Benchmark menu

Per-game leaderboard

GB2-01: Go

This page shows the per-game leaderboard for GB2-01: Go in the intensive filter. Entrants are ranked by their relative per-game score within this game.

GB2-01: Go

Go

Go is a large-grid territory-control game with stone placement, captures, ko restrictions, passing, and final area scoring.

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

Entrants

Every admitted unique code identity for GB2-01: Go. 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 33 entrants.
EntrantModelStatusScoreEloConfidenceW / L / DRated / attemptedOpponentsCapped drawsFaults / pluginsGeneration
E-8000131e469a8bb6Claude Fable 5Under-covered76.415076 / 6 / 012 / 12600 / 1First pass · 2026-07-03
E-5b675f86b98132f4Claude Opus 4.5Under-covered82.415605 / 1 / 06 / 6300 / 1First pass · —
E-3308d2952452916eClaude Opus 4.8Under-covered63.214904 / 5 / 110 / 10510 / 1First pass · 2026-07-03
E-700f3dddd611df07Claude Opus 5Under-covered65.415074 / 4 / 08 / 8400 / 1First pass · 2026-07-25
E-bf06fe9df8858291Claude Opus 5Under-covered15.815021 / 1 / 02 / 2100 / 1First pass · 2026-07-25
E-5e353d79b07fa294Claude Sonnet 5Under-covered52.114971 / 1 / 46 / 6340 / 1First pass · 2026-07-03
E-b9882650a0cde9acDeepSeek V4 FlashUnder-covered6.414830 / 1 / 12 / 2110 / 1First pass · 2026-07-02
E-cb8739e00cafec5bDeepSeek V4 FlashUnder-covered14.815000 / 0 / 22 / 2120 / 1Repaired · 2026-07-02
E-e192048d4eaa3c43DeepSeek V4 ProUnder-covered54.515302 / 0 / 24 / 4220 / 1Repaired · 2026-07-02
E-3ade0bdbb45d890eGemini 3.5 Flash LitePending0 / 0 / 00 / 0000 / 1Repaired · 2026-07-24
E-401e0639de33ca9eGemini 3.5 Flash LitePending0 / 0 / 00 / 0000 / 1Repaired · 2026-07-24
E-e9260a0da3a64563Gemini 3.6 FlashPending0 / 0 / 00 / 0000 / 1Repaired · 2026-07-24
E-3e63b136f656e976GPT 5Under-covered0.014690 / 2 / 02 / 2100 / 1First pass · 2026-07-02
E-5d8a6b14c27539abGPT-5.4Under-covered38.714972 / 2 / 04 / 4200 / 1First pass · 2026-07-02
E-ca99b677101014a8GPT-5.4 MiniUnder-covered9.314370 / 4 / 04 / 4200 / 1First pass · 2026-07-02
E-db1fc33e2a2467d5GPT-5.4 NanoUnder-covered39.414991 / 1 / 24 / 4220 / 1First pass · 2026-07-09
E-fbb3f2dccb7c7fbaGPT-5.4 NanoUnder-covered7.114840 / 1 / 12 / 2110 / 1First pass · 2026-07-02
E-8c61292c31db2722GPT-5.5Under-covered100.015787 / 1 / 08 / 8400 / 1First pass · 2026-07-02
E-38187ed58fb76057GPT-5.6 LunaUnder-covered42.314772 / 4 / 06 / 6300 / 1First pass · 2026-07-10
E-9e683b3cd6c7f7c3GPT-5.6 SolUnder-covered71.615075 / 5 / 010 / 10500 / 1First pass · 2026-07-10
E-36d36f4895d90b11GPT-5.6 TerraUnder-covered62.314883 / 4 / 310 / 10530 / 1First pass · 2026-07-10
E-99c7b0d758665b66Mistral Medium 3.5Under-covered7.814860 / 1 / 12 / 2110 / 1First pass · 2026-07-02
E-c89e5a24623ed70cKimi K3Under-covered14.114991 / 1 / 02 / 2100 / 1Repaired · 2026-07-17
E-d2f6679f6ac952b3Kimi K3Under-covered47.715162 / 1 / 14 / 4210 / 1Repaired · 2026-07-17
E-dbb89dcf5242a5a0Kimi K3Pending0 / 0 / 00 / 0000 / 1Repaired · 2026-07-24
E-ce064a9927030b28Nemotron 3 Ultra 550B A55BUnder-covered0.114700 / 2 / 02 / 2100 / 1Repaired · 2026-07-11
E-4b0ce2bc67b08d8aStep 3.7 FlashUnder-covered1.414720 / 2 / 02 / 2100 / 1Repaired · 2026-07-02
E-29e8870e43d717e5Hy3 PreviewPending0 / 0 / 00 / 0000 / 1First pass · 2026-07-02
E-098480b7039ef18dGrok 4.5Under-covered29.615312 / 0 / 02 / 2100 / 1First pass · 2026-07-17
E-1c8e452ede41ea2eGrok 4.5Pending0 / 0 / 00 / 0000 / 1Repaired · 2026-07-24
E-f9b8636a677996e4Grok 4.5Under-covered0.014690 / 2 / 02 / 2100 / 1First pass · 2026-07-17
E-5ab5088af70c19d6GLM-5.2Under-covered38.414972 / 2 / 04 / 4200 / 1Repaired · 2026-07-11
E-88bed07a2e526eedGLM-5.2Under-covered93.615526 / 2 / 210 / 10520 / 1Repaired · 2026-07-03

GB2-01: Go 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: Intensive Game: GB2-01: Go

Scroll sideways to see every column.

GB2-01: Go - Intensive filter
Rank Model Score Contributing programs Raw Elo W / L / D Uncertainty
1GPT-5.5100.011578.17/1/0100.0
2GLM-5.293.611552.16/2/2100.0
3Claude Opus 4.582.411559.65/1/0100.0
4Claude Fable 576.411507.06/6/094.9
5GPT-5.6 Sol71.611506.85/5/0100.0
6Claude Opus 565.411506.74/4/0100.0
7Claude Opus 4.863.211489.54/5/1100.0
8GPT-5.6 Terra62.311487.53/4/3100.0
9DeepSeek V4 Pro54.511529.82/0/2100.0
10Claude Sonnet 552.111497.21/1/4100.0
11Kimi K347.711515.92/1/1100.0
12GPT-5.6 Luna42.311476.92/4/0100.0
13GPT-5.4 Nano39.411498.71/1/2100.0
14GPT-5.438.711497.22/2/0100.0
15GLM-5.238.411496.62/2/0100.0
16Grok 4.529.611530.52/0/0100.0
17Claude Opus 515.811502.01/1/0100.0
18DeepSeek V4 Flash14.811499.90/0/2100.0
19Kimi K314.111498.51/1/0100.0
20GPT-5.4 Mini9.311436.50/4/0100.0
21Mistral Medium 3.57.811485.60/1/1100.0
22GPT-5.4 Nano7.111484.00/1/1100.0
23DeepSeek V4 Flash6.411482.60/1/1100.0
24Step 3.7 Flash1.411472.20/2/0100.0
25Nemotron 3 Ultra 550B A55B0.111469.60/2/0100.0
26Grok 4.50.011469.50/2/0100.0
27GPT 50.011469.40/2/0100.0