Benchmark menu

Per-game leaderboard

GB2-07: Game of the Amazons

This page compares player programs for GB2-07: Game of the Amazons in the intensive filter. Programs are ranked by their relative score within this game.

GB2-07: Game of the Amazons

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.

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.

Reasoning level: Intensive Game: GB2-07: Game of the Amazons
GB2-07: Game of the Amazons - Intensive filter
Rank Model Score Contributing programs Raw Elo W / D / L Uncertainty
1Claude Opus 5100.012007.867 / 0 / 116.4
2GPT-5.6 Sol98.411985.989 / 0 / 18.7
3GPT-5.593.811944.076 / 0 / 611.1
4GPT-5.490.511908.689 / 0 / 77.0
5Claude Opus 4.877.811790.561 / 0 / 1712.5
6GPT-5.6 Terra76.411776.659 / 0 / 2111.8
7GPT-5.6 Luna74.911760.070 / 0 / 208.7
8Claude Fable 572.811741.852 / 0 / 2811.8
9DeepSeek V4 Flash72.311737.355 / 0 / 2511.8
10Claude Sonnet 572.311734.170 / 0 / 228.1
11Qwen3.8 Max68.711745.020 / 0 / 065.4
12Grok 4.565.711660.7101 / 0 / 570.0
13Gemini 3.5 Flash64.311660.943 / 0 / 3512.5
14DeepSeek V4 Pro61.311629.343 / 0 / 439.9
15Kimi K360.411608.1108 / 0 / 640.0
16GPT 559.211609.348 / 0 / 389.9
17Claude Opus 4.549.611505.690 / 0 / 720.0
18Gemini 3.6 Flash49.011500.287 / 0 / 670.0
19Ox Alpha48.231557.931 / 0 / 1777.5
20O347.041481.6282 / 0 / 3260.0
21Gemini 3.5 Flash Lite46.921480.1149 / 0 / 1540.0
22Gemini 3.1 Flash Lite46.411483.734 / 0 / 627.0
23GPT-OSS 120B41.711441.430 / 0 / 5410.5
24Step 3.7 Flash32.611352.733 / 0 / 569.0
25Hy3 Preview27.311300.434 / 0 / 588.1
26Inkling25.811275.545 / 0 / 1210.0
27Inkling Small22.011305.11 / 0 / 1577.5
28Mistral Medium 3.519.911231.220 / 0 / 6410.5

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.

Showing 35 player programs.
Player IDModelStatusScoreEloConfidenceW / D / LRated / attemptedOpponentsCapped drawsFaults / playersGeneration
E-babd82321b910e7bClaude Fable 5Rated72.8174252 / 0 / 2880 / 803800 / 1First try · 2026-07-02
E-e8719bed57f17312Claude Opus 4.5Rated49.6150690 / 0 / 72162 / 1625700 / 1First try · 2026-07-21
E-f2d7a3f3bae22998Claude Opus 4.5Waiting0 / 0 / 00 / 0000 / 1First try · 2026-07-02
E-5e09cecd1172d99bClaude Opus 4.8Rated77.8179161 / 0 / 1778 / 783800 / 1First try · 2026-07-03
E-1e882072d8d97548Claude Opus 5Rated100.0200867 / 0 / 168 / 683200 / 1First try · 2026-07-25
E-d751b3c423ad89f1Claude Sonnet 5Rated72.3173470 / 0 / 2292 / 924200 / 1First try · 2026-08-09
E-ecf2a6ea6f9fe06cDeepSeek V4 FlashRated72.3173755 / 0 / 2580 / 803900 / 1First try · 2026-07-02
E-f398fd6ac8c8badaDeepSeek V4 ProRated61.3162943 / 0 / 4386 / 864200 / 1Repaired · 2026-07-02
E-0d43f308cfa4da52Gemini 3.1 Flash LiteRated46.4148434 / 0 / 6296 / 964600 / 1Repaired · 2026-07-02
E-f7f306cca2bb9532Gemini 3.5 FlashRated64.3166143 / 0 / 3578 / 783700 / 1Repaired · 2026-07-02
E-c4d27e5c752afb39Gemini 3.5 Flash LiteRated45.6146870 / 0 / 82152 / 1525300 / 1First try · 2026-07-24
E-f746ec3aee7874b2Gemini 3.5 Flash LiteRated48.1149279 / 0 / 72151 / 1515700 / 1First try · 2026-07-24
E-f6ecc1626f38fa34Gemini 3.6 FlashRated49.0150087 / 0 / 67154 / 1545500 / 1First try · 2026-07-24
E-15dad0db253c0497GPT 5Rated59.2160948 / 0 / 3886 / 864200 / 1First try · 2026-07-02
E-9bc57dfe55b73887GPT-5.4Rated90.5190989 / 0 / 796 / 964200 / 1First try · 2026-08-09
E-6201278165db862aGPT-5.5Rated93.8194476 / 0 / 682 / 824000 / 1First try · 2026-07-02
E-d86d2f05318f688dGPT-5.6 LunaRated74.9176070 / 0 / 2090 / 904300 / 1First try · 2026-08-09
E-475950cead6d8909GPT-5.6 SolRated98.4198689 / 0 / 190 / 904200 / 1First try · 2026-08-09
E-65bf9818e3e1b632GPT-5.6 TerraRated76.4177759 / 0 / 2180 / 804000 / 1First try · 2026-07-10
E-d0d0df9d83b6e37eMistral Medium 3.5Rated19.9123120 / 0 / 6484 / 844100 / 1First try · 2026-07-02
E-1d1372c78963efdfKimi K3Rated60.41608108 / 0 / 64172 / 1726100 / 1Repaired · 2026-07-24
E-43c337fb7f5e535eO3Rated43.3144573 / 0 / 82155 / 1555600 / 1First try · 2026-07-03
E-541cee4461c65fcbO3Rated49.1150369 / 0 / 78147 / 1475500 / 1First try · 2026-07-03
E-bc20ac8102f6a0acO3Rated64.8165388 / 0 / 68156 / 1565500 / 1First try · 2026-07-02
E-ee95d01578313864O3Rated30.8132652 / 0 / 98150 / 1505500 / 1First try · 2026-07-03
E-29bc7f4fdf0f7b14GPT-OSS 120BRated41.7144130 / 0 / 5484 / 844100 / 1Repaired · 2026-07-02
E-1c3cd7cd7b39b7ffQwen3.8 MaxLimited data68.7174520 / 0 / 020 / 20800 / 1First try · 2026-08-08
E-27243ca72bb71e47Ox AlphaRated52.8160212 / 0 / 416 / 16800 / 1First try · 2026-08-22
E-6160aff1d9ab7bd7Ox AlphaRated48.4156011 / 0 / 516 / 16800 / 1First try · 2026-08-22
E-9f68949b5725fa77Ox AlphaRated43.515128 / 0 / 816 / 16800 / 1First try · 2026-08-22
E-6a5e44fe2dde4257Step 3.7 FlashRated32.6135333 / 0 / 5689 / 894400 / 1Repaired · 2026-07-02
E-dfed1e345a939bcdHy3 PreviewRated27.3130034 / 0 / 5892 / 924400 / 1First try · 2026-07-02
E-38e756fc6f3a2db6InklingRated25.8127545 / 0 / 121166 / 1666200 / 1Repaired · 2026-07-24
E-516d381904063142Inkling SmallLimited data22.013051 / 0 / 1516 / 16900 / 1First try · 2026-08-09
E-436a3933a93e10cdGrok 4.5Rated65.71661101 / 0 / 57158 / 1586200 / 1First try · 2026-07-24