Benchmark menu

Per-game leaderboard

GB2-07: Game of the Amazons

This page shows one pooled row per model and reasoning setting for GB2-07: Game of the Amazons. Repeated evaluated entrants are combined in the same way as the benchmark page's game filter.

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 generated programs on 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 leaderboard

Each model and reasoning setting appears once. Repeated evaluated entrants are pooled before ranking, matching the score shown when this game is selected on the benchmark page. Raw rating, match record, and uncertainty are pooled over those contributing entrants.

Reasoning level: Reasoning Variants Game: GB2-07: Game of the Amazons
GB2-07: Game of the Amazons - Reasoning Variants
Rank Model Reasoning Score Raw Elo W / L / D Uncertainty
1GPT-5.4XHigh100.02162.3179/3/00.0
2GPT-5.5XHigh99.72158.4177/5/00.0
3Claude Opus 4.8XHigh85.61969.5159/24/00.0
4Claude Fable 5Medium84.41953.2158/24/00.0
5GPT-5.4 MiniXHigh83.61942.9317/47/00.0
6GPT-5.6 LunaXHigh82.71931.3155/27/00.0
7Qwen3.7 MaxMedium79.21884.4153/29/00.0
8GPT-5.6 SolXHigh78.71877.1148/34/00.0
9Nex N2 ProNone77.01854.1142/42/00.0
10GPT-5.6 TerraXHigh76.01841.4153/29/00.0
11Claude Fable 5XHigh75.71837.7148/34/00.0
12Claude Opus 4.8Medium75.31831.9142/40/00.0
13O3Medium71.31778.1128/54/00.0
14Claude Opus 4.5XHigh69.31752.3131/51/00.0
15GPT-5.6 SolMedium69.31752.0132/50/00.0
16Qwen3.7 MaxNone68.31738.4136/46/00.0
17GPT 5Medium68.11735.7132/51/00.0
18Gemini 3.5 FlashXHigh67.81732.2128/54/00.0
19GPT-5.5Medium66.81717.9136/46/00.0
20GPT-5.4Medium65.01694.4129/54/00.0
21GLM-5.2XHigh64.91693.5365/184/00.0
22GLM-5.2None63.71677.0346/198/00.0
23GLM-5.2Medium63.61703.1277/102/031.6
24DeepSeek V4 FlashXHigh63.11668.8238/127/00.0
25GPT 5XHigh63.11668.6119/64/00.0
26DeepSeek V4 ProXHigh63.11668.6117/65/00.0
27Claude Sonnet 5None62.71663.0119/63/00.0
28Claude Opus 4.8None60.51633.6110/72/00.0
29Kimi K2.7 CodeMedium59.51621.298/84/00.0
30Claude Opus 4.5Medium59.51621.1116/66/00.0
31GPT-5.6 SolNone58.91612.9109/73/00.0
32Claude Sonnet 5Medium58.01601.1110/72/00.0
33GPT 4.1None57.21590.4102/80/00.0
34GPT-5.4 NanoXHigh56.61581.4196/168/00.0
35Gemini 3.5 FlashMedium55.71570.3100/82/00.0
36Minimax M3Medium55.61568.298/84/00.0
37MiMo-V2.5-ProNone55.01560.8105/78/00.0
38Claude Sonnet 5XHigh53.01534.399/84/00.0
39O3XHigh52.71530.197/85/00.0
40Gemini 3.1 Flash LiteXHigh51.61516.580/88/00.0
41GPT-5.5None49.31484.382/100/00.0
42MiMo-V2.5-ProMedium49.21482.886/96/00.0
43DeepSeek V4 ProNone48.91480.378/90/00.0
44Claude Opus 4.5None48.51474.378/104/00.0
45North Mini CodeMedium44.81423.974/108/00.0
46GPT-5.6 LunaMedium44.01413.876/106/00.0
47GPT-5.4 MiniMedium43.21428.2169/210/030.0
48MiMo-V2.5Medium41.81383.6143/222/00.0
49GPT-5.6 TerraMedium41.61381.475/107/00.0
50GPT-5.6 TerraNone41.41379.267/115/00.0
51Hy3 PreviewXHigh41.41379.164/118/00.0
52GPT-OSS 120BXHigh41.11374.671/111/00.0
53DeepSeek V4 FlashMedium40.61408.676/119/047.5
54Minimax M3None39.71355.854/128/00.0
55Qwen3.7 PlusMedium39.31350.761/121/00.0
56Nex N2 ProMedium38.61341.363/119/00.0
57DeepSeek V4 FlashNone34.21282.0166/381/00.0
58Step 3.7 FlashXHigh33.51273.160/122/00.0
59GPT-5.4None32.71262.342/140/00.0
60GPT-5.4 NanoMedium31.31263.4171/389/023.7
61Gemma 4 31BMedium30.41231.859/123/00.0
62MiMo-V2.5None28.81210.8103/261/00.0
63GPT-5.4 NanoNone28.51206.882/283/00.0
64Grok Build 0.1Medium28.41204.840/143/00.0
65Gemma 4 31BNone26.01173.037/145/00.0
66North Mini CodeNone25.01160.077/288/00.0
67GPT-5.4 MiniNone22.61153.942/335/031.6
68Mistral Medium 3.5XHigh18.51073.129/154/00.0
69Nemotron 3 Ultra 550B A55BMedium14.91023.919/163/00.0
70GPT-5.6 LunaNone14.71021.621/161/00.0
71Qwen3.7 PlusNone14.51019.022/160/00.0
72Nemotron 3 Ultra 550B A55BNone10.8969.412/170/00.0
73Gemini 3.1 Flash LiteMedium9.0945.914/168/00.0
74Gemini 3.1 Flash LiteNone0.0825.34/178/00.0

Entrants

Every admitted unique code identity for GB2-07: Game of the Amazons. Capped draws are rated; unilateral model faults are listed separately.

Showing 97 entrants.
EntrantModelReasoningStatusScoreRatingW / L / DRated / attemptedOpponentsCapped drawsModel faultsAdmitted pluginsRepairGenerated
E-babd82321b910e7bclaude-fable-5highestrated75.71838148 / 34 / 0182 / 18291001first pass2026-07-02T16:51:45Z
E-bc12a8303ec2def7claude-fable-5mediumrated84.41953158 / 24 / 0182 / 18291001first pass2026-07-02T16:51:45Z
E-ca22621c58b6f244claude-opus-4-5nonerated48.5147478 / 104 / 0182 / 18291001first pass2026-07-02T16:51:45Z
E-ed9657bcd9dfeda4claude-opus-4-5mediumrated59.51621116 / 66 / 0182 / 18291001first pass2026-07-02T16:51:45Z
E-f2d7a3f3bae22998claude-opus-4-5highestrated69.31752131 / 51 / 0182 / 18291001first pass2026-07-02T16:51:45Z
E-0bf7b9ed307db853claude-opus-4-8mediumrated75.31832142 / 40 / 0182 / 18291001first pass2026-07-02T16:51:45Z
E-5e09cecd1172d99bclaude-opus-4-8highestrated85.61969159 / 24 / 0183 / 18392001first pass2026-07-03T17:20:00Z
E-76804598cce96e62claude-opus-4-8nonerated60.51634110 / 72 / 0182 / 18291001first pass2026-07-02T16:51:45Z
E-2146a36b46e938d6claude-sonnet-5highestrated53.0153499 / 84 / 0183 / 18392001first pass2026-07-03T16:50:00Z
E-9e40526fba9fa8b9claude-sonnet-5mediumrated58.01601110 / 72 / 0182 / 18291001first pass2026-07-02T16:51:45Z
E-cd6f193a087d8c8dclaude-sonnet-5nonerated62.71663119 / 63 / 0182 / 18291001first pass2026-07-02T16:51:45Z
E-1c961fde1b53f0ebcohere/north-mini-codemediumrated44.8142474 / 108 / 0182 / 18291001repaired2026-07-02T16:51:45Z
E-3b908f26a42804a4cohere/north-mini-codenonerated37.8133163 / 119 / 0182 / 18291001first pass2026-07-02T16:51:45Z
E-c7f5dc6d5d3c2a8dcohere/north-mini-codenonerated12.298914 / 169 / 0183 / 18894001repaired2026-07-11T17:22:09Z
E-20285efe5ad468c1deepseek/deepseek-v4-flashhighestrated46.6144889 / 94 / 0183 / 18392001repaired2026-07-02T06:10:40Z
E-8f2f6c973751f183deepseek/deepseek-v4-flashmediumunder covered38.414204 / 8 / 012 / 1312011first pass2026-07-01T00:15:48Z
E-8f6a725b68dde85bdeepseek/deepseek-v4-flashnonerated19.6108735 / 147 / 0182 / 18293001repaired2026-07-01T00:15:48Z
E-c394c0713cfcfaa4deepseek/deepseek-v4-flashnonerated38.1133560 / 122 / 0182 / 18291001first pass2026-07-02T16:51:45Z
E-c8fd55a5d257c569deepseek/deepseek-v4-flashnonerated44.8142471 / 112 / 0183 / 18392001first pass2026-07-02T06:10:40Z
E-ecf2a6ea6f9fe06cdeepseek/deepseek-v4-flashhighestrated79.61890149 / 33 / 0182 / 18291001first pass2026-07-02T16:51:45Z
E-edc2d085c4253ed3deepseek/deepseek-v4-flashmediumrated42.8139772 / 111 / 0183 / 18392001first pass2026-07-02T06:10:40Z
E-f398fd6ac8c8badadeepseek/deepseek-v4-prohighestrated63.11669117 / 65 / 0182 / 18291001repaired2026-07-02T16:51:45Z
E-f76d96b0f3163d4bdeepseek/deepseek-v4-prononerated48.9148078 / 90 / 0168 / 17286041repaired2026-07-02T16:51:45Z
E-0d43f308cfa4da52google/gemini-3.1-flash-litehighestrated51.6151680 / 88 / 0168 / 17286041repaired2026-07-02T16:51:45Z
E-1b3c52da51dfbdd4google/gemini-3.1-flash-litemediumrated9.094614 / 168 / 0182 / 18291001repaired2026-07-02T16:51:45Z
E-3d6a15fe821fe6adgoogle/gemini-3.1-flash-litenonerated0.08254 / 178 / 0182 / 18291001first pass2026-07-02T16:51:45Z
E-5447c508e2b0ab6cgoogle/gemini-3.5-flashmediumrated55.71570100 / 82 / 0182 / 18291001repaired2026-07-02T16:51:45Z
E-f7f306cca2bb9532google/gemini-3.5-flashhighestrated67.81732128 / 54 / 0182 / 18291001repaired2026-07-02T16:51:45Z
E-3f820f7e8ff15839google/gemma-4-31b-itnonerated26.0117337 / 145 / 0182 / 18291001repaired2026-07-02T16:51:45Z
E-f417d302c870dfa6google/gemma-4-31b-itmediumrated30.4123259 / 123 / 0182 / 18291001repaired2026-07-02T16:51:45Z
E-fcfa606d3cbb0ba0gpt-4.1nonerated57.21590102 / 80 / 0182 / 18291001repaired2026-07-02T16:51:45Z
E-15dad0db253c0497gpt-5highestrated63.11669119 / 64 / 0183 / 18392001first pass2026-07-02T16:51:45Z
E-4d8b4cfcff519db6gpt-5mediumrated68.11736132 / 51 / 0183 / 18392001repaired2026-07-02T16:51:45Z
E-22466ae84d7027e5gpt-5.4mediumrated65.01694129 / 54 / 0183 / 18392001first pass2026-07-02T16:51:45Z
E-80aa3ec3ac4ad97fgpt-5.4highestrated100.02162179 / 3 / 0182 / 18291001first pass2026-07-02T16:51:45Z
E-c8176c382cf75e88gpt-5.4nonerated32.7126242 / 140 / 0182 / 18291001first pass2026-07-02T16:51:45Z
E-022243613d51f0fbgpt-5.4-mininoneunder covered37.114034 / 8 / 012 / 1712051first pass2026-07-01T00:15:48Z
E-1b33882368041bb3gpt-5.4-minihighestrated88.62009163 / 19 / 0182 / 18291001first pass2026-07-02T06:10:40Z
E-6a87ebc54bdde781gpt-5.4-mininonerated15.1102717 / 166 / 0183 / 18392001first pass2026-07-02T06:10:40Z
E-946bc9bcbefb4ad1gpt-5.4-minimediumunder covered37.013983 / 10 / 013 / 1813051first pass2026-07-01T00:15:48Z
E-b96fbceba82aa188gpt-5.4-minimediumrated39.4135266 / 117 / 0183 / 18392001first pass2026-07-02T06:10:40Z
E-c2ab31787514c10cgpt-5.4-mininonerated15.5103221 / 161 / 0182 / 18291001first pass2026-07-02T16:51:45Z
E-e453890c6dd35fa3gpt-5.4-minihighestrated78.61876154 / 28 / 0182 / 18291001first pass2026-07-02T16:51:45Z
E-f4d7ac8a0f5d2974gpt-5.4-minimediumrated53.11536100 / 83 / 0183 / 18392001first pass2026-07-02T16:51:45Z
E-4e14ae758717169egpt-5.4-nanononerated36.6131451 / 132 / 0183 / 18392001repaired2026-07-02T16:51:45Z
E-acb1779a65c941b4gpt-5.4-nanomediumrated6.190712 / 171 / 0183 / 18392001repaired2026-07-02T06:10:40Z
E-b9e3f57bc887c6aegpt-5.4-nanohighestrated72.41793134 / 48 / 0182 / 18291001first pass2026-07-09T17:30:50Z
E-bea6d7d9558897f9gpt-5.4-nanomediumrated14.9102520 / 163 / 0183 / 18392001first pass2026-07-02T16:51:45Z
E-c4ad375a0a870e69gpt-5.4-nanomediumunder covered37.114034 / 8 / 012 / 1612041first pass2026-07-01T00:15:48Z
E-ce04fd14b6f43868gpt-5.4-nanomediumrated66.81719135 / 47 / 0182 / 18291001repaired2026-07-09T17:30:50Z
E-ce2925d9379d2a5dgpt-5.4-nanononerated20.5109931 / 151 / 0182 / 18291001repaired2026-07-02T06:10:40Z
E-e0e874b71d913c12gpt-5.4-nanohighestrated40.7137062 / 120 / 0182 / 18291001repaired2026-07-02T06:10:40Z
E-4edfe4117ad3e936gpt-5.5nonerated49.3148482 / 100 / 0182 / 18291001first pass2026-07-02T16:51:45Z
E-6201278165db862agpt-5.5highestrated99.72158177 / 5 / 0182 / 18291001first pass2026-07-02T16:51:45Z
E-640b3078b8bce40egpt-5.5mediumrated66.81718136 / 46 / 0182 / 18291001first pass2026-07-02T16:51:45Z
E-45c76cf9faaba10agpt-5.6-lunamediumrated44.0141476 / 106 / 0182 / 18291001first pass2026-07-10T05:30:29Z
E-73a7b73c1df452adgpt-5.6-lunahighestrated82.71931155 / 27 / 0182 / 18291001first pass2026-07-10T05:30:29Z
E-ea529147555b5f2egpt-5.6-lunanonerated14.7102221 / 161 / 0182 / 18291001first pass2026-07-10T05:30:29Z
E-1b522c9c14f3860cgpt-5.6-solhighestrated78.71877148 / 34 / 0182 / 18291001first pass2026-07-10T05:30:29Z
E-bef852aad169a609gpt-5.6-solnonerated58.91613109 / 73 / 0182 / 18291001first pass2026-07-10T05:30:29Z
E-cc78d54d18d4c3f1gpt-5.6-solmediumrated69.31752132 / 50 / 0182 / 18291001first pass2026-07-10T05:30:29Z
E-65bf9818e3e1b632gpt-5.6-terrahighestrated76.01841153 / 29 / 0182 / 18291001first pass2026-07-10T05:30:29Z
E-8ebe8776c7d44d46gpt-5.6-terranonerated41.4137967 / 115 / 0182 / 18291001first pass2026-07-10T05:30:29Z
E-aca193dd2a8774fbgpt-5.6-terramediumrated41.6138175 / 107 / 0182 / 18291001repaired2026-07-10T05:30:29Z
E-24e15c4d7490cdf3minimax/minimax-m3nonerated39.7135654 / 128 / 0182 / 18291001repaired2026-07-02T16:51:45Z
E-4547f4cedca403f9minimax/minimax-m3mediumrated55.6156898 / 84 / 0182 / 18291001repaired2026-07-02T16:51:45Z
E-d0d0df9d83b6e37emistralai/mistral-medium-3-5highestrated18.5107329 / 154 / 0183 / 18392001first pass2026-07-02T16:51:45Z
E-d35e87ebfc251f60moonshotai/kimi-k2.7-codemediumrated59.5162198 / 84 / 0182 / 18291001repaired2026-07-02T16:51:45Z
E-1006c453b0c3a745nex-agi/nex-n2-prononerated77.01854142 / 42 / 0184 / 19095001repaired2026-07-11T17:22:09Z
E-d1f432cda667f27fnex-agi/nex-n2-promediumrated38.6134163 / 119 / 0182 / 18291001repaired2026-07-02T16:51:45Z
E-0e1c7f89e1c19b69nvidia/nemotron-3-ultra-550b-a55bnonerated10.896912 / 170 / 0182 / 18291001first pass2026-07-03T18:15:00Z
E-459f395cc0af6d2envidia/nemotron-3-ultra-550b-a55bmediumrated14.9102419 / 163 / 0182 / 18291001repaired2026-07-02T16:51:45Z
E-312d25e3a9eeeee3o3highestrated52.7153097 / 85 / 0182 / 18291001first pass2026-07-03T16:00:00Z
E-f1e3e54a3d40556fo3mediumrated71.31778128 / 54 / 0182 / 18291001first pass2026-07-02T16:51:45Z
E-29bc7f4fdf0f7b14openai/gpt-oss-120bhighestrated41.1137571 / 111 / 0182 / 18291001repaired2026-07-02T16:51:45Z
E-3142a09c7f192060qwen/qwen3.7-maxnonerated68.31738136 / 46 / 0182 / 18291001first pass2026-07-02T16:51:45Z
E-59c7745eb1e91d63qwen/qwen3.7-maxmediumrated79.21884153 / 29 / 0182 / 18291001repaired2026-07-02T16:51:45Z
E-737a66790985a5e6qwen/qwen3.7-plusnonerated14.5101922 / 160 / 0182 / 18291001first pass2026-07-02T16:51:45Z
E-9d091700cb41ece2qwen/qwen3.7-plusmediumrated39.3135161 / 121 / 0182 / 18291001repaired2026-07-02T16:51:45Z
E-6a5e44fe2dde4257stepfun/step-3.7-flashhighestrated33.5127360 / 122 / 0182 / 18291001repaired2026-07-02T16:51:45Z
E-dfed1e345a939bcdtencent/hy3-previewhighestrated41.4137964 / 118 / 0182 / 18291001first pass2026-07-02T16:51:45Z
E-37ae0129627ee16fx-ai/grok-build-0.1mediumrated28.4120540 / 143 / 0183 / 18392001repaired2026-07-02T16:51:45Z
E-0984b025e9005f5bxiaomi/mimo-v2.5nonerated21.7111536 / 146 / 0182 / 18291001repaired2026-07-02T16:51:45Z
E-345a5b25cbac7f3bxiaomi/mimo-v2.5mediumrated53.3153792 / 91 / 0183 / 18394001first pass2026-07-01T00:15:48Z
E-47d67dcf0077af42xiaomi/mimo-v2.5nonerated36.0130767 / 115 / 0182 / 18293001first pass2026-07-01T00:15:48Z
E-fa1a93f7e4d57000xiaomi/mimo-v2.5mediumrated30.3123051 / 131 / 0182 / 18291001repaired2026-07-02T16:51:45Z
E-3b160130ae038271xiaomi/mimo-v2.5-promediumrated49.2148386 / 96 / 0182 / 18291001repaired2026-07-02T16:51:45Z
E-83580d03385c6759xiaomi/mimo-v2.5-prononerated55.01561105 / 78 / 0183 / 18392001first pass2026-07-02T16:51:45Z
E-1d66fd51bbcbb370z-ai/glm-5.2mediumrated79.11883151 / 32 / 0183 / 18392001first pass2026-07-02T06:10:40Z
E-62e8714f035ebc68z-ai/glm-5.2nonerated52.7152995 / 88 / 0183 / 18894001first pass2026-07-11T14:00:45Z
E-c81741d135c9dc9cz-ai/glm-5.2highestrated63.51674121 / 63 / 0184 / 19095001repaired2026-07-11T14:00:45Z
E-cb438d112c0ea172z-ai/glm-5.2highestrated60.41633113 / 70 / 0183 / 18392001repaired2026-07-02T06:10:40Z
E-d96269dd04d644e0z-ai/glm-5.2highestrated70.91773131 / 51 / 0182 / 18291001repaired2026-07-02T16:51:45Z
E-e10fd023695e8b0az-ai/glm-5.2mediumunder covered54.8163910 / 2 / 012 / 1712051repaired2026-07-01T00:15:48Z
E-e31f275ab7ef3741z-ai/glm-5.2nonerated70.41766127 / 55 / 0182 / 18291001first pass2026-07-02T16:51:45Z
E-ecd98326faa92bf4z-ai/glm-5.2mediumrated57.01587116 / 68 / 0184 / 19095001repaired2026-07-11T17:22:09Z
E-f7579fbfcb1dcbb9z-ai/glm-5.2nonerated68.11735124 / 55 / 0179 / 17990001first pass2026-07-01T00:15:48Z