Benchmark menu

Per-game leaderboard

GB2-03: Shogi

This page shows the per-game leaderboard for GB2-03: Shogi in the baseline filter. Entrants are ranked by their relative per-game score within this game.

GB2-03: Shogi

Shogi

Shogi is a 9x9 chess-family game with promotion zones, captured-piece drops, repetition handling, and impasse scoring.

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

Entrants

Every admitted unique code identity for GB2-03: Shogi. 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 41 entrants.
EntrantModelStatusScoreEloConfidenceW / L / DRated / attemptedOpponentsCapped drawsFaults / pluginsGeneration
E-1975db22db58e9b0Claude Opus 4.5Under-covered61.515332 / 0 / 68 / 8400 / 1First pass · 2026-07-02
E-49aaba66f6b19080Claude Opus 5Under-covered86.915827 / 1 / 08 / 8400 / 1First pass · 2026-07-25
E-ecf847457e616425Claude Opus 5Under-covered88.315727 / 1 / 210 / 10500 / 1First pass · 2026-07-25
E-4e52c100ed276347DeepSeek V4 FlashUnder-covered34.714822 / 3 / 38 / 8400 / 1First pass · 2026-07-02
E-ae9d59ec3a8a1d63DeepSeek V4 FlashUnder-covered38.915072 / 2 / 26 / 6300 / 1Repaired · 2026-07-02
E-f82a334a0fd1fb8eDeepSeek V4 ProUnder-covered0.013931 / 9 / 212 / 12600 / 1Repaired · 2026-07-02
E-28274045fbc35ae9Gemini 3.5 Flash LitePending0 / 0 / 00 / 0000 / 1Repaired · 2026-07-24
E-6743f1c221046d65Gemini 3.6 FlashPending0 / 0 / 00 / 0000 / 1First pass · 2026-07-24
E-80b8c1a18d6dd238Gemini 3.6 FlashPending0 / 0 / 00 / 0000 / 1First pass · 2026-07-24
E-ebd456dc6b320c61GPT-5.4Under-covered77.915524 / 0 / 610 / 10500 / 1First pass · 2026-07-02
E-35117a2e624d7970GPT-5.4 MiniUnder-covered44.215000 / 0 / 88 / 8400 / 1First pass · 2026-07-02
E-a51cd55f211305c2GPT-5.4 MiniUnder-covered79.815556 / 1 / 310 / 10500 / 1Repaired · 2026-07-01
E-dfa5098ec9c3cf47GPT-5.4 MiniUnder-covered48.215082 / 1 / 58 / 8400 / 1First pass · 2026-07-02
E-0ecb5b73c09f13b2GPT-5.4 NanoUnder-covered56.014927 / 6 / 114 / 14700 / 1First pass · 2026-07-01
E-e4eac938bdd5d40eGPT-5.4 NanoUnder-covered35.214822 / 3 / 38 / 8400 / 1First pass · 2026-07-02
E-f2a7b43bf689e68eGPT-5.4 NanoUnder-covered58.915154 / 3 / 310 / 10500 / 1First pass · 2026-07-09
E-446036823932df16GPT-5.5Under-covered49.114793 / 5 / 614 / 14710 / 1First pass · 2026-07-02
E-d192bb239087b778GPT-5.6 LunaUnder-covered44.114703 / 6 / 514 / 14700 / 1First pass · 2026-07-10
E-527999604d620080GPT-5.6 SolUnder-covered50.715123 / 3 / 28 / 8410 / 1First pass · 2026-07-10
E-c2f0f8f062659e83GPT-5.6 TerraUnder-covered76.915806 / 0 / 06 / 6300 / 1First pass · 2026-07-10
E-2524de3c7d4a81b7Ling 3.0 FlashUnder-covered25.814343 / 9 / 214 / 14700 / 1Repaired · 2026-07-24
E-641ddca04b054d56Ling 3.0 FlashUnder-covered55.014844 / 6 / 616 / 16800 / 1Repaired · 2026-07-24
E-198e8ddfe9f7ce20LongCat 2.0Under-covered50.214812 / 3 / 914 / 14710 / 1Repaired · 2026-07-24
E-84709c769628f9a2LongCat 2.0Under-covered63.315073 / 2 / 914 / 14730 / 1First pass · 2026-07-24
E-44cc758f104a74abMinimax M3Under-covered34.414681 / 3 / 610 / 10500 / 1First pass · 2026-07-02
E-09859be1b47131a0Kimi K3Pending0 / 0 / 00 / 0000 / 1First pass · 2026-07-24
E-a12d08354d94b221Kimi K3Under-covered57.915263 / 1 / 48 / 8400 / 1First pass · 2026-07-21
E-a05d4cef5f788f16Nex N2 ProUnder-covered20.114541 / 4 / 38 / 8400 / 1Repaired · 2026-07-02
E-08888c30d05ca8cbO3Under-covered23.514600 / 3 / 58 / 8400 / 1First pass · 2026-07-21
E-c90a449ff5e7b79aGPT-OSS 120BUnder-covered36.614852 / 3 / 38 / 8400 / 1First pass · 2026-07-21
E-467272d131a1a99bLaguna S 2.1Under-covered31.614532 / 5 / 512 / 12610 / 1Repaired · 2026-07-24
E-91efdb0c216f8504Laguna S 2.1Under-covered70.315373 / 0 / 710 / 10530 / 1Repaired · 2026-07-24
E-3325ebad2ef000c1Qwen3.7 MaxUnder-covered25.814420 / 5 / 712 / 12600 / 1First pass · 2026-07-02
E-02b2a2f01700292dStep 3.7 FlashUnder-covered51.815142 / 1 / 58 / 8410 / 1Repaired · 2026-07-21
E-2346cd049910cc0aHy3 PreviewUnder-covered31.814942 / 3 / 16 / 6300 / 1First pass · 2026-07-02
E-78048b7c08122f1cInklingUnder-covered58.214974 / 4 / 614 / 14700 / 1Repaired · 2026-07-24
E-adf1f0bb193bd39bInklingUnder-covered100.015856 / 0 / 612 / 12640 / 1First pass · 2026-07-24
E-02f7e54245bd5c85Grok 4.5Pending0 / 0 / 00 / 0000 / 1Repaired · 2026-07-24
E-3c1904811d11cd84Grok 4.5Under-covered51.815142 / 1 / 58 / 8410 / 1Repaired · 2026-07-21
E-b10e12eb6aef112eMiMo-V2.5Under-covered51.915022 / 2 / 610 / 10510 / 1First pass · 2026-07-02
E-b0948c64dddf57adMiMo-V2.5-ProUnder-covered32.714480 / 4 / 1014 / 14710 / 1Repaired · 2026-07-02

GB2-03: Shogi 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: Baseline Game: GB2-03: Shogi

Scroll sideways to see every column.

GB2-03: Shogi - Baseline filter
Rank Model Score Contributing programs Raw Elo W / L / D Uncertainty
1Inkling100.011584.66/0/694.9
2Claude Opus 588.311571.97/1/2100.0
3Claude Opus 586.911581.87/1/0100.0
4GPT-5.4 Mini79.811555.46/1/3100.0
5GPT-5.477.911551.84/0/6100.0
6GPT-5.6 Terra76.911580.46/0/0100.0
7Laguna S 2.170.311537.33/0/7100.0
8LongCat 2.063.311506.53/2/985.3
9Claude Opus 4.561.511533.02/0/6100.0
10GPT-5.4 Nano58.911515.44/3/3100.0
11Inkling58.211496.74/4/685.3
12Kimi K357.911526.13/1/4100.0
13GPT-5.4 Nano56.011492.47/6/185.3
14Ling 3.0 Flash55.011484.34/6/677.5
15MiMo-V2.551.911501.82/2/6100.0
16Grok 4.551.811514.42/1/5100.0
17Step 3.7 Flash51.811514.42/1/5100.0
18GPT-5.6 Sol50.711512.33/3/2100.0
19LongCat 2.050.211481.32/3/985.3
20GPT-5.549.111479.23/5/685.3
21GPT-5.4 Mini48.211507.62/1/5100.0
22GPT-5.4 Mini44.211499.80/0/8100.0
23GPT-5.6 Luna44.111469.53/6/585.3
24DeepSeek V4 Flash38.911507.52/2/2100.0
25GPT-OSS 120B36.611485.22/3/3100.0
26GPT-5.4 Nano35.211482.52/3/3100.0
27DeepSeek V4 Flash34.711481.52/3/3100.0
28Minimax M334.411468.21/3/6100.0
29MiMo-V2.5-Pro32.711447.80/4/1085.3
30Hy3 Preview31.811493.92/3/1100.0
31Laguna S 2.131.611453.12/5/594.9
32Ling 3.0 Flash25.811434.53/9/285.3
33Qwen3.7 Max25.811442.10/5/794.9
34O323.511460.00/3/5100.0
35Nex N2 Pro20.111453.51/4/3100.0
36DeepSeek V4 Pro0.011392.51/9/294.9