Benchmark menu

Per-game leaderboard

GB2-04: Xiangqi

This page shows one pooled row per model and reasoning setting for GB2-04: Xiangqi. Repeated evaluated entrants are combined in the same way as the benchmark page's game filter.

GB2-04: Xiangqi

Xiangqi

Xiangqi is a 9x10 chess-family game with palaces, river restrictions, cannon screens, horse-leg and elephant-eye blocking, and flying-general legality.

Scores here compare generated programs on DuelLab's encoded rules for Xiangqi; they are not a broad measure of human play strength.

GB2-04: Xiangqi 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: GB2-04: Xiangqi
GB2-04: Xiangqi - Reasoning Variants
Rank Model Reasoning Score Raw Elo W / L / D Uncertainty
1Claude Fable 5XHigh100.01950.2143/2/180.0
2Claude Opus 4.8XHigh54.01682.980/8/750.0
3GPT-5.6 SolXHigh50.71664.380/6/760.0
4Claude Fable 5Medium42.11614.055/13/950.0
5Claude Opus 4.5None34.61570.747/9/1070.0
6Claude Sonnet 5XHigh33.61564.339/11/1130.0
7GPT-5.6 TerraXHigh32.71559.554/16/920.0
8GPT-5.4 NanoMedium30.71548.077/46/2010.0
9GPT-5.4XHigh30.01543.867/17/790.0
10GPT-5.6 SolNone29.81542.630/17/1150.0
11MiMo-V2.5-ProMedium29.41540.339/26/970.0
12GPT-5.4 MiniMedium27.21527.3101/47/3390.0
13GPT-5.4 MiniXHigh26.91525.620/23/1190.0
14Step 3.7 FlashMedium26.81525.019/15/1300.0
15Gemma 4 31BMedium25.91519.713/18/1330.0
16Hy3 PreviewNone25.71518.743/20/1000.0
17Claude Sonnet 5Medium25.51517.333/18/1120.0
18Grok Build 0.1Medium25.11515.312/18/1330.0
19MiMo-V2.5XHigh25.11515.318/22/1220.0
20GPT-5.6 SolMedium25.01515.020/17/1250.0
21DeepSeek V4 ProXHigh25.01514.624/33/1060.0
22GPT-OSS 120BMedium24.81513.28/21/1350.0
23GPT-5.6 TerraNone24.31510.713/8/1410.0
24GPT-5.4Medium23.81507.828/15/1210.0
25Nemotron 3 Ultra 550B A55BNone23.71507.016/24/1240.0
26GLM-5.2None23.61506.782/79/4880.0
27Gemini 3.5 FlashMedium23.41505.234/28/1020.0
28Qwen3.7 PlusNone22.61500.611/17/1350.0
29O3Medium21.71495.413/24/1260.0
30Kimi K2.7 CodeMedium21.31493.014/29/1200.0
31GPT-5.4 MiniNone21.31493.063/87/3380.0
32Hy3 PreviewXHigh21.11492.15/15/1440.0
33GPT-5.6 LunaXHigh21.01491.332/27/1030.0
34Qwen3.7 MaxMedium21.01491.130/34/1000.0
35GPT-5.4None20.51488.518/25/1200.0
36GPT-5.6 TerraMedium20.51488.521/16/1250.0
37Claude Sonnet 5None20.41488.015/11/1380.0
38Claude Opus 4.8Medium20.41487.612/17/1350.0
39GPT 5XHigh20.11486.017/23/1240.0
40Claude Opus 4.8None19.81484.214/27/1220.0
41Nex N2 ProNone19.61483.48/11/1430.0
42GPT-5.5Medium19.51483.023/29/1100.0
43GPT 5Medium19.51482.729/37/980.0
44Gemma 4 31BNone19.41482.111/28/1250.0
45GLM-5.2Medium19.01480.195/90/1390.0
46GPT-5.5None19.01479.819/23/1220.0
47MiMo-V2.5None18.71477.935/48/2410.0
48Gemini 3.1 Flash LiteXHigh18.61477.410/15/1390.0
49GPT-5.6 LunaNone18.51476.812/30/1200.0
50Claude Opus 4.5Medium16.91488.62/5/5121.3
51MiMo-V2.5Medium16.51465.639/101/3470.0
52DeepSeek V4 FlashMedium16.51465.48/23/1310.0
53North Mini CodeMedium16.21463.714/31/1180.0
54GPT-5.6 LunaMedium16.21463.69/25/1280.0
55Claude Opus 4.5XHigh16.21463.414/29/1200.0
56GPT-OSS 120BXHigh13.21446.018/29/1160.0
57DeepSeek V4 FlashNone12.61442.924/89/3740.0
58Minimax M3Medium12.31440.915/29/1190.0
59GPT-5.4 NanoNone11.71437.429/82/2130.0
60GPT-5.4 NanoXHigh11.61437.169/129/1260.0
61Gemini 3.5 FlashXHigh11.51436.243/65/550.0
62GLM-5.2XHigh11.21434.645/67/2120.0
63Gemini 3.1 Flash LiteMedium11.21434.312/29/1220.0
64GPT 4.1None9.71425.610/32/1210.0
65Nemotron 3 Ultra 550B A55BXHigh8.61419.36/29/1270.0
66GPT-5.5XHigh7.91415.216/41/1050.0

Entrants

Every admitted unique code identity for GB2-04: Xiangqi. Capped draws are rated; unilateral model faults are listed separately.

Showing 83 entrants.
EntrantModelReasoningStatusScoreRatingW / L / DRated / attemptedOpponentsCapped drawsModel faultsAdmitted pluginsRepairGenerated
E-0ca15b39b465b370claude-fable-5highestrated100.01950143 / 2 / 18163 / 16382001first pass2026-07-03T17:50:00Z
E-eb1f17ce19beffd0claude-fable-5mediumrated42.1161455 / 13 / 95163 / 16382001first pass2026-07-02T16:51:45Z
E-8c9e611d78967342claude-opus-4-5mediumrated16.914892 / 5 / 5158 / 6542071first pass2026-07-02T16:51:45Z
E-9a77e43e752532c8claude-opus-4-5nonerated34.6157147 / 9 / 107163 / 16382001first pass2026-07-02T16:51:45Z
E-e3449ff084425b16claude-opus-4-5highestrated16.2146314 / 29 / 120163 / 16382001first pass2026-07-02T16:51:45Z
E-6344242dae68be1bclaude-opus-4-8highestrated54.0168380 / 8 / 75163 / 16382001first pass2026-07-03T17:20:00Z
E-688a139ef8557587claude-opus-4-8nonerated19.8148414 / 27 / 122163 / 16382001first pass2026-07-02T16:51:45Z
E-caf91ab5b69b1e64claude-opus-4-8mediumrated20.4148812 / 17 / 135164 / 16482001first pass2026-07-02T16:51:45Z
E-8e980ad934b3251eclaude-sonnet-5highestrated33.6156439 / 11 / 113163 / 16382001first pass2026-07-03T16:50:00Z
E-b1fc5b99a5deb881claude-sonnet-5mediumrated25.5151733 / 18 / 112163 / 16382001repaired2026-07-02T16:51:45Z
E-be938b7d5557f479claude-sonnet-5nonerated20.4148815 / 11 / 138164 / 16482001first pass2026-07-02T16:51:45Z
E-1460cf3cd86be35ccohere/north-mini-codemediumrated16.2146414 / 31 / 118163 / 16382001repaired2026-07-02T16:51:45Z
E-5d143d6301429619deepseek/deepseek-v4-flashmediumrated16.514658 / 23 / 131162 / 16281001first pass2026-07-01T00:15:48Z
E-81bc9a578754f220deepseek/deepseek-v4-flashnonerated1.613795 / 64 / 94163 / 16382001first pass2026-07-02T16:51:45Z
E-a43d18fadfcc5a89deepseek/deepseek-v4-flashnonerated20.2148714 / 11 / 137162 / 16281001first pass2026-07-01T00:15:48Z
E-cb48b9466ec54175deepseek/deepseek-v4-flashnonerated16.214635 / 14 / 143162 / 16281001repaired2026-07-02T06:10:40Z
E-38bc194a470fbf62deepseek/deepseek-v4-prohighestrated25.0151524 / 33 / 106163 / 16482001repaired2026-07-02T16:51:45Z
E-2be6f5c895691cb3google/gemini-3.1-flash-litehighestrated18.6147710 / 15 / 139164 / 16482001repaired2026-07-02T16:51:45Z
E-860c31323fa5eda7google/gemini-3.1-flash-litemediumrated11.2143412 / 29 / 122163 / 16482001repaired2026-07-02T16:51:45Z
E-32cfa6c9dfb1d16fgoogle/gemini-3.5-flashmediumrated23.4150534 / 28 / 102164 / 16482001repaired2026-07-02T16:51:45Z
E-8e95359e4cbd1851google/gemini-3.5-flashhighestrated11.5143643 / 65 / 55163 / 16482001repaired2026-07-02T16:51:45Z
E-62ca2464f2212fc9google/gemma-4-31b-itmediumrated25.9152013 / 18 / 133164 / 16482001repaired2026-07-02T16:51:45Z
E-ec0cf4b37c805eeegoogle/gemma-4-31b-itnonerated19.4148211 / 28 / 125164 / 16482001first pass2026-07-02T16:51:45Z
E-ecb06954153be8d5gpt-4.1nonerated9.7142610 / 32 / 121163 / 16482001first pass2026-07-02T16:51:45Z
E-6f1aae863396df76gpt-5mediumrated19.5148329 / 37 / 98164 / 16482001first pass2026-07-02T16:51:45Z
E-7e3da77777a95e31gpt-5highestrated20.1148617 / 23 / 124164 / 16482001repaired2026-07-02T16:51:45Z
E-0b4132559ee98cafgpt-5.4mediumrated23.8150828 / 15 / 121164 / 16482001first pass2026-07-02T16:51:45Z
E-8d62bf1b340a70dcgpt-5.4nonerated20.5148918 / 25 / 120163 / 16382001first pass2026-07-02T16:51:45Z
E-9279285adff8ed29gpt-5.4highestrated30.0154467 / 17 / 79163 / 16382001first pass2026-07-02T16:51:45Z
E-040a4b654fceeb0cgpt-5.4-minihighestrated26.9152620 / 23 / 119162 / 16281001repaired2026-07-02T06:10:40Z
E-0880cdf1a43cb90cgpt-5.4-mininonerated27.6153033 / 35 / 96164 / 16482001first pass2026-07-02T16:51:45Z
E-6d633c9c2680eb32gpt-5.4-minimediumrated29.9154338 / 18 / 106162 / 16281001first pass2026-07-01T00:15:48Z
E-74f5bcc8ad3796a5gpt-5.4-minimediumrated22.7150231 / 13 / 119163 / 16382001first pass2026-07-02T16:51:45Z
E-c9bf6a0be0c43fd1gpt-5.4-mininonerated18.7147814 / 27 / 121162 / 16281001first pass2026-07-02T06:10:40Z
E-f9e13a78abccfd1fgpt-5.4-minimediumrated28.8153732 / 16 / 114162 / 16281001first pass2026-07-02T06:10:40Z
E-ff4778924359442bgpt-5.4-mininonerated17.5147116 / 25 / 121162 / 16281001first pass2026-07-01T00:15:48Z
E-3403c285ceec6345gpt-5.4-nanohighestrated23.3150563 / 55 / 44162 / 16281001first pass2026-07-09T17:30:50Z
E-48f60c9100c65daagpt-5.4-nanononerated9.5142413 / 44 / 105162 / 16281001first pass2026-07-01T00:15:48Z
E-a32cb67d48c62b3bgpt-5.4-nanomediumrated41.2160952 / 14 / 96162 / 16281001repaired2026-07-09T17:30:50Z
E-bbf36865f2b7fe63gpt-5.4-nanohighestrated0.013706 / 74 / 82162 / 16281001first pass2026-07-02T06:10:40Z
E-c8f4bd9fcf2e481egpt-5.4-nanononerated13.9145016 / 38 / 108162 / 16281001repaired2026-07-02T06:10:40Z
E-fd2be90162c92ecfgpt-5.4-nanomediumrated20.3148725 / 32 / 105162 / 16281001first pass2026-07-01T00:15:48Z
E-64bf5daf186f8119gpt-5.5highestrated7.9141516 / 41 / 105162 / 16281001first pass2026-07-02T16:51:45Z
E-9e7bdad81107b7e4gpt-5.5mediumrated19.5148323 / 29 / 110162 / 16281001first pass2026-07-02T16:51:45Z
E-ba1aa87056709e9agpt-5.5nonerated19.0148019 / 23 / 122164 / 16482001first pass2026-07-02T16:51:45Z
E-5389e160269f5cebgpt-5.6-lunamediumrated16.214649 / 25 / 128162 / 16281001first pass2026-07-10T05:30:29Z
E-71a01107bf3f9fc1gpt-5.6-lunanonerated18.5147712 / 30 / 120162 / 16281001first pass2026-07-10T05:30:29Z
E-e348813cda8b38b7gpt-5.6-lunahighestrated21.0149132 / 27 / 103162 / 16281001first pass2026-07-10T05:30:29Z
E-270a233119b6cc62gpt-5.6-solhighestrated50.7166480 / 6 / 76162 / 16281001first pass2026-07-10T05:30:29Z
E-c81bf4d15f3d48f1gpt-5.6-solmediumrated25.0151520 / 17 / 125162 / 16281001first pass2026-07-10T05:30:29Z
E-f0b7195272d6417egpt-5.6-solnonerated29.8154330 / 17 / 115162 / 16281001first pass2026-07-10T10:07:13Z
E-50ee0aadbc66fe0egpt-5.6-terranonerated24.3151113 / 8 / 141162 / 16281001first pass2026-07-10T05:30:29Z
E-89c18d144e85d89fgpt-5.6-terramediumrated20.5148821 / 16 / 125162 / 16281001first pass2026-07-10T05:30:29Z
E-b85c80e7475ef9ecgpt-5.6-terrahighestrated32.7156054 / 16 / 92162 / 16281001first pass2026-07-10T05:30:29Z
E-c60620c3c72a6064minimax/minimax-m3mediumrated12.3144115 / 29 / 119163 / 16382001repaired2026-07-02T16:51:45Z
E-eb97811a38950c20moonshotai/kimi-k2.7-codemediumrated21.3149314 / 29 / 120163 / 16482001repaired2026-07-02T16:51:45Z
E-6f4b3b55e4ec7cf5nex-agi/nex-n2-prononerated19.614838 / 11 / 143162 / 16281001repaired2026-07-11T17:22:09Z
E-958dea26b779a042nvidia/nemotron-3-ultra-550b-a55bhighestrated8.614196 / 29 / 127162 / 16281001repaired2026-07-11T17:22:09Z
E-f36b99b3d76fbb35nvidia/nemotron-3-ultra-550b-a55bnonerated23.7150716 / 24 / 124164 / 16482001first pass2026-07-02T16:51:45Z
E-7e92e17a121661f4o3mediumrated21.7149513 / 24 / 126163 / 16482001first pass2026-07-02T16:51:45Z
E-3a27113d21c73b01openai/gpt-oss-120bhighestrated13.2144618 / 29 / 116163 / 16482001repaired2026-07-02T16:51:45Z
E-f1288f2abfdbbfe4openai/gpt-oss-120bmediumrated24.815138 / 21 / 135164 / 16482001repaired2026-07-02T16:51:45Z
E-ea08328e287de1adqwen/qwen3.7-maxmediumrated21.0149130 / 34 / 100164 / 16482001first pass2026-07-02T16:51:45Z
E-84b9a07f75f324e2qwen/qwen3.7-plusnonerated22.6150111 / 17 / 135163 / 16382001first pass2026-07-02T16:51:45Z
E-25e56c6bfae33c62stepfun/step-3.7-flashmediumrated26.8152519 / 15 / 130164 / 16482001repaired2026-07-02T16:51:45Z
E-3fd10f7865cc280etencent/hy3-previewnonerated25.7151943 / 20 / 100163 / 16382001repaired2026-07-02T16:51:45Z
E-51c104b34ef2a244tencent/hy3-previewhighestrated21.114925 / 15 / 144164 / 16482001first pass2026-07-02T16:51:45Z
E-85934b32572399dax-ai/grok-build-0.1mediumrated25.1151512 / 18 / 133163 / 16382001repaired2026-07-02T16:51:45Z
E-00e6914e513b1656xiaomi/mimo-v2.5mediumrated21.7149613 / 37 / 112162 / 16281001repaired2026-07-02T06:10:40Z
E-23e877112cb95491xiaomi/mimo-v2.5mediumrated13.2144620 / 41 / 101162 / 16281001repaired2026-07-01T00:15:48Z
E-2f7e15b8aa123825xiaomi/mimo-v2.5mediumrated14.714556 / 23 / 134163 / 16382001repaired2026-07-02T16:51:45Z
E-7ad356726cce2b22xiaomi/mimo-v2.5nonerated19.9148529 / 23 / 110162 / 16281001repaired2026-07-01T00:15:48Z
E-d58c55e107783a21xiaomi/mimo-v2.5nonerated17.414716 / 25 / 131162 / 16281001repaired2026-07-02T06:10:40Z
E-f8929b12716a2221xiaomi/mimo-v2.5highestrated25.1151518 / 22 / 122162 / 16281001repaired2026-07-02T06:10:40Z
E-ffdebde8a72ed049xiaomi/mimo-v2.5-promediumrated29.4154039 / 26 / 97162 / 16281001repaired2026-07-02T16:51:45Z
E-1d5f5ff0402ff944z-ai/glm-5.2nonerated26.8152523 / 12 / 128163 / 16382001repaired2026-07-02T16:51:45Z
E-3efc86009429a22cz-ai/glm-5.2nonerated25.5151815 / 17 / 130162 / 16281001first pass2026-07-02T06:10:40Z
E-6d59400949b2dde9z-ai/glm-5.2highestrated15.1145719 / 23 / 120162 / 16281001repaired2026-07-11T15:43:48Z
E-912f31ad14c4bf0az-ai/glm-5.2mediumrated12.7144323 / 36 / 103162 / 16281001repaired2026-07-11T17:22:09Z
E-947248ef34168cdez-ai/glm-5.2mediumrated25.4151772 / 54 / 36162 / 16281001repaired2026-07-01T00:15:48Z
E-e6dc2409fc5fe917z-ai/glm-5.2nonerated25.4151715 / 11 / 136162 / 16281001first pass2026-07-01T00:15:48Z
E-f776c26a98306f5dz-ai/glm-5.2nonerated16.7146729 / 39 / 94162 / 16281001first pass2026-07-11T14:00:45Z
E-f9359f32abb5e3c8z-ai/glm-5.2highestrated7.3141226 / 44 / 92162 / 16281001repaired2026-07-02T06:10:40Z