Benchmark menu

Per-game leaderboard

GB2-04: Xiangqi

This page compares player programs for GB2-04: Xiangqi in the balanced filter. Programs are ranked by their relative score within this game.

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 player programs using DuelLab's encoded rules for Xiangqi; they are not a broad measure of human play strength.

GB2-04: Xiangqi 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: Balanced Game: GB2-04: Xiangqi
GB2-04: Xiangqi - Balanced filter
Rank Model Score Contributing programs Raw Elo W / D / L Uncertainty
1GPT-5.6 Sol90.111805.964 / 11 / 312.5
2Claude Fable 556.111589.227 / 27 / 1416.4
3GPT-5.4 Nano55.111578.024 / 54 / 610.5
4Claude Opus 551.321553.249 / 80 / 459.6
5MiMo-V2.5-Pro50.911553.516 / 43 / 1713.2
6Gemini 3.5 Flash50.911550.626 / 47 / 139.9
7GPT-5.4 Mini50.711552.419 / 49 / 813.2
8Step 3.7 Flash46.211519.810 / 69 / 99.2
9GPT-5.6 Terra44.811511.113 / 66 / 99.2
10GPT 543.811505.616 / 54 / 1410.5
11Minimax M343.311504.17 / 64 / 513.2
12Kimi K342.211487.122 / 88 / 170.4
13Qwen3.7 Max42.011491.416 / 58 / 207.5
14Gemini 3.1 Flash Lite41.711494.87 / 63 / 414.0
15GLM-5.241.511497.47 / 46 / 919.2
16Grok 4.541.311485.612 / 75 / 136.0
17Grok Build 0.140.811485.95 / 73 / 610.5
18Claude Opus 4.539.511475.510 / 68 / 157.8
19GPT-5.539.511475.120 / 58 / 167.5
20Claude Opus 4.839.311474.55 / 77 / 108.1
21Gemini 3.5 Flash Lite39.221470.018 / 183 / 273.2
22Claude Sonnet 538.811475.014 / 46 / 1613.2
23MiMo-V2.537.831466.616 / 185 / 4910.4
24Gemma 4 31B37.811468.18 / 65 / 512.5
25Inkling37.411457.87 / 90 / 192.5
26DeepSeek V4 Flash37.311470.74 / 49 / 919.2
27Gemini 3.6 Flash36.921453.830 / 172 / 372.1
28GPT-OSS 120B36.811460.32 / 75 / 710.5
29North Mini Code36.621474.17 / 75 / 1229.4
30O336.411458.79 / 60 / 1111.8
31Ox Alpha35.231503.29 / 30 / 977.5
32GPT-5.6 Luna34.811449.19 / 58 / 1112.5
33Kimi K2.7 Code34.611445.28 / 68 / 129.2
34Ling 3.0 Flash32.621437.513 / 125 / 2616.2
35Inkling Small31.611470.82 / 13 / 565.4
36Qwen3.8 Max31.111477.03 / 9 / 477.5
37Muse Spark 1.229.411414.49 / 40 / 2713.2
38GPT-5.427.211398.88 / 41 / 3311.1
39Laguna S 2.126.511383.312 / 90 / 460.0
40LongCat 2.019.521340.819 / 147 / 881.2

Individual player programs

Each row is one accepted player program for GB2-04: Xiangqi. 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 49 player programs.
Player IDModelStatusScoreEloConfidenceW / D / LRated / attemptedOpponentsCapped drawsFaults / playersGeneration
E-eb1f17ce19beffd0Claude Fable 5Rated56.1158927 / 27 / 1468 / 683400 / 1First try · 2026-07-02
E-8c9e611d78967342Claude Opus 4.5Waiting0 / 0 / 00 / 0000 / 1First try · 2026-07-02
E-cbae2963ded72d76Claude Opus 4.5Rated39.5147610 / 68 / 1593 / 944600 / 1First try · 2026-07-21
E-caf91ab5b69b1e64Claude Opus 4.8Rated39.314755 / 77 / 1092 / 924300 / 1First try · 2026-07-02
E-048d3dcf802043b4Claude Opus 5Rated51.1155215 / 50 / 2186 / 864300 / 1First try · 2026-07-25
E-d0f0a2b1c4bbddaeClaude Opus 5Rated51.6155434 / 30 / 2488 / 884400 / 1First try · 2026-07-25
E-7031fd4afe7acb91Claude Sonnet 5Rated38.8147514 / 46 / 1676 / 763600 / 1First try · 2026-08-09
E-1460cf3cd86be35cNorth Mini CodeRated37.314733 / 45 / 856 / 562800 / 1Repaired · 2026-07-02
E-5d143d6301429619DeepSeek V4 FlashRated37.314714 / 49 / 962 / 623100 / 1First try · 2026-07-01
E-860c31323fa5eda7Gemini 3.1 Flash LiteRated41.714957 / 63 / 474 / 763502 / 1Repaired · 2026-07-02
E-32cfa6c9dfb1d16fGemini 3.5 FlashRated50.9155126 / 47 / 1386 / 864100 / 1Repaired · 2026-07-02
E-5c270e2afa7b70f5Gemini 3.5 Flash LiteRated42.5149410 / 78 / 1199 / 1025000 / 1First try · 2026-07-24
E-6098de52ddfabfb1Gemini 3.5 Flash LiteRated35.914468 / 105 / 16129 / 1355300 / 1First try · 2026-07-24
E-cefb1dec9ce36375Gemini 3.6 FlashRated30.8141310 / 96 / 25131 / 1315200 / 1First try · 2026-07-24
E-d109ab12db58a65fGemini 3.6 FlashRated43.0149520 / 76 / 12108 / 1085400 / 1First try · 2026-07-24
E-62ca2464f2212fc9Gemma 4 31BRated37.814688 / 65 / 578 / 803402 / 1Repaired · 2026-07-02
E-6f1aae863396df76GPT 5Rated43.8150616 / 54 / 1484 / 844000 / 1First try · 2026-07-02
E-cae96a5e03c2613eGPT-5.4Rated27.213998 / 41 / 3382 / 823700 / 1First try · 2026-08-09
E-74f5bcc8ad3796a5GPT-5.4 MiniRated50.7155219 / 49 / 876 / 763800 / 1First try · 2026-07-02
E-a32cb67d48c62b3bGPT-5.4 NanoRated55.1157824 / 54 / 684 / 843900 / 1Repaired · 2026-07-09
E-9e7bdad81107b7e4GPT-5.5Rated39.5147520 / 58 / 1694 / 944700 / 1First try · 2026-07-02
E-3c11110e415436c3GPT-5.6 LunaRated34.814499 / 58 / 1178 / 783600 / 1First try · 2026-08-09
E-7f8aa62c2a56b424GPT-5.6 SolRated90.1180664 / 11 / 378 / 783600 / 1First try · 2026-08-09
E-89c18d144e85d89fGPT-5.6 TerraRated44.8151113 / 66 / 988 / 884300 / 1First try · 2026-07-10
E-20e94e7276184071Ling 3.0 FlashRated29.314283 / 32 / 944 / 442200 / 1Repaired · 2026-07-24
E-4ccf296e55b59be3LongCat 2.0Rated17.0132614 / 57 / 45116 / 13949023 / 1Repaired · 2026-07-24
E-9c9e87bb30b3cb99LongCat 2.0Rated22.113565 / 90 / 43138 / 1385300 / 1First try · 2026-07-24
E-57e6f935250459a2Muse Spark 1.2Rated29.414149 / 40 / 2776 / 763600 / 1First try · 2026-08-13
E-c60620c3c72a6064Minimax M3Rated43.315047 / 64 / 576 / 763700 / 1Repaired · 2026-07-02
E-eb97811a38950c20Kimi K2.7 CodeRated34.614458 / 68 / 1288 / 884300 / 1Repaired · 2026-07-02
E-7c724729d138057bKimi K3Rated42.2148722 / 88 / 17127 / 1315000 / 1First try · 2026-07-24
E-7e92e17a121661f4O3Rated36.414599 / 60 / 1180 / 803800 / 1First try · 2026-07-02
E-f1288f2abfdbbfe4GPT-OSS 120BRated36.814602 / 75 / 784 / 844000 / 1Repaired · 2026-07-02
E-e996fd38983e3b7fLaguna S 2.1Rated26.5138312 / 90 / 46148 / 1485700 / 1Repaired · 2026-07-24
E-ea08328e287de1adQwen3.7 MaxRated42.0149116 / 58 / 2094 / 944200 / 1First try · 2026-07-02
E-1f87c69eddf28f4eQwen3.8 MaxLimited data31.114773 / 9 / 416 / 16800 / 1First try · 2026-08-08
E-43ae1b9ca4bd7996Ox AlphaRated41.615456 / 8 / 216 / 16800 / 1Repaired · 2026-08-22
E-6139f660620fd73bOx AlphaRated34.514992 / 11 / 316 / 16800 / 1First try · 2026-08-22
E-be47453e36658247Ox AlphaRated29.314651 / 11 / 416 / 16800 / 1First try · 2026-08-22
E-25e56c6bfae33c62Step 3.7 FlashRated46.2152010 / 69 / 988 / 884200 / 1Repaired · 2026-07-02
E-fce01db31ecf26d2InklingRated37.414587 / 90 / 19116 / 1164400 / 1First try · 2026-07-24
E-20d371c6aae692a2Inkling SmallLimited data31.614712 / 13 / 520 / 201000 / 1Repaired · 2026-08-09
E-ba6a8e6d7fc9a48dGrok 4.5Rated41.3148612 / 75 / 13100 / 1004900 / 1First try · 2026-07-24
E-85934b32572399daGrok Build 0.1Rated40.814865 / 73 / 684 / 844000 / 1Repaired · 2026-07-02
E-00e6914e513b1656MiMo-V2.5Rated37.014637 / 55 / 1678 / 783700 / 1Repaired · 2026-07-02
E-23e877112cb95491MiMo-V2.5Rated35.214505 / 55 / 2484 / 843900 / 1Repaired · 2026-07-01
E-2f7e15b8aa123825MiMo-V2.5Rated39.514764 / 75 / 988 / 884100 / 1Repaired · 2026-07-02
E-ffdebde8a72ed049MiMo-V2.5-ProRated50.9155416 / 43 / 1776 / 763700 / 1Repaired · 2026-07-02
E-912f31ad14c4bf0aGLM-5.2Rated41.514977 / 46 / 962 / 623100 / 1Repaired · 2026-07-11