Benchmark menu

Per-game leaderboard

GB2-01: Go

This page shows one pooled row per model and reasoning setting for GB2-01: Go. Repeated evaluated entrants are combined in the same way as the benchmark page's game filter.

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.

GB2-01: Go 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: GB2-01: Go
GB2-01: Go - Reasoning Variants
Rank Model Reasoning Score Raw Elo W / L / D Uncertainty
1GPT-5.4XHigh100.02182.5177/0/00.0
2GPT-5.4None93.92109.1170/5/00.0
3Gemini 3.5 FlashMedium90.12063.2163/11/00.0
4Claude Fable 5Medium81.31956.9152/22/00.0
5Hy3 PreviewNone78.91927.2140/14/200.0
6GPT-5.6 SolXHigh78.71925.7158/16/00.0
7GPT-5.6 LunaXHigh76.81902.6157/19/00.0
8Claude Fable 5XHigh76.31895.8153/25/00.0
9GPT-5.4Medium71.31835.5124/12/410.0
10GPT-5.6 LunaMedium70.51825.7136/27/130.0
11Claude Sonnet 5XHigh70.31823.6127/26/250.0
12GPT-5.5XHigh69.21809.8126/9/400.0
13Claude Opus 4.8XHigh67.01782.8125/32/210.0
14GPT-5.6 SolMedium66.41776.8134/38/40.0
15Hy3 PreviewXHigh65.11760.6119/36/210.0
16MiMo-V2.5-ProMedium64.71755.6126/32/170.0
17Qwen3.7 MaxNone61.01711.0110/25/390.0
18Minimax M3None60.31702.495/49/320.0
19GPT 4.1None58.41679.8117/51/80.0
20Claude Opus 4.8None57.31665.9103/38/350.0
21Claude Sonnet 5None57.11663.7114/36/260.0
22GPT-5.6 SolNone55.51644.197/56/210.0
23Nemotron 3 Ultra 550B A55BNone54.81636.3102/49/250.0
24GPT-5.4 MiniXHigh52.51608.3109/57/120.0
25GPT-5.6 TerraMedium50.41583.382/46/480.0
26GPT-5.6 TerraNone50.01578.577/42/570.0
27DeepSeek V4 ProXHigh49.01566.576/71/290.0
28GPT-5.5Medium48.71562.042/13/1220.0
29Qwen3.7 PlusMedium48.11555.289/63/240.0
30Nemotron 3 Ultra 550B A55BMedium47.61548.780/54/420.0
31GPT-5.4 MiniMedium45.71553.5205/123/3731.6
32Claude Opus 4.5None45.71526.441/46/890.0
33GPT-5.5None44.91515.831/27/1180.0
34MiMo-V2.5None44.51511.7218/210/1000.0
35O3Medium44.51511.066/76/340.0
36GLM-5.2XHigh44.11506.565/85/2040.0
37Claude Sonnet 5Medium44.01505.174/67/340.0
38MiMo-V2.5-ProNone42.71489.758/75/430.0
39DeepSeek V4 FlashNone41.21471.965/76/360.0
40Kimi K2.7 CodeMedium40.91467.879/95/20.0
41Claude Opus 4.8Medium40.81467.071/77/280.0
42GLM-5.2None40.51463.6287/335/860.0
43GPT 5XHigh39.81454.876/70/300.0
44Claude Opus 4.5Medium39.21447.824/59/930.0
45GPT-5.6 TerraXHigh38.61439.758/80/380.0
46Gemma 4 31BNone38.21434.970/80/260.0
47DeepSeek V4 ProNone37.71429.650/74/520.0
48GLM-5.2Medium37.21422.689/148/1230.0
49GPT-5.4 MiniNone37.11448.9124/160/8231.6
50DeepSeek V4 FlashXHigh36.91419.0109/171/730.0
51Grok Build 0.1Medium36.61415.759/85/320.0
52Gemini 3.1 Flash LiteMedium35.41401.529/66/810.0
53GPT-5.4 NanoNone35.01414.5199/242/10021.3
54Claude Opus 4.5XHigh30.01336.219/90/670.0
55Nemotron 3 Ultra 550B A55BXHigh30.01335.833/105/420.0
56DeepSeek V4 FlashMedium27.71347.020/127/4344.9
57GPT-5.4 NanoXHigh25.91286.741/216/960.0
58Mistral Medium 3.5None25.41282.443/106/80.0
59GPT-OSS 120BMedium24.31266.837/102/370.0
60MiMo-V2.5Medium23.61259.391/223/380.0
61Minimax M3Medium23.41256.941/123/120.0
62North Mini CodeNone23.01251.150/209/970.0
63Qwen3.7 MaxMedium21.51233.618/113/450.0
64MiMo-V2.5XHigh20.61222.42/100/750.0
65GPT 5Medium19.01202.725/124/270.0
66Qwen3.7 PlusNone18.71199.522/121/330.0
67GPT-5.6 LunaNone15.81165.118/118/390.0
68GPT-5.4 NanoMedium15.31157.970/516/1210.0
69Gemini 3.1 Flash LiteNone14.01143.211/125/400.0
70Mistral Medium 3.5XHigh11.01106.313/131/320.0
71Step 3.7 FlashXHigh7.21061.016/147/130.0

Entrants

Every admitted unique code identity for GB2-01: Go. Capped draws are rated; unilateral model faults are listed separately.

Showing 92 entrants.
EntrantModelReasoningStatusScoreRatingW / L / DRated / attemptedOpponentsCapped drawsModel faultsAdmitted pluginsRepairGenerated
E-2dbc6efbd7db03b5claude-fable-5mediumrated81.31957152 / 22 / 0174 / 18087001first pass2026-07-02T16:51:45Z
E-8000131e469a8bb6claude-fable-5highestrated76.31896153 / 25 / 0178 / 17890001first pass2026-07-03T17:50:00Z
E-2e3eca63f7980facclaude-opus-4-5nonerated45.7152641 / 46 / 89176 / 176888901first pass2026-07-02T16:51:45Z
E-53c8add70ed7d2e7claude-opus-4-5highestrated30.0133619 / 90 / 67176 / 176886701first pass2026-07-02T16:51:45Z
E-7631f602d0516364claude-opus-4-5mediumrated39.2144824 / 59 / 93176 / 176889301first pass2026-07-02T16:51:45Z
E-13ec9509bc80f2bfclaude-opus-4-8mediumrated40.8146771 / 77 / 28176 / 176882801first pass2026-07-02T16:51:45Z
E-3308d2952452916eclaude-opus-4-8highestrated67.01783125 / 32 / 21178 / 178902101first pass2026-07-03T17:20:00Z
E-757a6149e87d8b53claude-opus-4-8nonerated57.31666103 / 38 / 35176 / 176883501first pass2026-07-02T16:51:45Z
E-5e353d79b07fa294claude-sonnet-5highestrated70.31824127 / 26 / 25178 / 178902501first pass2026-07-03T16:50:00Z
E-73ff84eba4ec19cbclaude-sonnet-5nonerated57.11664114 / 36 / 26176 / 176882601first pass2026-07-02T16:51:45Z
E-cd50a27a6bb44b58claude-sonnet-5mediumrated44.0150574 / 67 / 34175 / 178883401first pass2026-07-02T16:51:45Z
E-194759b182ce3244cohere/north-mini-codenonerated39.6145245 / 58 / 73176 / 176887301first pass2026-07-02T16:51:45Z
E-c309b463b29efb71cohere/north-mini-codenonerated6.410505 / 151 / 24180 / 184922401repaired2026-07-11T17:22:09Z
E-b9882650a0cde9acdeepseek/deepseek-v4-flashhighestrated32.3136440 / 97 / 39176 / 176883901first pass2026-07-02T16:51:45Z
E-c4c43ee3f29394f8deepseek/deepseek-v4-flashnonerated41.2147265 / 76 / 36177 / 177893601first pass2026-07-02T06:10:40Z
E-cb8739e00cafec5bdeepseek/deepseek-v4-flashhighestrated41.4147469 / 74 / 34177 / 177893401repaired2026-07-02T06:10:40Z
E-f1d9dfb787d0d902deepseek/deepseek-v4-flashmediumrated11.6111311 / 125 / 41177 / 177894101repaired2026-07-02T06:10:40Z
E-fd9da5310ad15cacdeepseek/deepseek-v4-flashmediumunder covered43.915819 / 2 / 213 / 1813251first pass2026-07-01T00:15:48Z
E-e121525dd1846069deepseek/deepseek-v4-prononerated37.7143050 / 74 / 52176 / 176885201first pass2026-07-02T16:51:45Z
E-e192048d4eaa3c43deepseek/deepseek-v4-prohighestrated49.0156676 / 71 / 29176 / 176882901repaired2026-07-02T16:51:45Z
E-7669b8a03ef19548google/gemini-3.1-flash-litemediumrated35.4140129 / 66 / 81176 / 176888101repaired2026-07-02T16:51:45Z
E-cc0af0bfa6a9a29fgoogle/gemini-3.1-flash-litenonerated14.0114311 / 125 / 40176 / 176884001repaired2026-07-02T16:51:45Z
E-22f31826bcf76511google/gemini-3.5-flashmediumrated90.12063163 / 11 / 0174 / 18087001repaired2026-07-02T16:51:45Z
E-caaa54d3c88e6570google/gemma-4-31b-itnonerated38.2143570 / 80 / 26176 / 176882601first pass2026-07-02T16:51:45Z
E-f50ec6b60d5b85dagpt-4.1nonerated58.41680117 / 51 / 8176 / 17688801first pass2026-07-02T16:51:45Z
E-3e63b136f656e976gpt-5highestrated39.8145576 / 70 / 30176 / 176883001first pass2026-07-02T16:51:45Z
E-adee794ecd761044gpt-5mediumrated19.0120325 / 124 / 27176 / 176882701first pass2026-07-02T16:51:45Z
E-586de6c9939561c3gpt-5.4mediumrated71.31835124 / 12 / 41177 / 177894101first pass2026-07-02T16:51:45Z
E-5d8a6b14c27539abgpt-5.4highestrated100.02182177 / 0 / 0177 / 17789001first pass2026-07-02T16:51:45Z
E-60fa13e461853992gpt-5.4nonerated93.92109170 / 5 / 0175 / 18188001first pass2026-07-02T16:51:45Z
E-3834aa9e894c458bgpt-5.4-mininoneunder covered30.414213 / 9 / 012 / 1612041first pass2026-07-01T00:15:48Z
E-62424dfd649cbac9gpt-5.4-minimediumrated66.21774131 / 35 / 10176 / 176881001first pass2026-07-02T16:51:45Z
E-aa899d4eca8a2891gpt-5.4-minimediumunder covered32.414464 / 7 / 112 / 1512131first pass2026-07-01T00:15:48Z
E-b6ed01547d27188cgpt-5.4-mininonerated43.9150478 / 73 / 27178 / 178902701first pass2026-07-02T06:10:40Z
E-c675a6c67536654dgpt-5.4-minimediumrated38.6144070 / 81 / 26177 / 177892601first pass2026-07-02T06:10:40Z
E-ca99b677101014a8gpt-5.4-minihighestrated52.51608109 / 57 / 12178 / 178901201first pass2026-07-02T06:10:40Z
E-ea1cb793f92b3cffgpt-5.4-mininonerated37.1142143 / 78 / 55176 / 176885501first pass2026-07-02T16:51:45Z
E-22c14c8deb751cb3gpt-5.4-nanomediumrated25.7128427 / 106 / 44177 / 177894401first pass2026-07-02T06:10:40Z
E-5c28f8f5135ce060gpt-5.4-nanononerated27.5130533 / 106 / 38177 / 177893801repaired2026-07-02T06:10:40Z
E-9257cc1e94bf4b17gpt-5.4-nanomediumrated31.6135637 / 99 / 40176 / 176884001first pass2026-07-02T16:51:45Z
E-98c36ba5e36ecf75gpt-5.4-nanomediumrated3.810194 / 154 / 20178 / 178902001first pass2026-07-01T00:15:48Z
E-9eb27042bf28d67cgpt-5.4-nanononerated49.0156696 / 52 / 28176 / 176882801first pass2026-07-09T17:30:50Z
E-a8887794a1195b75gpt-5.4-nanononerated42.1148370 / 74 / 30174 / 180873001repaired2026-07-02T16:51:45Z
E-c48c1aed1cdecc72gpt-5.4-nanomediumrated0.09732 / 157 / 17176 / 176881701repaired2026-07-09T17:30:50Z
E-db1fc33e2a2467d5gpt-5.4-nanohighestrated39.1144633 / 70 / 73176 / 176887301first pass2026-07-09T17:30:50Z
E-f491ad1b583dbcacgpt-5.4-nanononeunder covered21.313040 / 10 / 414 / 1914451first pass2026-07-01T00:15:48Z
E-fbb3f2dccb7c7fbagpt-5.4-nanohighestrated12.711278 / 146 / 23177 / 177892301first pass2026-07-02T06:10:40Z
E-58178b9b32a94ca0gpt-5.5nonerated44.9151631 / 27 / 118176 / 1768811801first pass2026-07-02T16:51:45Z
E-8c61292c31db2722gpt-5.5highestrated69.21810126 / 9 / 40175 / 178884001first pass2026-07-02T16:51:45Z
E-e4496be687faac9dgpt-5.5mediumrated48.7156242 / 13 / 122177 / 1778912201repaired2026-07-02T16:51:45Z
E-38187ed58fb76057gpt-5.6-lunahighestrated76.81903157 / 19 / 0176 / 17688001first pass2026-07-10T05:30:29Z
E-4f775a5b7b265daegpt-5.6-lunamediumrated70.51826136 / 27 / 13176 / 176881301first pass2026-07-10T05:30:29Z
E-959ed218b1c5605bgpt-5.6-lunanonerated15.8116518 / 118 / 39175 / 178883901first pass2026-07-10T05:30:29Z
E-890c38b8e811c121gpt-5.6-solnonerated55.5164497 / 56 / 21174 / 180872101first pass2026-07-10T05:30:29Z
E-9e683b3cd6c7f7c3gpt-5.6-solhighestrated78.71926158 / 16 / 0174 / 18087001first pass2026-07-10T05:30:29Z
E-bc834303cebba06agpt-5.6-solmediumrated66.41777134 / 38 / 4176 / 17688401first pass2026-07-10T05:30:29Z
E-36d36f4895d90b11gpt-5.6-terrahighestrated38.6144058 / 80 / 38176 / 176883801first pass2026-07-10T05:30:29Z
E-40742129939a44b5gpt-5.6-terranonerated50.0157877 / 42 / 57176 / 176885701first pass2026-07-10T05:30:29Z
E-46de264ad4571b48gpt-5.6-terramediumrated50.4158382 / 46 / 48176 / 176884801repaired2026-07-10T05:30:29Z
E-444510032bc433fcminimax/minimax-m3nonerated60.3170295 / 49 / 32176 / 176883201first pass2026-07-02T16:51:45Z
E-e0a841a9daa66219minimax/minimax-m3mediumrated23.4125741 / 123 / 12176 / 176881201repaired2026-07-02T16:51:45Z
E-99c7b0d758665b66mistralai/mistral-medium-3-5highestrated11.0110613 / 131 / 32176 / 176883201first pass2026-07-02T16:51:45Z
E-a0a38f5e77e983bcmistralai/mistral-medium-3-5nonerated25.4128243 / 106 / 8157 / 2798181221repaired2026-07-02T16:51:45Z
E-4935e918b1e70ea1moonshotai/kimi-k2.7-codemediumrated40.9146879 / 95 / 2176 / 17688201repaired2026-07-02T16:51:45Z
E-0ce5e196701b51f3nvidia/nemotron-3-ultra-550b-a55bnonerated54.81636102 / 49 / 25176 / 176882501first pass2026-07-02T16:51:45Z
E-b851008baae8f441nvidia/nemotron-3-ultra-550b-a55bmediumrated47.6154980 / 54 / 42176 / 176884201repaired2026-07-02T16:51:45Z
E-ce064a9927030b28nvidia/nemotron-3-ultra-550b-a55bhighestrated30.0133633 / 105 / 42180 / 184924201repaired2026-07-11T17:22:09Z
E-428923c2eb87dc7ao3mediumrated44.5151166 / 76 / 34176 / 176883401first pass2026-07-02T16:51:45Z
E-a3e0c8f8ea39b5ecopenai/gpt-oss-120bmediumrated24.3126737 / 102 / 37176 / 176883701repaired2026-07-02T16:51:45Z
E-24581eb49b81bf8fqwen/qwen3.7-maxmediumrated21.5123418 / 113 / 45176 / 176884501repaired2026-07-02T16:51:45Z
E-8a70cd704fcbcf6fqwen/qwen3.7-maxnonerated61.01711110 / 25 / 39174 / 180873901first pass2026-07-02T16:51:45Z
E-1e5dceaf2ba3ca9aqwen/qwen3.7-plusmediumrated48.1155589 / 63 / 24176 / 176882401repaired2026-07-02T16:51:45Z
E-5e09f0c994a59f3cqwen/qwen3.7-plusnonerated18.7120022 / 121 / 33176 / 176883301repaired2026-07-03T18:55:00Z
E-4b0ce2bc67b08d8astepfun/step-3.7-flashhighestrated7.2106116 / 147 / 13176 / 176881301repaired2026-07-02T16:51:45Z
E-29e8870e43d717e5tencent/hy3-previewhighestrated65.11761119 / 36 / 21176 / 176882101first pass2026-07-02T16:51:45Z
E-3407ff2dd1928eb5tencent/hy3-previewnonerated78.91927140 / 14 / 20174 / 242872001first pass2026-07-02T16:51:45Z
E-f1ded648f3ab17dcx-ai/grok-build-0.1mediumrated36.6141659 / 85 / 32176 / 176883201repaired2026-07-02T16:51:45Z
E-1208f50b0908ecb4xiaomi/mimo-v2.5mediumrated27.9131157 / 115 / 4176 / 17688401repaired2026-07-02T16:51:45Z
E-2a71bee21bd7c0b9xiaomi/mimo-v2.5mediumrated19.4120834 / 108 / 34176 / 176883401repaired2026-07-02T06:10:40Z
E-2cdd8ae895784956xiaomi/mimo-v2.5nonerated56.21653111 / 51 / 14176 / 176881401first pass2026-07-02T06:10:40Z
E-8478c64d84536b61xiaomi/mimo-v2.5highestrated20.612222 / 100 / 75177 / 177897501repaired2026-07-02T06:10:40Z
E-912a4a40bbdcbd45xiaomi/mimo-v2.5nonerated40.2146060 / 83 / 33176 / 176883301first pass2026-07-02T16:51:45Z
E-a168350bd057f924xiaomi/mimo-v2.5nonerated37.1142247 / 76 / 53176 / 176885301first pass2026-07-01T00:15:48Z
E-9ce4191c7f1f3b3exiaomi/mimo-v2.5-prononerated42.7149058 / 75 / 43176 / 176884301first pass2026-07-02T16:51:45Z
E-5ab5088af70c19d6z-ai/glm-5.2highestrated40.3146034 / 60 / 84178 / 180908401repaired2026-07-11T14:00:45Z
E-5bc0612062635fa8z-ai/glm-5.2nonerated40.9146891 / 83 / 3177 / 17789301repaired2026-07-01T00:15:48Z
E-5c3b7f5666a38043z-ai/glm-5.2nonerated36.8141854 / 83 / 42179 / 182914201first pass2026-07-11T14:00:45Z
E-6a7eb114b16dc845z-ai/glm-5.2nonerated65.81769116 / 34 / 26176 / 176882601first pass2026-07-02T06:10:40Z
E-88bed07a2e526eedz-ai/glm-5.2highestrated47.9155331 / 25 / 120176 / 1768812001repaired2026-07-03T18:27:00Z
E-b2a148bd3f2766ffz-ai/glm-5.2mediumrated38.9144420 / 50 / 110180 / 1809211001repaired2026-07-01T00:15:48Z
E-c8076ea61de8da45z-ai/glm-5.2nonerated18.7120026 / 135 / 15176 / 176881501first pass2026-07-02T16:51:45Z
E-f889d782e3cce209z-ai/glm-5.2mediumrated35.4140269 / 98 / 13180 / 184921301repaired2026-07-11T17:22:09Z