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 player programs using DuelLab's encoded rules for Game of the Amazons; they are not a broad measure of human play strength.
By model and setting
GB2-07: Game of the Amazons 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 | 81.4 | 1 | 1824.0 | 63 / 0 / 19 | 11.1 | |
| 2 | 76.3 | 1 | 1764.6 | 110 / 0 / 32 | 0.0 | |
| 3 | 73.0 | 2 | 1732.8 | 196 / 0 / 94 | 0.0 | |
| 4 | 68.9 | 1 | 1704.7 | 51 / 0 / 27 | 12.5 | |
| 5 | 63.5 | 1 | 1652.7 | 56 / 0 / 24 | 11.8 | |
| 6 | 55.6 | 1 | 1575.9 | 52 / 0 / 30 | 11.1 | |
| 7 | 55.0 | 2 | 1558.5 | 161 / 0 / 144 | 0.0 | |
| 8 | 54.0 | 1 | 1547.9 | 82 / 0 / 78 | 0.0 | |
| 9 | 53.7 | 1 | 1559.9 | 37 / 0 / 35 | 14.8 | |
| 10 | 53.0 | 1 | 1548.4 | 56 / 0 / 37 | 7.8 | |
| 11 | 53.0 | 1 | 1549.5 | 51 / 0 / 35 | 9.9 | |
| 12 | 52.4 | 2 | 1543.1 | 79 / 0 / 99 | 9.0 | |
| 13 | 51.2 | 2 | 1539.9 | 59 / 0 / 65 | 19.3 | |
| 14 | 49.2 | 1 | 1559.3 | 12 / 0 / 7 | 68.1 | |
| 15 | 46.9 | 1 | 1488.6 | 52 / 0 / 44 | 7.0 | |
| 16 | 44.1 | 1 | 1461.7 | 51 / 0 / 47 | 6.5 | |
| 17 | 42.8 | 1 | 1450.1 | 51 / 0 / 41 | 8.1 | |
| 18 | 41.1 | 2 | 1432.7 | 97 / 0 / 93 | 7.3 | |
| 19 | 40.4 | 1 | 1426.4 | 43 / 0 / 51 | 7.5 | |
| 20 | 39.6 | 3 | 1475.1 | 21 / 0 / 27 | 77.5 | |
| 21 | 38.4 | 1 | 1408.0 | 36 / 0 / 52 | 9.2 | |
| 22 | 38.0 | 1 | 1393.0 | 67 / 0 / 105 | 0.0 | |
| 23 | 35.3 | 1 | 1380.3 | 32 / 0 / 48 | 11.8 | |
| 24 | 35.2 | 1 | 1375.7 | 34 / 0 / 62 | 7.0 | |
| 25 | 33.5 | 1 | 1406.4 | 6 / 0 / 14 | 65.4 | |
| 26 | 32.8 | 1 | 1357.2 | 34 / 0 / 44 | 12.5 | |
| 27 | 31.5 | 1 | 1342.4 | 30 / 0 / 58 | 9.2 | |
| 28 | 31.1 | 1 | 1335.9 | 46 / 0 / 52 | 6.5 | |
| 29 | 30.9 | 2 | 1338.8 | 68 / 0 / 90 | 12.2 | |
| 30 | 29.7 | 1 | 1323.5 | 37 / 0 / 57 | 7.5 | |
| 31 | 27.9 | 1 | 1295.2 | 54 / 0 / 118 | 0.0 | |
| 32 | 24.9 | 2 | 1278.3 | 53 / 0 / 123 | 9.3 | |
| 33 | 19.0 | 1 | 1224.1 | 24 / 0 / 56 | 11.8 | |
| 34 | 11.8 | 1 | 1151.8 | 13 / 0 / 79 | 8.1 | |
| 35 | 10.5 | 1 | 1144.7 | 9 / 0 / 61 | 15.6 | |
| 36 | 9.1 | 1 | 1114.7 | 24 / 0 / 138 | 0.0 | |
| 37 | 7.1 | 1 | 1108.5 | 13 / 0 / 69 | 11.1 | |
| 38 | 3.6 | 1 | 1075.8 | 17 / 0 / 61 | 12.5 | |
| 39 | 0.0 | 1 | 1044.3 | 4 / 0 / 64 | 16.4 |
Underlying results
Individual player programs
Each row is one accepted player program for GB2-07: Game of the Amazons. 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.
| Player ID | Model | Status | Score | Elo | Confidence | W / D / L | Rated / attempted | Opponents | Capped draws | Faults / players | Generation |
|---|---|---|---|---|---|---|---|---|---|---|---|
| E-ca22621c58b6f244 | Claude Opus 4.5 | Rated | 46.9 | 1489 | — | 52 / 0 / 44 | 96 / 96 | 48 | 0 | 0 / 1 | First try · 2026-07-02 |
| E-76804598cce96e62 | Claude Opus 4.8 | Rated | 55.6 | 1576 | — | 52 / 0 / 30 | 82 / 82 | 41 | 0 | 0 / 1 | First try · 2026-07-02 |
| E-914b104a64ab3110 | Claude Opus 5 | Rated | 81.4 | 1824 | — | 63 / 0 / 19 | 82 / 82 | 41 | 0 | 0 / 1 | First try · 2026-07-25 |
| E-754e53d1d8048114 | Claude Sonnet 5 | Rated | 38.4 | 1408 | — | 36 / 0 / 52 | 88 / 88 | 42 | 0 | 0 / 1 | First try · 2026-08-09 |
| E-3b908f26a42804a4 | North Mini Code | Rated | 42.3 | 1446 | — | 45 / 0 / 47 | 92 / 92 | 42 | 0 | 0 / 1 | First try · 2026-07-02 |
| E-c7f5dc6d5d3c2a8d | North Mini Code | Rated | 7.4 | 1111 | — | 8 / 0 / 76 | 84 / 88 | 40 | 0 | 4 / 1 | Repaired · 2026-07-11 |
| E-c394c0713cfcfaa4 | DeepSeek V4 Flash | Rated | 32.8 | 1357 | — | 34 / 0 / 44 | 78 / 78 | 39 | 0 | 0 / 1 | First try · 2026-07-02 |
| E-f76d96b0f3163d4b | DeepSeek V4 Pro | Rated | 42.8 | 1450 | — | 51 / 0 / 41 | 92 / 92 | 45 | 0 | 0 / 1 | Repaired · 2026-07-02 |
| E-3d6a15fe821fe6ad | Gemini 3.1 Flash Lite | Rated | 0.0 | 1044 | — | 4 / 0 / 64 | 68 / 68 | 34 | 0 | 0 / 1 | First try · 2026-07-02 |
| E-c9fe3c158f1169e0 | Gemini 3.5 Flash | Waiting | — | — | — | 0 / 0 / 0 | 0 / 0 | 0 | 0 | 0 / 1 | First try · 2026-07-21 |
| E-455ee67905f5f955 | Gemini 3.5 Flash Lite | Rated | 62.4 | 1631 | — | 77 / 0 / 65 | 142 / 142 | 55 | 0 | 0 / 1 | First try · 2026-07-24 |
| E-e2e240babaf0b862 | Gemini 3.5 Flash Lite | Rated | 83.7 | 1835 | — | 119 / 0 / 29 | 148 / 148 | 58 | 0 | 0 / 1 | First try · 2026-07-24 |
| E-8e9b51be911dad38 | Gemini 3.6 Flash | Rated | 39.4 | 1408 | — | 66 / 0 / 91 | 157 / 161 | 55 | 0 | 0 / 1 | First try · 2026-07-24 |
| E-a2d90fcdc2f4ef9d | Gemini 3.6 Flash | Rated | 70.6 | 1709 | — | 95 / 0 / 53 | 148 / 148 | 58 | 0 | 0 / 1 | First try · 2026-07-24 |
| E-3f820f7e8ff15839 | Gemma 4 31B | Rated | 19.0 | 1224 | — | 24 / 0 / 56 | 80 / 82 | 40 | 0 | 2 / 1 | Repaired · 2026-07-02 |
| E-fcfa606d3cbb0ba0 | GPT 4.1 | Rated | 53.7 | 1560 | — | 37 / 0 / 35 | 72 / 72 | 36 | 0 | 0 / 1 | Repaired · 2026-07-02 |
| E-a67f59519ca31035 | GPT 5 | Waiting | — | — | — | 0 / 0 / 0 | 0 / 0 | 0 | 0 | 0 / 1 | First try · 2026-07-21 |
| E-323834608cbfa7f4 | GPT-5.4 | Rated | 35.2 | 1376 | — | 34 / 0 / 62 | 96 / 96 | 42 | 0 | 0 / 1 | First try · 2026-08-09 |
| E-c2ab31787514c10c | GPT-5.4 Mini | Rated | 7.1 | 1109 | — | 13 / 0 / 69 | 82 / 84 | 41 | 0 | 2 / 1 | First try · 2026-07-02 |
| E-4e14ae758717169e | GPT-5.4 Nano | Rated | 29.7 | 1323 | — | 37 / 0 / 57 | 94 / 94 | 47 | 0 | 0 / 1 | Repaired · 2026-07-02 |
| E-4edfe4117ad3e936 | GPT-5.5 | Rated | 44.1 | 1462 | — | 51 / 0 / 47 | 98 / 98 | 49 | 0 | 0 / 1 | First try · 2026-07-02 |
| E-8fd5624103eac132 | GPT-5.6 Luna | Rated | 11.8 | 1152 | — | 13 / 0 / 79 | 92 / 92 | 42 | 0 | 0 / 1 | First try · 2026-08-09 |
| E-e65ec062f67d1b0b | GPT-5.6 Sol | Rated | 53.0 | 1548 | — | 56 / 0 / 37 | 93 / 93 | 43 | 0 | 0 / 1 | First try · 2026-08-09 |
| E-8ebe8776c7d44d46 | GPT-5.6 Terra | Rated | 40.4 | 1426 | — | 43 / 0 / 51 | 94 / 94 | 46 | 0 | 0 / 1 | First try · 2026-07-10 |
| E-c1f595f47c71e648 | LongCat 2.0 | Rated | 36.9 | 1393 | — | 51 / 0 / 43 | 94 / 94 | 46 | 0 | 0 / 1 | First try · 2026-07-24 |
| E-e2db910734ca5315 | LongCat 2.0 | Rated | 45.2 | 1473 | — | 46 / 0 / 50 | 96 / 96 | 47 | 0 | 0 / 1 | Repaired · 2026-07-24 |
| E-5618329845b079c7 | Muse Spark 1.2 | Rated | 31.5 | 1342 | — | 30 / 0 / 58 | 88 / 88 | 42 | 0 | 0 / 1 | First try · 2026-08-13 |
| E-24e15c4d7490cdf3 | Minimax M3 | Rated | 35.3 | 1380 | — | 32 / 0 / 48 | 80 / 80 | 40 | 0 | 0 / 1 | Repaired · 2026-07-02 |
| E-4d8815930b656774 | Kimi K3 | Rated | 27.9 | 1295 | — | 54 / 0 / 118 | 172 / 172 | 67 | 0 | 0 / 1 | First try · 2026-07-24 |
| E-1006c453b0c3a745 | Nex N2 Pro | Rated | 63.5 | 1653 | — | 56 / 0 / 24 | 80 / 80 | 40 | 0 | 0 / 1 | Repaired · 2026-07-11 |
| E-0e1c7f89e1c19b69 | Nemotron 3 Ultra 550B A55B | Rated | 10.5 | 1145 | — | 9 / 0 / 61 | 70 / 70 | 35 | 0 | 0 / 1 | First try · 2026-07-03 |
| E-585aa996c86c4b8a | O3 | Rated | 54.0 | 1548 | — | 82 / 0 / 78 | 160 / 160 | 59 | 0 | 0 / 1 | First try · 2026-07-21 |
| E-759d747bb732d949 | GPT-OSS 120B | Rated | 9.1 | 1115 | — | 24 / 0 / 138 | 162 / 162 | 61 | 0 | 0 / 1 | First try · 2026-07-21 |
| E-069a963abdd14cdf | Laguna S 2.1 | Rated | 45.3 | 1474 | — | 35 / 0 / 55 | 90 / 98 | 44 | 0 | 0 / 1 | First try · 2026-07-24 |
| E-d8e68d23876f6d21 | Laguna S 2.1 | Rated | 59.5 | 1612 | — | 44 / 0 / 44 | 88 / 88 | 44 | 0 | 0 / 1 | First try · 2026-07-24 |
| E-3142a09c7f192060 | Qwen3.7 Max | Rated | 68.9 | 1705 | — | 51 / 0 / 27 | 78 / 78 | 39 | 0 | 0 / 1 | First try · 2026-07-02 |
| E-737a66790985a5e6 | Qwen3.7 Plus | Rated | 3.6 | 1076 | — | 17 / 0 / 61 | 78 / 80 | 39 | 0 | 2 / 1 | First try · 2026-07-02 |
| E-9060604c6d76c81b | Qwen3.8 Max | Limited data | 49.2 | 1559 | — | 12 / 0 / 7 | 19 / 19 | 10 | 0 | 0 / 1 | First try · 2026-08-08 |
| E-b7e03d205460428f | Ox Alpha | Rated | 52.1 | 1595 | — | 12 / 0 / 4 | 16 / 16 | 8 | 0 | 0 / 1 | First try · 2026-08-22 |
| E-c2beebe255c607a1 | Ox Alpha | Rated | 36.6 | 1446 | — | 6 / 0 / 10 | 16 / 16 | 8 | 0 | 0 / 1 | First try · 2026-08-22 |
| E-f9e2fbd96bb7a98d | Ox Alpha | Rated | 30.2 | 1384 | — | 3 / 0 / 13 | 16 / 16 | 8 | 0 | 0 / 1 | First try · 2026-08-22 |
| E-1140a7c92290e8f4 | Step 3.7 Flash | Rated | 38.0 | 1393 | — | 67 / 0 / 105 | 172 / 172 | 65 | 0 | 0 / 1 | Repaired · 2026-07-21 |
| E-062d41f517db2ccb | Inkling | Rated | 31.1 | 1336 | — | 46 / 0 / 52 | 98 / 98 | 48 | 0 | 0 / 1 | First try · 2026-07-24 |
| E-f330739aca81e515 | Inkling Small | Limited data | 33.5 | 1406 | — | 6 / 0 / 14 | 20 / 20 | 11 | 0 | 0 / 1 | Repaired · 2026-08-09 |
| E-1d206565b78f3121 | Grok 4.5 | Rated | 76.3 | 1765 | — | 110 / 0 / 32 | 142 / 142 | 55 | 0 | 0 / 1 | First try · 2026-07-24 |
| E-0984b025e9005f5b | MiMo-V2.5 | Rated | 11.8 | 1154 | — | 24 / 0 / 56 | 80 / 82 | 40 | 0 | 2 / 1 | Repaired · 2026-07-02 |
| E-47d67dcf0077af42 | MiMo-V2.5 | Rated | 50.0 | 1523 | — | 44 / 0 / 34 | 78 / 78 | 39 | 0 | 0 / 1 | First try · 2026-07-01 |
| E-83580d03385c6759 | MiMo-V2.5-Pro | Rated | 53.0 | 1549 | — | 51 / 0 / 35 | 86 / 86 | 43 | 0 | 0 / 1 | First try · 2026-07-02 |
| E-62e8714f035ebc68 | GLM-5.2 | Rated | 41.3 | 1445 | — | 27 / 0 / 33 | 60 / 60 | 30 | 0 | 0 / 1 | First try · 2026-07-11 |
| E-e31f275ab7ef3741 | GLM-5.2 | Rated | 61.1 | 1635 | — | 32 / 0 / 32 | 64 / 64 | 32 | 0 | 0 / 1 | First try · 2026-07-02 |