Benchmark menu

Per-game leaderboard

GB2-08: Tumbleweed

This page shows one pooled row per model and reasoning setting for GB2-08: Tumbleweed. Repeated evaluated entrants are combined in the same way as the benchmark page's game filter.

GB2-08: Tumbleweed

Tumbleweed

Tumbleweed is a hex-grid territory game where players grow visible stacks and final control is determined by line-of-sight strength.

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

GB2-08: Tumbleweed 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: GB2-08: Tumbleweed
GB2-08: Tumbleweed - Reasoning Variants
Rank Model Reasoning Score Raw Elo W / L / D Uncertainty
1Claude Fable 5XHigh98.22132.2184/4/10.0
2Claude Opus 4.8XHigh87.02028.7176/13/00.0
3Claude Opus 4.8None80.91972.2168/21/00.0
4Claude Fable 5Medium80.71970.1178/11/00.0
5Claude Opus 4.5None78.91953.4154/15/190.0
6GPT-5.6 SolMedium78.21947.1154/20/140.0
7O3XHigh75.21919.3162/19/80.0
8Claude Opus 4.5XHigh71.31882.6162/27/00.0
9GPT-5.6 LunaXHigh62.61802.5150/29/90.0
10Kimi K2.7 CodeMedium58.81767.1142/26/210.0
11GPT-5.5XHigh56.71747.3113/12/640.0
12GLM-5.2None55.51736.3325/102/1380.0
13Minimax M3None54.01722.2112/52/250.0
14GPT-5.4XHigh50.21687.0114/39/350.0
15GPT-5.4 NanoXHigh45.91646.9205/99/2580.0
16GPT-5.6 TerraXHigh43.61626.0120/36/320.0
17GPT-5.6 SolNone39.51588.195/41/520.0
18GPT-5.4 MiniXHigh38.31576.8155/82/1400.0
19GPT-5.5Medium35.61552.170/27/890.0
20GPT-5.4 NanoMedium33.71534.1181/161/2190.0
21GLM-5.2XHigh32.81525.5175/194/1950.0
22Claude Opus 4.5Medium32.61523.475/39/760.0
23O3Medium30.91508.346/42/1010.0
24GPT-5.4Medium30.11515.322/38/2310.8
25GPT-5.4 NanoNone29.61495.7171/177/4020.0
26GPT 4.1None28.81488.630/37/1210.0
27GPT-5.6 TerraMedium28.51485.440/39/1070.0
28Gemini 3.1 Flash LiteMedium28.01480.647/64/790.0
29DeepSeek V4 ProNone25.61459.215/20/1510.0
30Claude Sonnet 5XHigh24.41447.933/39/1140.0
31Hy3 PreviewXHigh23.71441.259/73/580.0
32GPT-5.4 MiniMedium23.51439.080/137/3460.0
33GPT-5.5None23.11435.58/40/1380.0
34Qwen3.7 PlusMedium21.11417.00/34/1520.0
35GPT-5.4None20.81413.720/44/1240.0
36GPT-5.6 TerraNone20.61412.915/43/1280.0
37Nex N2 ProNone20.31409.91/43/1450.0
38Step 3.7 FlashXHigh20.01407.17/43/1360.0
39GPT-OSS 120BMedium20.01407.014/45/1270.0
40Claude Opus 4.8Medium19.91405.49/48/1320.0
41Qwen3.7 MaxMedium19.71404.414/45/1270.0
42GPT-5.4 MiniNone19.61402.848/153/3600.0
43GPT 5XHigh19.51402.022/55/1090.0
44Nemotron 3 Ultra 550B A55BNone18.81395.912/48/1290.0
45North Mini CodeNone18.41391.98/49/1320.0
46Claude Sonnet 5Medium18.31391.211/45/1320.0
47MiMo-V2.5Medium18.01388.546/138/1910.0
48Nemotron 3 Ultra 550B A55BMedium18.01387.89/51/1290.0
49Minimax M3Medium17.91387.09/48/1290.0
50Nemotron 3 Ultra 550B A55BXHigh17.51383.723/99/2560.0
51GLM-5.2Medium17.51404.041/105/24823.7
52North Mini CodeMedium17.41383.10/55/1320.0
53Qwen3.7 MaxNone17.21380.611/48/1270.0
54DeepSeek V4 FlashMedium17.11379.818/110/2470.0
55Hy3 PreviewNone16.81377.613/47/1260.0
56Gemini 3.1 Flash LiteXHigh16.71376.16/53/1270.0
57GPT-OSS 120BXHigh16.61375.210/46/1310.0
58Gemma 4 31BNone16.31372.18/49/1290.0
59DeepSeek V4 FlashXHigh16.11370.58/49/1290.0
60GPT 5Medium16.01369.65/66/1150.0
61DeepSeek V4 FlashNone15.91387.725/131/23821.8
62Gemini 3.5 FlashMedium15.51365.40/60/1260.0
63GPT-5.6 LunaMedium15.31363.410/51/1270.0
64DeepSeek V4 ProXHigh15.01360.711/48/1270.0
65Grok Build 0.1Medium14.61357.08/47/1320.0
66MiMo-V2.5XHigh14.51355.41/52/1330.0
67GPT-5.6 LunaNone13.71348.36/57/1250.0
68MiMo-V2.5-ProMedium13.31344.40/58/1280.0
69MiMo-V2.5None11.61329.14/132/2390.0
70Claude Sonnet 5None11.41327.03/56/1300.0
71Mistral Medium 3.5None11.21324.96/64/1180.0
72Gemini 3.5 FlashXHigh5.51272.40/81/1050.0
73GPT-5.6 SolXHigh3.81256.340/123/250.0
74Nex N2 ProMedium2.01276.31/30/538.4

Entrants

Every admitted unique code identity for GB2-08: Tumbleweed. Capped draws are rated; unilateral model faults are listed separately.

Showing 98 entrants.
EntrantModelReasoningStatusScoreRatingW / L / DRated / attemptedOpponentsCapped drawsModel faultsAdmitted pluginsRepairGenerated
E-12891afa894223fdclaude-fable-5highestrated98.22132184 / 4 / 1189 / 18995101repaired2026-07-02T16:51:45Z
E-9ccf296d44d35675claude-fable-5mediumrated80.71970178 / 11 / 0189 / 18995001first pass2026-07-02T16:51:45Z
E-01b57d5e6655f927claude-opus-4-5nonerated78.91953154 / 15 / 19188 / 188951901first pass2026-07-02T16:51:45Z
E-355427eb0d526f34claude-opus-4-5mediumrated32.6152375 / 39 / 76190 / 190967601first pass2026-07-02T16:51:45Z
E-6a0c04b4335bfea0claude-opus-4-5highestrated71.31883162 / 27 / 0189 / 18995001first pass2026-07-02T16:51:45Z
E-22dc6fe5ae5fb8b1claude-opus-4-8highestrated87.02029176 / 13 / 0189 / 18995001first pass2026-07-03T17:20:00Z
E-c2dade0b97891d8aclaude-opus-4-8mediumrated19.914059 / 48 / 132189 / 1899513201first pass2026-07-02T16:51:45Z
E-c9d7578e8375d994claude-opus-4-8nonerated80.91972168 / 21 / 0189 / 18995001first pass2026-07-02T16:51:45Z
E-130fb40b1c7a4d39claude-sonnet-5mediumrated18.3139111 / 45 / 132188 / 1889513201first pass2026-07-02T16:51:45Z
E-b5805acb90227d50claude-sonnet-5highestrated24.4144833 / 39 / 114186 / 1869311401first pass2026-07-03T16:50:00Z
E-cf0ed4bbe4aaadd7claude-sonnet-5nonerated11.413273 / 56 / 130189 / 1909513001first pass2026-07-02T16:51:45Z
E-c36a98e057c264ebcohere/north-mini-codenonerated18.413928 / 49 / 132189 / 1929613201first pass2026-07-11T17:22:09Z
E-efd7b75d5cd3b538cohere/north-mini-codemediumrated17.413830 / 55 / 132187 / 1879413201first pass2026-07-02T16:51:45Z
E-4375cf96eeb624e2deepseek/deepseek-v4-flashnonerated20.9141518 / 51 / 117186 / 1869311701repaired2026-07-02T16:51:45Z
E-43aba68125a9abc5deepseek/deepseek-v4-flashmediumrated18.0138813 / 48 / 126187 / 1879412601first pass2026-07-02T06:10:40Z
E-95b070e1c29e44f0deepseek/deepseek-v4-flashnonerated12.813407 / 76 / 105188 / 1889510501first pass2026-07-02T06:10:40Z
E-a7310645c3b96434deepseek/deepseek-v4-flashhighestrated16.113708 / 49 / 129186 / 1869312901repaired2026-07-02T16:51:45Z
E-b53fd6f34eb6127ddeepseek/deepseek-v4-flashnonerated13.814080 / 4 / 1620 / 26201661first pass2026-07-01T00:15:48Z
E-d28ef17ff6995c62deepseek/deepseek-v4-flashmediumrated16.213725 / 62 / 121188 / 1889512101repaired2026-07-01T00:15:48Z
E-3a5b5c4507a989d3deepseek/deepseek-v4-prohighestrated15.0136111 / 48 / 127186 / 1869312701repaired2026-07-02T16:51:45Z
E-c296a7abab6975d7deepseek/deepseek-v4-prononerated25.6145915 / 20 / 151186 / 1869315101first pass2026-07-02T16:51:45Z
E-b335c9f92035f80bgoogle/gemini-3.1-flash-litehighestrated16.713766 / 53 / 127186 / 1869312701repaired2026-07-02T16:51:45Z
E-cc6fb78c96472032google/gemini-3.1-flash-litemediumrated28.0148147 / 64 / 79190 / 190967901first pass2026-07-02T16:51:45Z
E-bd0bbefbbd252fc5google/gemini-3.5-flashmediumrated15.513650 / 60 / 126186 / 1869312601repaired2026-07-02T16:51:45Z
E-fa332e578ae97122google/gemini-3.5-flashhighestrated5.512720 / 81 / 105186 / 1869310501repaired2026-07-02T16:51:45Z
E-8546650b7690a81agoogle/gemma-4-31b-itnonerated16.313728 / 49 / 129186 / 1869312901first pass2026-07-02T16:51:45Z
E-eabc996d553eebe0gpt-4.1nonerated28.8148930 / 37 / 121188 / 1889512101first pass2026-07-02T16:51:45Z
E-04ae9f2b42e0e036gpt-5mediumrated16.013705 / 66 / 115186 / 1869311501first pass2026-07-02T16:51:45Z
E-ebca8ea756b4a4adgpt-5highestrated19.5140222 / 55 / 109186 / 1879310901first pass2026-07-02T16:51:45Z
E-95f891d54f35bb4agpt-5.4nonerated20.8141420 / 44 / 124188 / 1889512401repaired2026-07-02T16:51:45Z
E-b13a2be40d59c1eagpt-5.4mediumrated30.1151522 / 38 / 2383 / 89532361first pass2026-07-02T16:51:45Z
E-ddc1f3e68bf1e74agpt-5.4highestrated50.21687114 / 39 / 35188 / 188953501first pass2026-07-02T16:51:45Z
E-00b5df785d927901gpt-5.4-mininonerated24.4144825 / 52 / 109186 / 1869310901first pass2026-07-02T06:10:40Z
E-1e5d07fc67fd8710gpt-5.4-minihighestrated54.01722133 / 40 / 17190 / 190961701repaired2026-07-02T16:51:45Z
E-7ff0b78720f446adgpt-5.4-mininonerated14.7135814 / 58 / 116188 / 1889511601first pass2026-07-01T00:15:48Z
E-8cc872d6760c46c1gpt-5.4-minimediumrated16.913784 / 46 / 136186 / 1869313601first pass2026-07-02T06:10:40Z
E-acdb5996d6e8fdfcgpt-5.4-minimediumrated21.6142218 / 36 / 133187 / 1879413301first pass2026-07-01T00:15:48Z
E-b5171a15f0048555gpt-5.4-minimediumrated31.9151758 / 55 / 77190 / 190967701first pass2026-07-02T16:51:45Z
E-b63acb1096519102gpt-5.4-minihighestrated22.7143222 / 42 / 123187 / 1879412301first pass2026-07-02T06:10:40Z
E-bb8ac98c284a38cegpt-5.4-mininonerated19.514039 / 43 / 135187 / 1879413501first pass2026-07-02T16:51:45Z
E-024aff0a983df40dgpt-5.4-nanononerated17.813860 / 42 / 144186 / 1869314401first pass2026-07-09T17:30:50Z
E-26fa12e871bd8f3agpt-5.4-nanomediumrated5.212702 / 91 / 93186 / 186939301repaired2026-07-02T16:51:45Z
E-814593575d73a7cdgpt-5.4-nanononerated17.013798 / 57 / 122187 / 1879412201repaired2026-07-02T06:10:40Z
E-98e55f26cfe52488gpt-5.4-nanohighestrated100.02149185 / 4 / 0189 / 18995001first pass2026-07-02T16:51:45Z
E-ba371b627387f273gpt-5.4-nanohighestrated16.513742 / 47 / 138187 / 1879413801first pass2026-07-02T06:10:40Z
E-bb4437fab8180bfcgpt-5.4-nanohighestrated21.1141718 / 48 / 120186 / 1869312001repaired2026-07-09T17:30:50Z
E-c320ceaf4558afabgpt-5.4-nanononerated18.713949 / 53 / 126188 / 1889512601repaired2026-07-01T00:15:48Z
E-e361d8cbba2abd67gpt-5.4-nanomediumrated80.31966166 / 22 / 0188 / 18894001repaired2026-07-09T17:30:50Z
E-f26c38927e48d019gpt-5.4-nanomediumrated15.6136613 / 48 / 126187 / 1879412601repaired2026-07-02T06:10:40Z
E-fd5a36e5fd795426gpt-5.4-nanononerated64.91823154 / 25 / 10189 / 189951001repaired2026-07-02T16:51:45Z
E-0d83a3c5c5e66085gpt-5.5mediumrated35.6155270 / 27 / 89186 / 186938901first pass2026-07-02T16:51:45Z
E-3e859a6b27767128gpt-5.5highestrated56.71747113 / 12 / 64189 / 189956401first pass2026-07-02T16:51:45Z
E-c42fbee03a029c83gpt-5.5nonerated23.114368 / 40 / 138186 / 1869313801first pass2026-07-02T16:51:45Z
E-0fb7de4e8156a229gpt-5.6-lunahighestrated62.61802150 / 29 / 9188 / 18894901first pass2026-07-10T05:30:29Z
E-8feb37d0677409f2gpt-5.6-lunanonerated13.713486 / 57 / 125188 / 1889412501first pass2026-07-10T05:30:29Z
E-e6198d88365e0492gpt-5.6-lunamediumrated15.3136310 / 51 / 127188 / 1889412701first pass2026-07-10T05:30:29Z
E-0385f0602a8e29e2gpt-5.6-solmediumrated78.21947154 / 20 / 14188 / 188941401first pass2026-07-10T05:30:29Z
E-3ae62f195160add3gpt-5.6-solhighestrated3.8125640 / 123 / 25188 / 188942501first pass2026-07-10T05:30:29Z
E-994624d0bc2e266dgpt-5.6-solnonerated39.5158895 / 41 / 52188 / 188945201first pass2026-07-10T05:30:29Z
E-44cace55a6126cdfgpt-5.6-terranonerated20.6141315 / 43 / 128186 / 1869312801first pass2026-07-10T05:30:29Z
E-b061663dc342c859gpt-5.6-terrahighestrated43.61626120 / 36 / 32188 / 188943201repaired2026-07-10T05:30:29Z
E-d004e78844cdd202gpt-5.6-terramediumrated28.5148540 / 39 / 107186 / 1869310701first pass2026-07-10T05:30:29Z
E-d169e7b29be70652minimax/minimax-m3mediumrated17.913879 / 48 / 129186 / 1869312901repaired2026-07-02T16:51:45Z
E-e67e41d4491d7ad3minimax/minimax-m3nonerated54.01722112 / 52 / 25189 / 189952501first pass2026-07-02T16:51:45Z
E-ba85be2fa53925f5mistralai/mistral-medium-3-5nonerated11.213256 / 64 / 118188 / 1889511801first pass2026-07-02T16:51:45Z
E-251b5d53a5f89562moonshotai/kimi-k2.7-codemediumrated58.81767142 / 26 / 21189 / 189952101repaired2026-07-02T16:51:45Z
E-506d972b5c69a00dnex-agi/nex-n2-prononerated20.314101 / 43 / 145189 / 1929614501repaired2026-07-11T17:22:09Z
E-92332f4d765b2297nex-agi/nex-n2-promediumrated2.012761 / 30 / 536 / 3736511repaired2026-07-02T16:51:45Z
E-15cf0dede27b7e1bnvidia/nemotron-3-ultra-550b-a55bmediumrated18.013889 / 51 / 129189 / 1899612901repaired2026-07-02T16:51:45Z
E-2e3c01d0103fc439nvidia/nemotron-3-ultra-550b-a55bhighestrated16.8137711 / 49 / 129189 / 1929612901repaired2026-07-11T17:22:09Z
E-8c24e8bcbe9b1228nvidia/nemotron-3-ultra-550b-a55bhighestrated18.2139012 / 50 / 127189 / 1899612701first pass2026-07-02T16:51:45Z
E-ada32b27ea6ffeddnvidia/nemotron-3-ultra-550b-a55bnonerated18.8139612 / 48 / 129189 / 1899612901first pass2026-07-02T16:51:45Z
E-1b6fc7dfefb8cea4o3highestrated75.21919162 / 19 / 8189 / 18995801first pass2026-07-03T16:00:00Z
E-35de956c8305ff90o3mediumrated30.9150846 / 42 / 101189 / 1909610111first pass2026-07-02T16:51:45Z
E-24a75273941e6ea3openai/gpt-oss-120bhighestrated16.6137510 / 46 / 131187 / 1879413101repaired2026-07-02T16:51:45Z
E-6e65dec497ff2de3openai/gpt-oss-120bmediumrated20.0140714 / 45 / 127186 / 1869312701repaired2026-07-02T16:51:45Z
E-64624689e7cbd439qwen/qwen3.7-maxmediumrated19.7140414 / 45 / 127186 / 1869312701repaired2026-07-02T16:51:45Z
E-a667eb7d15f7f43eqwen/qwen3.7-maxnonerated17.2138111 / 48 / 127186 / 1869312701first pass2026-07-02T16:51:45Z
E-6c2a9942e92223c8qwen/qwen3.7-plusmediumrated21.114170 / 34 / 152186 / 1869315201first pass2026-07-02T16:51:45Z
E-8b265019ada47f24stepfun/step-3.7-flashhighestrated20.014077 / 43 / 136186 / 1869313601repaired2026-07-02T16:51:45Z
E-56487337fad4192ftencent/hy3-previewnonerated16.8137813 / 47 / 126186 / 1869312601first pass2026-07-02T16:51:45Z
E-81a5e5ef15f371dctencent/hy3-previewhighestrated23.7144159 / 73 / 58190 / 190965801first pass2026-07-02T16:51:45Z
E-3e2fe948d2bcebb0x-ai/grok-build-0.1mediumrated14.613578 / 47 / 132187 / 1879413201repaired2026-07-02T16:51:45Z
E-5f664f9580459829xiaomi/mimo-v2.5highestrated14.513551 / 52 / 133186 / 1869313301repaired2026-07-02T06:10:40Z
E-650d06103e7fa176xiaomi/mimo-v2.5mediumrated30.0149945 / 40 / 102187 / 1879410201repaired2026-07-03T19:35:00Z
E-b5eb7da0f5021b69xiaomi/mimo-v2.5mediumrated6.112781 / 98 / 89188 / 188948901repaired2026-07-02T06:10:40Z
E-cabbf604f15eb575xiaomi/mimo-v2.5nonerated7.812941 / 78 / 108187 / 1879410801first pass2026-07-02T16:51:45Z
E-d51fce0298267f96xiaomi/mimo-v2.5nonerated15.513653 / 54 / 131188 / 1889513101first pass2026-07-01T00:15:48Z
E-bd1bb7ac29877b8fxiaomi/mimo-v2.5-promediumrated13.313440 / 58 / 128186 / 1869312801repaired2026-07-02T16:51:45Z
E-1549af3bdbe8e3c4z-ai/glm-5.2mediumrated23.4143937 / 46 / 104187 / 1879410401repaired2026-07-02T06:10:40Z
E-18e15798a90b1d2fz-ai/glm-5.2mediumunder covered16.114330 / 3 / 1518 / 23181551first pass2026-07-01T00:15:48Z
E-6a361d88d8c1fb48z-ai/glm-5.2nonerated20.614128 / 49 / 131188 / 1909513101first pass2026-07-11T14:00:45Z
E-907d60010bf80864z-ai/glm-5.2highestrated84.52005174 / 15 / 0189 / 19296001repaired2026-07-11T14:00:45Z
E-97efd9455394f6d7z-ai/glm-5.2nonerated79.91962171 / 18 / 0189 / 18995001repaired2026-07-02T16:51:45Z
E-9e8f3e43bfd2810ez-ai/glm-5.2highestrated13.913500 / 64 / 122186 / 1869312201repaired2026-07-02T06:10:40Z
E-b87c8a15936f0f63z-ai/glm-5.2nonerated66.11834146 / 35 / 7188 / 18894701repaired2026-07-02T06:10:40Z
E-bc28f817090c9f60z-ai/glm-5.2highestrated0.012211 / 115 / 73189 / 189957301repaired2026-07-02T16:51:45Z
E-da1e9a6be31e371fz-ai/glm-5.2mediumrated12.913414 / 56 / 129189 / 1929612901repaired2026-07-11T17:22:09Z