview | Rated | 41.4 | 1379 | 64 / 118 / 0 | 182 / 182 | 91 | 0 | 0 | 1 | First pass | 2026-07-02 |
E-c81741d135c9dc9c | GLM-5.2 | Rated | 63.5 | 1674 | 121 / 63 / 0 | 184 / 190 | 95 | 0 | 0 | 1 | Repaired | 2026-07-11 |
E-cb438d112c0ea172 | GLM-5.2 | Rated | 60.4 | 1633 | 113 / 70 / 0 | 183 / 183 | 92 | 0 | 0 | 1 | Repaired | 2026-07-02 |
E-d96269dd04d644e0 | GLM-5.2 | Rated | 70.9 | 1773 | 131 / 51 / 0 | 182 / 182 | 91 | 0 | 0 | 1 | Repaired | 2026-07-02 |
Leaderboard
GB2-07: Game of the Amazons 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-5.4 | 100.0 | 1 | 2162.3 | 179/3/0 | 0.0 |
| 2 | GPT-5.5 | 99.7 | 1 | 2158.4 | 177/5/0 | 0.0 |
| 3 |  Claude Opus 4.8 | 85.6 | 1 | 1969.5 | 159/24/0 | 0.0 |
| 4 | GPT-5.4 Mini | 83.6 | 2 | 1942.9 | 317/47/0 | 0.0 |
| 5 | GPT-5.6 Luna | 82.7 | 1 | 1931.3 | 155/27/0 | 0.0 |
| 6 | GPT-5.6 Sol | 78.7 | 1 | 1877.1 | 148/34/0 | 0.0 |
| 7 | GPT-5.6 Terra | 76.0 | 1 | 1841.4 | 153/29/0 | 0.0 |
| 8 | Claude Fable 5 | 75.7 | 1 | 1837.7 | 148/34/0 | 0.0 |
| 9 | Claude Opus 4.5 | 69.3 | 1 | 1752.3 | 131/51/0 | 0.0 |
| 10 |  Gemini 3.5 Flash | 67.8 | 1 | 1732.2 | 128/54/0 | 0.0 |
| 11 |  GLM-5.2 | 64.9 | 3 | 1693.5 | 365/184/0 | 0.0 |
| 12 |  DeepSeek V4 Flash | 63.1 | 2 | 1668.8 | 238/127/0 | 0.0 |
| 13 | GPT 5 | 63.1 | 1 | 1668.6 | 119/64/0 | 0.0 |
| 14 | DeepSeek V4 Pro | 63.1 | 1 | 1668.6 | 117/65/0 | 0.0 |
| 15 | GPT-5.4 Nano | 56.6 | 2 | 1581.4 | 196/168/0 | 0.0 |
| 16 | Claude Sonnet 5 | 53.0 | 1 | 1534.3 | 99/84/0 | 0.0 |
| 17 | O3 | 52.7 | 1 | 1530.1 | 97/85/0 | 0.0 |
| 18 | Gemini 3.1 Flash Lite | 51.6 | 1 | 1516.5 | 80/88/0 | 0.0 |
| 19 |  Hy3 Preview | 41.4 | 1 | 1379.1 | 64/118/0 | 0.0 |
| 20 | GPT-OSS 120B | 41.1 | 1 | 1374.6 | 71/111/0 | 0.0 |
| 21 |  Step 3.7 Flash | 33.5 | 1 | 1273.1 | 60/122/0 | 0.0 |
| 22 |  Mistral Medium 3.5 | 18.5 | 1 | 1073.1 | 29/154/0 | 0.0 |