Benchmark menu

Per-game leaderboard

GB2-05: Hex

This page shows one pooled row per model and reasoning setting for GB2-05: Hex. Repeated evaluated entrants are combined in the same way as the benchmark page's game filter.

GB2-05: Hex

Hex

Hex is a connection game on a hexagonal grid where players race to join opposite board edges, with a swap option after the first move.

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

GB2-05: Hex 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: GB2-05: Hex
GB2-05: Hex - Reasoning Variants
Rank Model Reasoning Score Raw Elo W / L / D Uncertainty
1GPT-5.4XHigh100.02197.6188/4/00.0
2Claude Fable 5XHigh92.92105.6187/5/00.0
3GPT-5.5Medium85.92015.8173/19/00.0
4DeepSeek V4 ProXHigh85.72012.7176/16/00.0
5GPT-5.4None82.81975.7171/21/00.0
6GPT 5XHigh82.31969.2169/23/00.0
7GPT-5.4 NanoXHigh81.01952.8319/65/00.0
8GPT-5.6 SolMedium80.81950.3164/28/00.0
9GPT-5.6 SolXHigh79.91938.7168/24/00.0
10GPT-5.6 TerraXHigh79.71935.9168/24/00.0
11GPT-5.5XHigh76.61895.8163/29/00.0
12Claude Fable 5Medium71.01823.4156/36/00.0
13GPT-5.6 TerraMedium66.31762.3144/48/00.0
14Claude Sonnet 5Medium64.71742.3125/67/00.0
15Nemotron 3 Ultra 550B A55BNone64.11734.2137/55/00.0
16Hy3 PreviewXHigh63.91731.4135/57/00.0
17GPT 5Medium63.81730.8134/58/00.0
18Gemini 3.5 FlashMedium63.81730.4131/61/00.0
19Claude Sonnet 5XHigh63.61727.8129/64/00.0
20GPT-5.6 SolNone61.61701.9138/54/00.0
21Claude Opus 4.5None61.51700.3120/72/00.0
22Grok Build 0.1Medium61.11695.2124/68/00.0
23O3XHigh60.21684.2128/64/00.0
24Kimi K2.7 CodeMedium59.61675.9129/63/00.0
25Claude Opus 4.5XHigh57.61650.3112/80/00.0
26GPT-5.4 MiniXHigh57.01643.2247/137/00.0
27GPT-5.6 LunaXHigh57.01643.0128/64/00.0
28GPT-5.6 TerraNone54.91615.9111/81/00.0
29GPT-5.5None54.81614.4118/74/00.0
30Gemma 4 31BMedium54.51609.8118/74/00.0
31Gemini 3.5 FlashXHigh54.31607.8115/77/00.0
32GPT-5.6 LunaMedium53.71600.4117/75/00.0
33O3Medium53.31595.0116/76/00.0
34Claude Opus 4.8Medium52.61586.1123/69/00.0
35GLM-5.2XHigh52.01578.1348/233/00.0
36Claude Opus 4.8XHigh51.91576.7114/79/00.0
37Qwen3.7 PlusMedium51.91576.1122/70/00.0
38GPT-5.4Medium51.11566.0102/90/00.0
39GLM-5.2Medium51.01605.5140/68/047.5
40Claude Opus 4.5Medium50.71560.7109/84/00.0
41Step 3.7 FlashXHigh50.01552.690/102/00.0
42Claude Sonnet 5None48.41531.591/101/00.0
43North Mini CodeMedium46.71509.499/93/00.0
44Qwen3.7 MaxMedium45.31491.4102/90/00.0
45Qwen3.7 MaxNone44.91486.8103/89/00.0
46Nex N2 ProNone44.41479.984/112/00.0
47GPT-5.4 NanoMedium43.71491.6271/319/023.7
48Step 3.7 FlashMedium43.21464.192/100/00.0
49Qwen3.7 PlusNone39.81420.580/112/00.0
50Nemotron 3 Ultra 550B A55BXHigh39.51416.4151/237/00.0
51Minimax M3None37.71393.981/111/00.0
52GLM-5.2None37.11385.1309/466/00.0
53GPT-5.4 MiniMedium36.91409.9159/238/031.6
54DeepSeek V4 FlashXHigh36.21374.2153/231/00.0
55MiMo-V2.5None35.31362.0218/359/00.0
56MiMo-V2.5Medium34.71355.2134/250/00.0
57GPT-OSS 120BMedium34.61353.876/116/00.0
58Claude Opus 4.8None34.51352.057/135/00.0
59MiMo-V2.5-ProMedium33.81343.668/124/00.0
60DeepSeek V4 FlashNone29.01281.3190/387/00.0
61DeepSeek V4 ProNone28.91279.372/120/00.0
62MiMo-V2.5-ProNone28.51274.759/133/00.0
63Mistral Medium 3.5XHigh23.91215.945/147/00.0
64Mistral Medium 3.5None22.01191.057/136/00.0
65GPT-5.4 NanoNone20.61199.950/346/031.6
66DeepSeek V4 FlashMedium19.81162.587/299/00.0
67Nex N2 ProMedium19.41157.135/157/00.0
68Gemini 3.1 Flash LiteMedium18.81150.037/155/00.0
69GPT-5.4 MiniNone18.21141.3122/458/00.0
70GPT 4.1None17.01125.833/160/00.0
71Hy3 PreviewNone15.81111.341/151/00.0
72Gemma 4 31BNone13.31078.327/165/00.0
73Gemini 3.1 Flash LiteXHigh6.4988.828/164/00.0
74Gemini 3.1 Flash LiteNone5.8981.319/173/00.0
75Minimax M3Medium5.4977.011/181/00.0
76GPT-5.6 LunaNone0.0906.89/183/00.0

Entrants

Every admitted unique code identity for GB2-05: Hex. Capped draws are rated; unilateral model faults are listed separately.

Showing 101 entrants.
EntrantModelReasoningStatusScoreRatingW / L / DRated / attemptedOpponentsCapped drawsModel faultsAdmitted pluginsRepairGenerated
E-5aa4402ccce7b855claude-fable-5highestrated92.92106187 / 5 / 0192 / 19296001repaired2026-07-02T16:51:45Z
E-ad7cf41c05ec3f64claude-fable-5mediumrated71.01823156 / 36 / 0192 / 19296001first pass2026-07-02T16:51:45Z
E-7e9bc3ebc12ef500claude-opus-4-5highestrated57.61650112 / 80 / 0192 / 19296001first pass2026-07-02T16:51:45Z
E-934b5bc34a7e20b9claude-opus-4-5nonerated61.51700120 / 72 / 0192 / 19296001first pass2026-07-02T16:51:45Z
E-ff0722d17402bafaclaude-opus-4-5mediumrated50.71561109 / 84 / 0193 / 19397001first pass2026-07-02T16:51:45Z
E-233f9cae6335e53dclaude-opus-4-8nonerated34.5135257 / 135 / 0192 / 19296001first pass2026-07-02T16:51:45Z
E-6774d700e60de31aclaude-opus-4-8highestrated51.91577114 / 79 / 0193 / 19397001repaired2026-07-02T16:51:45Z
E-924d7e6ee41b562eclaude-opus-4-8mediumrated52.61586123 / 69 / 0192 / 19296001first pass2026-07-02T16:51:45Z
E-c902807aab849f31claude-sonnet-5highestrated63.61728129 / 64 / 0193 / 19397001first pass2026-07-03T16:50:00Z
E-e0a09b1ea3f11175claude-sonnet-5mediumrated64.71742125 / 67 / 0192 / 19296001first pass2026-07-02T16:51:45Z
E-e619c51e7d5d70d2claude-sonnet-5nonerated48.4153191 / 101 / 0192 / 19296001first pass2026-07-02T16:51:45Z
E-a0518a43c688d1e2cohere/north-mini-codemediumrated46.7150999 / 93 / 0192 / 19296001first pass2026-07-02T16:51:45Z
E-06a41d0e11b18b77deepseek/deepseek-v4-flashmediumrated19.1115341 / 153 / 0194 / 19498001first pass2026-07-01T00:15:48Z
E-0dca18c79b6ac9d7deepseek/deepseek-v4-flashnonerated32.4132676 / 116 / 0192 / 19296001first pass2026-07-02T16:51:45Z
E-2c1cbd253f3a9d69deepseek/deepseek-v4-flashmediumrated20.5117246 / 146 / 0192 / 19296001first pass2026-07-02T06:10:40Z
E-b306c8f5ffbbec38deepseek/deepseek-v4-flashhighestrated12.9107430 / 162 / 0192 / 19296001repaired2026-07-02T06:10:40Z
E-b3d889b0631db85fdeepseek/deepseek-v4-flashhighestrated59.51675123 / 69 / 0192 / 19296001repaired2026-07-02T16:51:45Z
E-b8554f0ccf0845dadeepseek/deepseek-v4-flashnonerated19.4115742 / 150 / 0192 / 19296001first pass2026-07-02T06:10:40Z
E-efa8d9109b008ee9deepseek/deepseek-v4-flashnonerated35.2136172 / 121 / 0193 / 19397001repaired2026-07-01T00:15:48Z
E-0ca4798825ceaccbdeepseek/deepseek-v4-prohighestrated85.72013176 / 16 / 0192 / 19296001repaired2026-07-02T16:51:45Z
E-da5f3b1a4e370e1adeepseek/deepseek-v4-prononerated28.9127972 / 120 / 0192 / 19296001repaired2026-07-02T16:51:45Z
E-7603462aff103041google/gemini-3.1-flash-litemediumrated18.8115037 / 155 / 0192 / 19296001repaired2026-07-02T16:51:45Z
E-a72dd193e1dc4331google/gemini-3.1-flash-litehighestrated6.498928 / 164 / 0192 / 19296001repaired2026-07-02T16:51:45Z
E-d979b43c3aeea657google/gemini-3.1-flash-litenonerated5.898119 / 173 / 0192 / 19296001first pass2026-07-02T16:51:45Z
E-a7ce764239377b3fgoogle/gemini-3.5-flashmediumrated63.81730131 / 61 / 0192 / 19296001repaired2026-07-02T16:51:45Z
E-b50da126631c1ea1google/gemini-3.5-flashhighestrated54.31608115 / 77 / 0192 / 19296001repaired2026-07-02T16:51:45Z
E-e8e17fbbdd12faa4google/gemma-4-31b-itnonerated13.3107827 / 165 / 0192 / 19296001first pass2026-07-02T16:51:45Z
E-fd1bc1e2e6ac48fbgoogle/gemma-4-31b-itmediumrated54.51610118 / 74 / 0192 / 19296001repaired2026-07-02T16:51:45Z
E-1b9f1f7b70f02927gpt-4.1nonerated17.0112633 / 160 / 0193 / 19397001first pass2026-07-02T16:51:45Z
E-9e5b308c41a36374gpt-5mediumrated63.81731134 / 58 / 0192 / 19296001first pass2026-07-02T16:51:45Z
E-c5ad048b6fb4e93dgpt-5highestrated82.31969169 / 23 / 0192 / 19296001first pass2026-07-02T16:51:45Z
E-6d3546010ef68f50gpt-5.4nonerated82.81976171 / 21 / 0192 / 19296001repaired2026-07-02T16:51:45Z
E-cafab3c275850d3bgpt-5.4mediumrated51.11566102 / 90 / 0192 / 19296001first pass2026-07-02T16:51:45Z
E-f6403f7a30e19e82gpt-5.4highestrated100.02198188 / 4 / 0192 / 19296001first pass2026-07-02T16:51:45Z
E-0791f6b66243ec1agpt-5.4-minimediumrated58.91667112 / 80 / 0192 / 19296001first pass2026-07-02T16:51:45Z
E-427bdffeacc6c394gpt-5.4-mininonerated12.5106927 / 165 / 0192 / 19296001repaired2026-07-02T16:51:45Z
E-481582e8f8e3217egpt-5.4-minihighestrated70.61818146 / 46 / 0192 / 19296001first pass2026-07-02T16:51:45Z
E-539afc540807da47gpt-5.4-minimediumrated20.0116544 / 149 / 0193 / 19397001first pass2026-07-02T06:10:40Z
E-8ed627956c0a0292gpt-5.4-mininonerated28.1126957 / 139 / 0196 / 196100001first pass2026-07-01T00:15:48Z
E-95d1a872f51b78e7gpt-5.4-minihighestrated43.51468101 / 91 / 0192 / 19296001first pass2026-07-02T06:10:40Z
E-cdd304da89074d54gpt-5.4-mininonerated13.9108638 / 154 / 0192 / 19296001first pass2026-07-02T06:10:40Z
E-ce84b7a3c6105fb2gpt-5.4-minimediumunder covered31.613973 / 9 / 012 / 1712051first pass2026-07-01T00:15:48Z
E-3311575b341ee4a8gpt-5.4-nanononerated13.7108322 / 170 / 0192 / 19296001repaired2026-07-09T17:30:50Z
E-49b3c6006a3b9fccgpt-5.4-nanononeunder covered36.514605 / 7 / 012 / 1712051first pass2026-07-01T00:15:48Z
E-54b9ca4996a5589dgpt-5.4-nanohighestrated74.91874144 / 48 / 0192 / 19296001first pass2026-07-02T16:51:45Z
E-6c37eeef15b82287gpt-5.4-nanononerated11.6105623 / 169 / 0192 / 19296001repaired2026-07-02T16:51:45Z
E-83cfa14483bf0d43gpt-5.4-nanomediumrated22.3119538 / 156 / 0194 / 19498001first pass2026-07-02T06:10:40Z
E-8e40431df091d53fgpt-5.4-nanomediumrated91.42087181 / 11 / 0192 / 19296001first pass2026-07-02T16:51:45Z
E-a0d8c8fd6b01598cgpt-5.4-nanomediumrated30.2129749 / 143 / 0192 / 19296001first pass2026-07-09T17:30:50Z
E-b05a7e0987de9967gpt-5.4-nanohighestrated87.22032175 / 17 / 0192 / 19296001first pass2026-07-09T17:30:50Z
E-ff2b4db95370e3d6gpt-5.4-nanomediumunder covered30.913883 / 9 / 012 / 1712051first pass2026-07-01T00:15:48Z
E-6f42dbbf02274b56gpt-5.5nonerated54.81614118 / 74 / 0192 / 19296001first pass2026-07-02T16:51:45Z
E-762e9d80a60b41edgpt-5.5highestrated76.61896163 / 29 / 0192 / 19296001first pass2026-07-02T16:51:45Z
E-ffa82d1e96e897abgpt-5.5mediumrated85.92016173 / 19 / 0192 / 19296001first pass2026-07-02T16:51:45Z
E-25a83ddaeb1268a4gpt-5.6-lunahighestrated57.01643128 / 64 / 0192 / 19296001first pass2026-07-10T05:30:29Z
E-59156a669808a24fgpt-5.6-lunanonerated0.09079 / 183 / 0192 / 19296001repaired2026-07-10T05:30:29Z
E-e917387a1c57aa23gpt-5.6-lunamediumrated53.71600117 / 75 / 0192 / 19296001first pass2026-07-10T05:30:29Z
E-471e9297eea18ffdgpt-5.6-solnonerated61.61702138 / 54 / 0192 / 19296001first pass2026-07-10T05:30:29Z
E-af9c2c2998294ad0gpt-5.6-solhighestrated79.91939168 / 24 / 0192 / 19296001first pass2026-07-10T05:30:29Z
E-d61f8454991c5422gpt-5.6-solmediumrated80.81950164 / 28 / 0192 / 19296001first pass2026-07-10T05:30:29Z
E-012ecb9ce0709c05gpt-5.6-terrahighestrated79.71936168 / 24 / 0192 / 19296001repaired2026-07-10T05:30:29Z
E-1f00b423eab1c19dgpt-5.6-terranonerated54.91616111 / 81 / 0192 / 19296001first pass2026-07-10T05:30:29Z
E-9664e98d37ece097gpt-5.6-terramediumrated66.31762144 / 48 / 0192 / 19296001first pass2026-07-10T05:30:29Z
E-33797d7b77c7800cminimax/minimax-m3nonerated37.7139481 / 111 / 0192 / 19296001repaired2026-07-02T16:51:45Z
E-fb8ac45946e32e22minimax/minimax-m3mediumrated5.497711 / 181 / 0192 / 19296001repaired2026-07-02T16:51:45Z
E-1954b83d439b455cmistralai/mistral-medium-3-5highestrated23.9121645 / 147 / 0192 / 19296001repaired2026-07-02T16:51:45Z
E-4a7d37b86196302fmistralai/mistral-medium-3-5nonerated22.0119157 / 136 / 0193 / 19397001first pass2026-07-02T16:51:45Z
E-952fba19b28982d5moonshotai/kimi-k2.7-codemediumrated59.61676129 / 63 / 0192 / 19296001repaired2026-07-02T16:51:45Z
E-5f76f577111bee8dnex-agi/nex-n2-promediumrated19.4115735 / 157 / 0192 / 19296001repaired2026-07-02T16:51:45Z
E-962a9da8812a74d4nex-agi/nex-n2-prononerated44.4148084 / 112 / 0196 / 200100001repaired2026-07-11T17:22:09Z
E-4477e0de2e04aad4nvidia/nemotron-3-ultra-550b-a55bnonerated64.11734137 / 55 / 0192 / 19296001first pass2026-07-02T16:51:45Z
E-48ed5c5e00ef38fbnvidia/nemotron-3-ultra-550b-a55bhighestrated31.7131652 / 140 / 0192 / 19296001first pass2026-07-02T16:51:45Z
E-da3b98638ff53ea9nvidia/nemotron-3-ultra-550b-a55bhighestrated47.3151799 / 97 / 0196 / 200100001repaired2026-07-11T17:22:09Z
E-343b92f3dda3dcb5o3mediumrated53.31595116 / 76 / 0192 / 19296001first pass2026-07-02T16:51:45Z
E-4fc62dc65156d576o3highestrated60.21684128 / 64 / 0192 / 19296001first pass2026-07-03T16:00:00Z
E-5ef540286ecbb63dopenai/gpt-oss-120bmediumrated34.6135476 / 116 / 0192 / 19296001repaired2026-07-02T16:51:45Z
E-435ec29661cdc285qwen/qwen3.7-maxmediumrated45.31491102 / 90 / 0192 / 19296001repaired2026-07-02T16:51:45Z
E-c577c41440c17864qwen/qwen3.7-maxnonerated44.91487103 / 89 / 0192 / 19296001first pass2026-07-02T16:51:45Z
E-6cc7454f585005c4qwen/qwen3.7-plusmediumrated51.91576122 / 70 / 0192 / 19296001repaired2026-07-02T16:51:45Z
E-94daaf1196d89c6cqwen/qwen3.7-plusnonerated39.8142080 / 112 / 0192 / 19296001first pass2026-07-02T16:51:45Z
E-358338a9fbdbcb6astepfun/step-3.7-flashhighestrated50.0155390 / 102 / 0192 / 19296001repaired2026-07-02T16:51:45Z
E-7b9b33921ba865f5stepfun/step-3.7-flashmediumrated43.2146492 / 100 / 0192 / 19296001repaired2026-07-02T16:51:45Z
E-1bb81f8a4ae78954tencent/hy3-previewnonerated15.8111141 / 151 / 0192 / 19296001first pass2026-07-02T16:51:45Z
E-92dc0ac61d798488tencent/hy3-previewhighestrated63.91731135 / 57 / 0192 / 19296001repaired2026-07-03T19:10:00Z
E-4aac1b6621aeae38x-ai/grok-build-0.1mediumrated61.11695124 / 68 / 0192 / 19296001repaired2026-07-02T16:51:45Z
E-09d406abc15f7c9axiaomi/mimo-v2.5nonerated58.11656125 / 67 / 0192 / 19296001first pass2026-07-02T16:51:45Z
E-9490f08c56c27d13xiaomi/mimo-v2.5nonerated20.3116940 / 153 / 0193 / 19397001repaired2026-07-01T00:15:48Z
E-ad48cf51fe7da3ccxiaomi/mimo-v2.5mediumrated44.9148683 / 109 / 0192 / 19296001repaired2026-07-02T16:51:45Z
E-be8fc9653466bbe1xiaomi/mimo-v2.5nonerated27.4126053 / 139 / 0192 / 19296001first pass2026-07-02T06:10:40Z
E-faaa866ee28d6401xiaomi/mimo-v2.5mediumrated24.6122451 / 141 / 0192 / 19296001repaired2026-07-02T06:10:40Z
E-9c228ad72a159b33xiaomi/mimo-v2.5-promediumrated33.8134468 / 124 / 0192 / 19296001repaired2026-07-02T16:51:45Z
E-af55f57b03605914xiaomi/mimo-v2.5-prononerated28.5127559 / 133 / 0192 / 19296001first pass2026-07-02T16:51:45Z
E-1a8c2012f200fd88z-ai/glm-5.2mediumunder covered44.8156810 / 2 / 012 / 1712051repaired2026-07-01T00:15:48Z
E-235e4beedf22bc99z-ai/glm-5.2highestrated57.71651140 / 56 / 0196 / 200100001repaired2026-07-11T14:00:45Z
E-38e323f4ce233fa1z-ai/glm-5.2nonerated34.9135774 / 122 / 0196 / 200100001first pass2026-07-11T14:00:45Z
E-3916ba303b2ff700z-ai/glm-5.2mediumrated57.11643130 / 66 / 0196 / 200100001repaired2026-07-11T17:22:09Z
E-503ecd021099d8f9z-ai/glm-5.2highestrated41.3144083 / 110 / 0193 / 19397001repaired2026-07-02T06:10:40Z
E-51c8f79c1671819ez-ai/glm-5.2highestrated57.01643125 / 67 / 0192 / 19296001repaired2026-07-02T16:51:45Z
E-6370c4b68d38a97ez-ai/glm-5.2nonerated35.2136169 / 125 / 0194 / 19498001repaired2026-07-01T00:15:48Z
E-a6655b3c71893984z-ai/glm-5.2nonerated24.1121842 / 151 / 0193 / 19397001first pass2026-07-02T06:10:40Z
E-d8655d29a4806df8z-ai/glm-5.2nonerated54.11605124 / 68 / 0192 / 19296001repaired2026-07-02T16:51:45Z