Benchmark menu

Per-game leaderboard

GB2-04: Xiangqi

This page shows the per-game leaderboard for GB2-04: Xiangqi in the balanced filter. Entrants are ranked by their relative per-game 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 generated programs on DuelLab's encoded rules for Xiangqi; they are not a broad measure of human play strength.

Entrants

Every admitted unique code identity for GB2-04: Xiangqi. Elo and W/L/D use the public historical sequential-Elo result universe. Confidence and coverage use only evidence compatible with the active adaptive policy and can therefore be blank or lower. Capped draws are rated; unilateral model faults are listed separately.

Showing 47 entrants.
EntrantModelStatusScoreEloConfidenceW / L / DRated / attemptedOpponentsCapped drawsFaults / pluginsGeneration
E-eb1f17ce19beffd0Claude Fable 5Under-covered100.015524 / 0 / 48 / 8400 / 1First pass · 2026-07-02
E-cbae2963ded72d76Claude Opus 4.5Under-covered55.515031 / 1 / 46 / 6300 / 1First pass · —
E-caf91ab5b69b1e64Claude Opus 4.8Under-covered65.014860 / 1 / 910 / 10500 / 1First pass · 2026-07-02
E-048d3dcf802043b4Claude Opus 5Under-covered83.315142 / 1 / 710 / 10500 / 1First pass · 2026-07-25
E-d0f0a2b1c4bbddaeClaude Opus 5Under-covered56.514862 / 3 / 38 / 8400 / 1First pass · 2026-07-25
E-b1fc5b99a5deb881Claude Sonnet 5Under-covered34.614710 / 2 / 46 / 6300 / 1Repaired · 2026-07-02
E-1460cf3cd86be35cNorth Mini CodePending0 / 0 / 00 / 0000 / 1Repaired · 2026-07-02
E-860c31323fa5eda7Gemini 3.1 Flash LiteUnder-covered52.514980 / 0 / 66 / 6300 / 1Repaired · 2026-07-02
E-32cfa6c9dfb1d16fGemini 3.5 FlashUnder-covered35.315001 / 1 / 24 / 4200 / 1Repaired · 2026-07-02
E-2fe680857b884561Gemini 3.5 Flash LiteUnder-covered64.814991 / 1 / 68 / 8400 / 1Repaired · 2026-07-24
E-5c270e2afa7b70f5Gemini 3.5 Flash LiteUnder-covered60.514921 / 2 / 58 / 8400 / 1First pass · 2026-07-24
E-1ff96286ae16ecd4Gemini 3.6 FlashUnder-covered54.514711 / 3 / 610 / 10500 / 1Repaired · 2026-07-24
E-d109ab12db58a65fGemini 3.6 FlashUnder-covered72.714981 / 1 / 810 / 10500 / 1First pass · 2026-07-24
E-62ca2464f2212fc9Gemma 4 31BPending0 / 0 / 00 / 0000 / 1Repaired · 2026-07-02
E-6f1aae863396df76GPT 5Under-covered50.314770 / 2 / 68 / 8400 / 1First pass · 2026-07-02
E-0b4132559ee98cafGPT-5.4Under-covered36.215011 / 1 / 24 / 4200 / 1First pass · 2026-07-02
E-6d633c9c2680eb32GPT-5.4 MiniUnder-covered55.515302 / 0 / 24 / 4200 / 1First pass · 2026-07-01
E-74f5bcc8ad3796a5GPT-5.4 MiniUnder-covered43.215122 / 1 / 14 / 4200 / 1First pass · 2026-07-02
E-f9e13a78abccfd1fGPT-5.4 MiniUnder-covered65.615002 / 2 / 48 / 8400 / 1First pass · 2026-07-02
E-a32cb67d48c62b3bGPT-5.4 NanoUnder-covered36.114730 / 2 / 46 / 6300 / 1Repaired · 2026-07-09
E-fd2be90162c92ecfGPT-5.4 NanoUnder-covered0.014990 / 0 / 22 / 2100 / 1First pass · 2026-07-01
E-9e7bdad81107b7e4GPT-5.5Under-covered0.915000 / 0 / 22 / 2100 / 1First pass · 2026-07-02
E-5389e160269f5cebGPT-5.6 LunaUnder-covered34.914990 / 0 / 44 / 4200 / 1First pass · 2026-07-10
E-c81bf4d15f3d48f1GPT-5.6 SolUnder-covered63.914972 / 2 / 48 / 8400 / 1First pass · 2026-07-10
E-89c18d144e85d89fGPT-5.6 TerraUnder-covered73.915121 / 0 / 78 / 8400 / 1First pass · 2026-07-10
E-20e94e7276184071Ling 3.0 FlashPending0 / 0 / 00 / 0000 / 1Repaired · 2026-07-24
E-46a1c9f4e3ff6058LongCat 2.0Pending0 / 0 / 00 / 0000 / 1Repaired · 2026-07-24
E-4ccf296e55b59be3LongCat 2.0Pending0 / 0 / 00 / 0000 / 1Repaired · 2026-07-24
E-c60620c3c72a6064Minimax M3Pending0 / 0 / 00 / 0000 / 1Repaired · 2026-07-02
E-eb97811a38950c20Kimi K2.7 CodePending0 / 0 / 00 / 0000 / 1Repaired · 2026-07-02
E-0f7ca9245c7db7c7Kimi K3Under-covered0.915000 / 0 / 22 / 2100 / 1Repaired · 2026-07-21
E-35e5c9532c697b2cKimi K3Pending0 / 0 / 00 / 0000 / 1Repaired · 2026-07-24
E-7e92e17a121661f4O3Under-covered52.114980 / 0 / 66 / 6300 / 1First pass · 2026-07-02
E-f1288f2abfdbbfe4GPT-OSS 120BUnder-covered56.714870 / 1 / 78 / 8400 / 1Repaired · 2026-07-02
E-e996fd38983e3b7fLaguna S 2.1Pending0 / 0 / 00 / 0000 / 1Repaired · 2026-07-24
E-ea08328e287de1adQwen3.7 MaxPending0 / 0 / 00 / 0000 / 1First pass · 2026-07-02
E-25e56c6bfae33c62Step 3.7 FlashUnder-covered66.415011 / 1 / 68 / 8400 / 1Repaired · 2026-07-02
E-7ca32267720b2e1aInklingUnder-covered71.814870 / 1 / 1112 / 12600 / 1Repaired · 2026-07-24
E-d9e91f86e4e39739InklingUnder-covered82.715262 / 0 / 68 / 8400 / 1Repaired · 2026-07-24
E-1a7064508fe2a12fGrok 4.5Under-covered65.715000 / 0 / 88 / 8400 / 1Repaired · 2026-07-17
E-83f4cc0ffc20bde5Grok 4.5Under-covered37.015021 / 1 / 24 / 4200 / 1Repaired · 2026-07-17
E-ba6a8e6d7fc9a48dGrok 4.5Under-covered83.815282 / 0 / 68 / 8400 / 1First pass · 2026-07-24
E-85934b32572399daGrok Build 0.1Pending0 / 0 / 00 / 0000 / 1Repaired · 2026-07-02
E-00e6914e513b1656MiMo-V2.5Pending0 / 0 / 00 / 0000 / 1Repaired · 2026-07-02
E-23e877112cb95491MiMo-V2.5Pending0 / 0 / 00 / 0000 / 1Repaired · 2026-07-01
E-2f7e15b8aa123825MiMo-V2.5Pending0 / 0 / 00 / 0000 / 1Repaired · 2026-07-02
E-ffdebde8a72ed049MiMo-V2.5-ProPending0 / 0 / 00 / 0000 / 1Repaired · 2026-07-02

GB2-04: Xiangqi leaderboard

Entrants are ranked by relative per-game score (0–100). Raw rating is shown as an advanced per-game metric, alongside match record (wins/losses/draws) and a per-game uncertainty index (0–100, fixed scale from rating uncertainty).

Reasoning level: Balanced Game: GB2-04: Xiangqi

Scroll sideways to see every column.

GB2-04: Xiangqi - Balanced filter
Rank Model Score Contributing programs Raw Elo W / L / D Uncertainty
1Claude Fable 5100.011551.94/0/4100.0
2Grok 4.583.811527.52/0/6100.0
3Claude Opus 583.311514.02/1/7100.0
4Inkling82.711525.82/0/6100.0
5GPT-5.6 Terra73.911512.51/0/7100.0
6Gemini 3.6 Flash72.711498.01/1/8100.0
7Inkling71.811486.90/1/1194.9
8Step 3.7 Flash66.411501.21/1/6100.0
9Grok 4.565.711500.20/0/8100.0
10GPT-5.4 Mini65.611500.02/2/4100.0
11Claude Opus 4.865.011486.30/1/9100.0
12Gemini 3.5 Flash Lite64.811498.91/1/6100.0
13GPT-5.6 Sol63.911497.42/2/4100.0
14Gemini 3.5 Flash Lite60.511492.31/2/5100.0
15GPT-OSS 120B56.711486.60/1/7100.0
16Claude Opus 556.511486.32/3/3100.0
17Claude Opus 4.555.511502.71/1/4100.0
18GPT-5.4 Mini55.511530.32/0/2100.0
19Gemini 3.6 Flash54.511470.51/3/6100.0
20Gemini 3.1 Flash Lite52.511498.10/0/6100.0
21O352.111497.50/0/6100.0
22GPT 550.311477.00/2/6100.0
23GPT-5.4 Mini43.211511.82/1/1100.0
24Grok 4.537.011502.51/1/2100.0
25GPT-5.436.211501.21/1/2100.0
26GPT-5.4 Nano36.111473.40/2/4100.0
27Gemini 3.5 Flash35.311499.91/1/2100.0
28GPT-5.6 Luna34.911499.30/0/4100.0
29Claude Sonnet 534.611471.10/2/4100.0
30Kimi K30.911500.00/0/2100.0
31GPT-5.50.911500.00/0/2100.0
32GPT-5.4 Nano0.011498.70/0/2100.0