Benchmark menu

Per-game leaderboard

GB2-02: Chess

This page shows one pooled row per model and reasoning setting for GB2-02: Chess. Repeated evaluated entrants are combined in the same way as the benchmark page's game filter.

GB2-02: Chess

Chess

Chess is an 8x8 tactical piece-movement game with asymmetric pieces, castling, en passant, promotion, check, checkmate, and automatic draw rules.

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

GB2-02: Chess 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: GB2-02: Chess
GB2-02: Chess - Reasoning Variants
Rank Model Reasoning Score Raw Elo W / L / D Uncertainty
1GPT-5.6 SolXHigh100.01979.8147/4/110.0
2Claude Opus 4.8XHigh60.31755.8103/2/580.0
3Claude Fable 5Medium59.41750.994/2/670.0
4Claude Fable 5XHigh53.61717.993/1/690.0
5GPT-5.4XHigh32.91601.254/2/1070.0
6GPT-5.5Medium32.91601.048/4/1110.0
7GPT-5.6 SolMedium31.81595.067/6/890.0
8GPT-5.6 TerraXHigh28.11574.137/7/1180.0
9Claude Sonnet 5XHigh24.71555.229/5/1290.0
10Gemini 3.5 FlashMedium20.61531.721/7/1350.0
11GPT-5.4 MiniXHigh15.51503.012/24/2900.0
12GPT-5.4 NanoXHigh15.21501.218/20/2870.0
13Claude Opus 4.5Medium14.91499.49/6/1490.0
14GPT-5.6 SolNone14.81499.114/8/1400.0
15GPT-5.6 TerraNone14.71498.76/9/1470.0
16GLM-5.2Medium14.61498.30/7/1550.0
17GPT 5XHigh14.51497.410/15/1390.0
18GPT-5.4Medium14.51497.58/15/1400.0
19GPT-5.4 MiniMedium14.51497.314/32/4410.0
20Qwen3.7 MaxMedium14.01494.710/11/1420.0
21MiMo-V2.5Medium13.71492.818/36/4340.0
22GPT-5.4None13.61492.42/12/1500.0
23GPT-OSS 120BMedium13.61492.07/10/1470.0
24Claude Opus 4.5XHigh13.21490.25/8/1510.0
25Claude Sonnet 5None13.01489.07/15/1420.0
26GPT-5.4 NanoMedium13.01489.212/36/4400.0
27Qwen3.7 PlusMedium13.01488.92/7/1550.0
28Minimax M3None12.81487.61/15/1470.0
29Kimi K2.7 CodeMedium12.51486.38/18/1380.0
30MiMo-V2.5XHigh11.61481.17/8/1470.0
31Grok Build 0.1Medium11.61480.86/12/1460.0
32GPT-5.6 LunaMedium11.41479.91/11/1500.0
33GPT-5.6 TerraMedium10.91477.53/8/1510.0
34MiMo-V2.5None10.81476.90/15/1470.0
35Nex N2 ProNone10.81476.67/31/1240.0
36Qwen3.7 MaxNone10.81493.14/3/6216.0
37GLM-5.2XHigh10.71475.826/41/4210.0
38Claude Opus 4.8None10.51475.17/19/1360.0
39Gemini 3.1 Flash LiteNone10.51474.63/11/1500.0
40GPT 4.1None10.41474.21/13/1490.0
41Nemotron 3 Ultra 550B A55BMedium10.21473.31/12/1510.0
42DeepSeek V4 ProNone10.11472.72/14/1470.0
43Claude Sonnet 5Medium10.01471.73/11/1500.0
44GPT-5.6 LunaXHigh9.91471.76/11/1450.0
45Step 3.7 FlashMedium9.91471.23/9/1520.0
46DeepSeek V4 FlashXHigh9.71470.411/24/2910.0
47GPT-5.4 MiniNone9.61469.84/41/4430.0
48GPT-5.5None9.21467.21/12/1510.0
49Claude Opus 4.5None9.11467.112/12/1390.0
50Qwen3.7 PlusNone9.11466.92/17/1440.0
51GPT-5.4 NanoNone8.81465.58/57/5850.0
52Claude Opus 4.8Medium8.81465.23/10/1500.0
53GPT-5.6 LunaNone8.71464.81/11/1500.0
54Nemotron 3 Ultra 550B A55BXHigh8.41462.94/25/2970.0
55Hy3 PreviewXHigh8.21462.04/23/1360.0
56GLM-5.2None8.11461.112/54/4210.0
57GPT-OSS 120BXHigh7.91459.90/19/1440.0
58Minimax M3Medium7.51457.83/19/1410.0
59DeepSeek V4 FlashNone6.91454.41/35/2890.0
60DeepSeek V4 FlashMedium6.71453.85/37/2820.0
61Hy3 PreviewNone3.91437.80/22/1410.0
62MiMo-V2.5-ProNone0.01415.58/24/1320.0

Entrants

Every admitted unique code identity for GB2-02: Chess. Capped draws are rated; unilateral model faults are listed separately.

Showing 83 entrants.
EntrantModelReasoningStatusScoreRatingW / L / DRated / attemptedOpponentsCapped drawsModel faultsAdmitted pluginsRepairGenerated
E-cd3608270e8c00fdclaude-fable-5mediumrated59.4175194 / 2 / 67163 / 16382001first pass2026-07-02T16:51:45Z
E-f6a30e7d9986c9b8claude-fable-5highestrated53.6171893 / 1 / 69163 / 16382001first pass2026-07-03T17:50:00Z
E-0454dbb9530f84f7claude-opus-4-5highestrated13.214905 / 8 / 151164 / 16482001first pass2026-07-02T16:51:45Z
E-16462f3d1f3a7b19claude-opus-4-5nonerated9.1146712 / 12 / 139163 / 16482001first pass2026-07-02T16:51:45Z
E-3cbd11fb314c75e1claude-opus-4-5mediumrated14.914999 / 6 / 149164 / 16482001first pass2026-07-02T16:51:45Z
E-a81bd03e764818f6claude-opus-4-8highestrated60.31756103 / 2 / 58163 / 16382001first pass2026-07-03T17:20:00Z
E-c142942f4138c871claude-opus-4-8nonerated10.514757 / 19 / 136162 / 16281001first pass2026-07-02T16:51:45Z
E-ed71c4ecf219b609claude-opus-4-8mediumrated8.814653 / 10 / 150163 / 16382001first pass2026-07-02T16:51:45Z
E-a1a16bb5799cfdbeclaude-sonnet-5mediumrated10.014723 / 11 / 150164 / 16482001first pass2026-07-02T16:51:45Z
E-e35d82f3fd09a1f4claude-sonnet-5highestrated24.7155529 / 5 / 129163 / 16382001first pass2026-07-03T16:50:00Z
E-e501d6808bd19cccclaude-sonnet-5nonerated13.014897 / 15 / 142164 / 16482001first pass2026-07-02T16:51:45Z
E-08e2baea96c43eb4deepseek/deepseek-v4-flashmediumrated0.114170 / 27 / 135162 / 16281001first pass2026-07-02T06:10:40Z
E-12dcb25370550495deepseek/deepseek-v4-flashhighestrated12.014836 / 12 / 146164 / 16482001repaired2026-07-02T16:51:45Z
E-1e168b9e73c26073deepseek/deepseek-v4-flashmediumrated13.314915 / 10 / 147162 / 16281001repaired2026-07-01T00:15:48Z
E-3358fbcda6ab6f4ddeepseek/deepseek-v4-flashnonerated6.114501 / 17 / 145163 / 16382001first pass2026-07-02T16:51:45Z
E-bc9a8c3886a48505deepseek/deepseek-v4-flashnonerated7.714590 / 18 / 144162 / 16281001first pass2026-07-02T06:10:40Z
E-f2e6dd87c5656ee3deepseek/deepseek-v4-flashhighestrated7.514585 / 12 / 145162 / 16281001first pass2026-07-02T06:10:40Z
E-6c3b019c1b20a09bdeepseek/deepseek-v4-prononerated10.114732 / 14 / 147163 / 16382001first pass2026-07-02T16:51:45Z
E-20b3484be872df52google/gemini-3.1-flash-litenonerated10.514753 / 11 / 150164 / 16482001repaired2026-07-02T16:51:45Z
E-ef7a835bdb46a90egoogle/gemini-3.5-flashmediumrated20.6153221 / 7 / 135163 / 16482001repaired2026-07-02T16:51:45Z
E-e4707b8e4c581edegpt-4.1nonerated10.414741 / 13 / 149163 / 16382001repaired2026-07-02T16:51:45Z
E-5bccb9b671ce5eaegpt-5highestrated14.5149710 / 15 / 139164 / 16482001first pass2026-07-02T16:51:45Z
E-4aa582caf9d9f6dagpt-5.4highestrated32.9160154 / 2 / 107163 / 16382001first pass2026-07-02T16:51:45Z
E-98ddce22d3eb5886gpt-5.4nonerated13.614922 / 12 / 150164 / 16482001first pass2026-07-02T16:51:45Z
E-f4948a32cdd115a9gpt-5.4mediumrated14.514988 / 15 / 140163 / 16382001first pass2026-07-02T16:51:45Z
E-3082b8a32a9c1e1fgpt-5.4-minimediumrated13.414916 / 10 / 146162 / 16281001first pass2026-07-02T06:10:40Z
E-322cbb8be1559087gpt-5.4-mininonerated11.514811 / 11 / 152164 / 16482001first pass2026-07-02T16:51:45Z
E-4f2717a1b63468f4gpt-5.4-minimediumrated16.215075 / 11 / 146162 / 16281001first pass2026-07-01T00:15:48Z
E-59f362f57892ab54gpt-5.4-minihighestrated12.214843 / 11 / 150164 / 16482001first pass2026-07-02T16:51:45Z
E-6724998b59176607gpt-5.4-minimediumrated13.814943 / 11 / 149163 / 16382001first pass2026-07-02T16:51:45Z
E-7ef67fa468b6c12cgpt-5.4-minihighestrated18.815229 / 13 / 140162 / 16281001first pass2026-07-02T06:10:40Z
E-b45c06f99639b8dbgpt-5.4-mininonerated8.114611 / 13 / 148162 / 16281001first pass2026-07-02T06:10:40Z
E-dd45dfa7984ab9fagpt-5.4-mininonerated9.214672 / 17 / 143162 / 16281001repaired2026-07-01T00:15:48Z
E-038a95fb13c8aa94gpt-5.4-nanononerated2.114281 / 20 / 141162 / 16281001repaired2026-07-09T17:30:50Z
E-1ce420518fc32de1gpt-5.4-nanohighestrated11.714822 / 11 / 149162 / 16281001repaired2026-07-09T17:30:50Z
E-23b12c36ef5c7ef8gpt-5.4-nanononerated11.314801 / 16 / 145162 / 16281001repaired2026-07-01T00:15:48Z
E-6a4ccfcf11c5e3f3gpt-5.4-nanomediumrated11.314794 / 18 / 140162 / 16281001repaired2026-07-01T00:15:48Z
E-786cc9019eb3ee2bgpt-5.4-nanononerated11.814833 / 9 / 150162 / 16281001repaired2026-07-02T06:10:40Z
E-a92f8113f0090156gpt-5.4-nanomediumrated13.214906 / 8 / 148162 / 16281001repaired2026-07-02T06:10:40Z
E-b084ba147f956b49gpt-5.4-nanohighestrated18.6152116 / 9 / 138163 / 16382001repaired2026-07-02T16:51:45Z
E-be95cc83ce87847cgpt-5.4-nanononerated10.014723 / 12 / 149164 / 16482001repaired2026-07-02T16:51:45Z
E-d96eaa4f1d20c47bgpt-5.4-nanomediumrated14.614982 / 10 / 152164 / 16482001repaired2026-07-02T16:51:45Z
E-51e935956fa76015gpt-5.5nonerated9.214671 / 12 / 151164 / 16482001first pass2026-07-02T16:51:45Z
E-8460841e3919c568gpt-5.5mediumrated32.9160148 / 4 / 111163 / 16382001first pass2026-07-02T16:51:45Z
E-a30e455ba172d80egpt-5.6-lunahighestrated9.914726 / 11 / 145162 / 16281001repaired2026-07-10T05:30:29Z
E-ba4589e1cf2c827bgpt-5.6-lunanonerated8.714651 / 11 / 150162 / 16281001first pass2026-07-10T05:30:29Z
E-e2dda893ae4363f2gpt-5.6-lunamediumrated11.414801 / 11 / 150162 / 16281001first pass2026-07-10T05:30:29Z
E-0420ca9039edc6fbgpt-5.6-solnonerated14.8149914 / 8 / 140162 / 16281001first pass2026-07-10T05:30:29Z
E-087d760c91df7f17gpt-5.6-solmediumrated31.8159567 / 6 / 89162 / 16281001repaired2026-07-10T05:30:29Z
E-33dc9365cfacf9c0gpt-5.6-solhighestrated100.01980147 / 4 / 11162 / 16281001first pass2026-07-10T05:30:29Z
E-1b12482867c807c9gpt-5.6-terrahighestrated28.1157437 / 7 / 118162 / 16281001first pass2026-07-10T05:30:29Z
E-82ad98d8d570daabgpt-5.6-terramediumrated10.914773 / 8 / 151162 / 16281001repaired2026-07-10T05:30:29Z
E-c6593bd789768bdbgpt-5.6-terranonerated14.714996 / 9 / 147162 / 16281001repaired2026-07-10T05:30:29Z
E-1e46941293882535minimax/minimax-m3nonerated12.814881 / 15 / 147163 / 16382001first pass2026-07-02T16:51:45Z
E-cad87bcb23d33fefminimax/minimax-m3mediumrated7.514583 / 19 / 141163 / 16382101repaired2026-07-02T16:51:45Z
E-85c8a9372a607001moonshotai/kimi-k2.7-codemediumrated12.514868 / 18 / 138164 / 16482101repaired2026-07-02T16:51:45Z
E-811f47e902ce0d21nex-agi/nex-n2-prononerated10.814777 / 31 / 124162 / 16281001repaired2026-07-11T17:22:09Z
E-2404d10bab26a254nvidia/nemotron-3-ultra-550b-a55bhighestrated7.714592 / 12 / 150164 / 16482001repaired2026-07-02T16:51:45Z
E-abd2cae3e3ff9bdbnvidia/nemotron-3-ultra-550b-a55bhighestrated9.014672 / 13 / 147162 / 16281001repaired2026-07-11T17:22:09Z
E-bd70ebbd81fdbef0nvidia/nemotron-3-ultra-550b-a55bmediumrated10.214731 / 12 / 151164 / 16482001repaired2026-07-02T16:51:45Z
E-8f0c6569aa132f8eopenai/gpt-oss-120bmediumrated13.614927 / 10 / 147164 / 16482001first pass2026-07-02T16:51:45Z
E-e5b4a3586049e1c9openai/gpt-oss-120bhighestrated7.914600 / 19 / 144163 / 16382001repaired2026-07-02T16:51:45Z
E-5f64c2ae9860ba38qwen/qwen3.7-maxnonerated10.814934 / 3 / 6269 / 7446051first pass2026-07-02T16:51:45Z
E-95265340f8562bfdqwen/qwen3.7-maxmediumrated14.0149510 / 11 / 142163 / 16482001repaired2026-07-02T16:51:45Z
E-010dafcd7561851aqwen/qwen3.7-plusnonerated9.114672 / 17 / 144163 / 16482001repaired2026-07-02T16:51:45Z
E-57293d5b71f14882qwen/qwen3.7-plusmediumrated13.014892 / 7 / 155164 / 16482001repaired2026-07-02T16:51:45Z
E-0ccea44addccfff0stepfun/step-3.7-flashmediumrated9.914713 / 9 / 152164 / 16482001repaired2026-07-02T16:51:45Z
E-d910e47dd13c2c71tencent/hy3-previewnonerated3.914380 / 22 / 141163 / 16382001repaired2026-07-02T16:51:45Z
E-fbf6af15f65f01d7tencent/hy3-previewhighestrated8.214624 / 23 / 136163 / 16482001repaired2026-07-02T16:51:45Z
E-99592fa0331c6679x-ai/grok-build-0.1mediumrated11.614816 / 12 / 146164 / 16482001repaired2026-07-02T16:51:45Z
E-39b08fe4c0318552xiaomi/mimo-v2.5nonerated10.814770 / 15 / 147162 / 16281001first pass2026-07-01T00:15:48Z
E-5b213ae773e821ccxiaomi/mimo-v2.5mediumrated13.414919 / 12 / 143164 / 16482001repaired2026-07-02T16:51:45Z
E-9077f1e8e006290bxiaomi/mimo-v2.5highestrated11.614817 / 8 / 147162 / 16281001repaired2026-07-02T06:10:40Z
E-a5f372b0e5962ee5xiaomi/mimo-v2.5mediumrated11.614810 / 10 / 152162 / 16281001repaired2026-07-01T00:15:48Z
E-c37f25e181320efbxiaomi/mimo-v2.5mediumrated16.015069 / 14 / 139162 / 16281001repaired2026-07-02T06:10:40Z
E-b9f44937a1269e8dxiaomi/mimo-v2.5-prononerated0.014168 / 24 / 132164 / 16482001first pass2026-07-02T16:51:45Z
E-32435b01ac08ed41z-ai/glm-5.2mediumrated14.614980 / 7 / 155162 / 16281001repaired2026-07-11T17:22:09Z
E-4442c0e8a06187bfz-ai/glm-5.2highestrated5.614485 / 24 / 133162 / 16281001repaired2026-07-11T14:00:45Z
E-4959351a96fd2b82z-ai/glm-5.2nonerated0.414182 / 25 / 136163 / 16382001repaired2026-07-02T16:51:45Z
E-925b589068dc7268z-ai/glm-5.2nonerated7.114561 / 15 / 146162 / 16281001repaired2026-07-11T14:00:45Z
E-98394109d97d67eez-ai/glm-5.2highestrated10.114720 / 8 / 156164 / 16482001repaired2026-07-02T16:51:45Z
E-b090ee9c8b9921adz-ai/glm-5.2nonerated16.615099 / 14 / 139162 / 16281001first pass2026-07-01T00:15:48Z
E-dd5764d86cd88052z-ai/glm-5.2highestrated16.2150721 / 9 / 132162 / 16281001first pass2026-07-02T06:10:40Z