Benchmark menu

Per-game leaderboard

GB2-05: Hex

This page compares player programs for GB2-05: Hex in the baseline filter. Programs are ranked by their relative score within this game.

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 player programs using DuelLab's encoded rules for Hex; they are not a broad measure of human play strength.

GB2-05: Hex by model and setting

Player programs are ranked by relative per-game score (0–100). Raw rating is shown as an advanced metric, alongside wins, draws, losses, and a per-game uncertainty index.

Reasoning level: Baseline Game: GB2-05: Hex
GB2-05: Hex - Baseline filter
Rank Model Score Contributing programs Raw Elo W / D / L Uncertainty
1Claude Opus 591.021963.1181 / 0 / 176.3
2Qwen3.8 Max65.311727.917 / 0 / 074.1
3Kimi K363.511642.7117 / 0 / 620.0
4Claude Opus 4.561.411630.661 / 0 / 318.1
5Nemotron 3 Ultra 550B A55B59.711615.347 / 0 / 2913.2
6Laguna S 2.157.921591.7113 / 0 / 639.3
7Muse Spark 1.256.611576.350 / 0 / 428.1
8GPT-5.456.611576.658 / 0 / 328.7
9GPT-5.6 Terra55.211564.746 / 0 / 3013.2
10GPT-5.554.011550.046 / 0 / 3212.5
11Gemini 3.6 Flash52.221516.0191 / 0 / 1440.0
12Qwen3.7 Max52.211525.547 / 0 / 497.0
13GPT-5.6 Sol51.511519.554 / 0 / 368.7
14GLM-5.251.121519.872 / 0 / 7414.6
15MiMo-V2.550.831514.9116 / 0 / 11413.0
16Grok 4.549.511486.776 / 0 / 810.0
17Qwen3.7 Plus48.511484.045 / 0 / 497.5
18Nex N2 Pro47.711474.748 / 0 / 487.0
19Minimax M347.411470.152 / 0 / 525.0
20Ox Alpha45.131501.825 / 0 / 2377.5
21DeepSeek V4 Flash44.211433.946 / 0 / 565.5
22MiMo-V2.5-Pro43.811432.348 / 0 / 409.2
23DeepSeek V4 Pro41.911411.144 / 0 / 468.7
24Claude Opus 4.839.911388.640 / 0 / 508.7
25Claude Sonnet 538.111367.329 / 0 / 638.1
26Mistral Medium 3.538.011366.143 / 0 / 478.7
27Hy3 Preview35.211334.139 / 0 / 557.5
28Inkling34.121320.271 / 0 / 1355.3
29Step 3.7 Flash33.911311.349 / 0 / 990.0
30GPT-5.4 Mini31.111289.427 / 0 / 599.9
31GPT-5.6 Luna30.811285.133 / 0 / 598.1
32Inkling Small25.711277.81 / 0 / 1771.0
33GPT-5.4 Nano21.121177.538 / 0 / 12810.8
34Gemini 3.1 Flash Lite18.811154.117 / 0 / 5714.0
35Gemma 4 31B18.611147.625 / 0 / 639.2
36GPT 4.118.511146.426 / 0 / 648.7
37LongCat 2.017.321134.446 / 0 / 12410.2
38GPT-OSS 120B15.511100.533 / 0 / 1480.0
39Gemini 3.5 Flash Lite10.621046.247 / 0 / 2770.0

Individual player programs

Each row is one accepted player program for GB2-05: Hex. A model can appear more than once when it produced more than one program. Score is the normalized 0–100 result; Elo and W / D / L show the underlying play record. Confidence and evidence can be blank when too few compatible matches are available. Draws at the move limit count; one-sided model faults are listed separately.

Showing 53 player programs.
Player IDModelStatusScoreEloConfidenceW / D / LRated / attemptedOpponentsCapped drawsFaults / playersGeneration
E-934b5bc34a7e20b9Claude Opus 4.5Rated61.4163161 / 0 / 3192 / 924600 / 1First try · 2026-07-02
E-233f9cae6335e53dClaude Opus 4.8Rated39.9138940 / 0 / 5090 / 904500 / 1First try · 2026-07-02
E-09963ffe0b0fa5fdClaude Opus 5Rated92.5198092 / 0 / 8100 / 1005000 / 1First try · 2026-07-25
E-b53cb955b1d8baabClaude Opus 5Rated89.5194689 / 0 / 998 / 984900 / 1First try · 2026-07-25
E-66c9ddb5d274adfeClaude Sonnet 5Rated38.1136729 / 0 / 6392 / 924500 / 1First try · 2026-08-09
E-0dca18c79b6ac9d7DeepSeek V4 FlashRated44.2143446 / 0 / 56102 / 1025100 / 1First try · 2026-07-02
E-da5f3b1a4e370e1aDeepSeek V4 ProRated41.9141144 / 0 / 4690 / 904500 / 1Repaired · 2026-07-02
E-d979b43c3aeea657Gemini 3.1 Flash LiteRated18.8115417 / 0 / 5774 / 743700 / 1First try · 2026-07-02
E-a13c4c9fdf6b244dGemini 3.5 FlashWaiting0 / 0 / 00 / 0000 / 1First try · 2026-07-21
E-214f636367cbdac4Gemini 3.5 Flash LiteRated14.2108723 / 0 / 141164 / 1646000 / 1Repaired · 2026-07-24
E-a870d09d3e1a40d4Gemini 3.5 Flash LiteRated6.9100524 / 0 / 136160 / 1605800 / 1First try · 2026-07-24
E-9bef179ce22a6c93Gemini 3.6 FlashRated58.4158784 / 0 / 73157 / 1576400 / 1First try · 2026-07-24
E-e23af86eb5787555Gemini 3.6 FlashRated46.01445107 / 0 / 71178 / 1786600 / 1First try · 2026-07-24
E-e8e17fbbdd12faa4Gemma 4 31BRated18.6114825 / 0 / 6388 / 884400 / 1First try · 2026-07-02
E-1b9f1f7b70f02927GPT 4.1Rated18.5114626 / 0 / 6490 / 904500 / 1First try · 2026-07-02
E-d03d2c6a69fc3e16GPT 5Waiting0 / 0 / 00 / 0000 / 1Repaired · 2026-07-21
E-a09c0b14cae46193GPT-5.4Rated56.6157758 / 0 / 3290 / 904300 / 1First try · 2026-08-09
E-427bdffeacc6c394GPT-5.4 MiniRated31.1128927 / 0 / 5986 / 864300 / 1Repaired · 2026-07-02
E-3311575b341ee4a8GPT-5.4 NanoRated22.9119819 / 0 / 6382 / 824100 / 1Repaired · 2026-07-09
E-6c37eeef15b82287GPT-5.4 NanoRated19.3115719 / 0 / 6584 / 844200 / 1Repaired · 2026-07-02
E-6f42dbbf02274b56GPT-5.5Rated54.0155046 / 0 / 3278 / 783900 / 1First try · 2026-07-02
E-6879be00992f95f0GPT-5.6 LunaRated30.8128533 / 0 / 5992 / 924300 / 1First try · 2026-08-09
E-d29c6c5eb08da2d9GPT-5.6 SolRated51.5151954 / 0 / 3690 / 904300 / 1First try · 2026-08-09
E-1f00b423eab1c19dGPT-5.6 TerraRated55.2156546 / 0 / 3076 / 763800 / 1First try · 2026-07-10
E-067ab716d64e3e9aLongCat 2.0Rated15.1110919 / 0 / 6988 / 904402 / 1Repaired · 2026-07-24
E-8cc657b7db4428cbLongCat 2.0Rated19.5116027 / 0 / 5582 / 844102 / 1First try · 2026-07-24
E-1fbf9ab6a0c6d3eeMuse Spark 1.2Rated56.6157650 / 0 / 4292 / 924300 / 1First try · 2026-08-13
E-33797d7b77c7800cMinimax M3Rated47.4147052 / 0 / 52104 / 1045200 / 1Repaired · 2026-07-02
E-4a7d37b86196302fMistral Medium 3.5Rated38.0136643 / 0 / 4790 / 904500 / 1First try · 2026-07-02
E-4419230379dcd41eKimi K3Rated63.51643117 / 0 / 62179 / 1797400 / 1First try · 2026-07-24
E-962a9da8812a74d4Nex N2 ProRated47.7147548 / 0 / 4896 / 964800 / 1Repaired · 2026-07-11
E-4477e0de2e04aad4Nemotron 3 Ultra 550B A55BRated59.7161547 / 0 / 2976 / 763800 / 1First try · 2026-07-02
E-172336d3fd38632aGPT-OSS 120BRated15.5110133 / 0 / 148181 / 1816700 / 1Repaired · 2026-07-21
E-1ca53619662c7f6fLaguna S 2.1Rated77.4181367 / 0 / 1986 / 864300 / 1First try · 2026-07-24
E-21623e96b2b104e9Laguna S 2.1Rated38.3137046 / 0 / 4490 / 904500 / 1Repaired · 2026-07-24
E-c577c41440c17864Qwen3.7 MaxRated52.2152647 / 0 / 4996 / 964800 / 1First try · 2026-07-02
E-94daaf1196d89c6cQwen3.7 PlusRated48.5148445 / 0 / 4994 / 944700 / 1First try · 2026-07-02
E-776235fa35035a89Qwen3.8 MaxLimited data65.3172817 / 0 / 017 / 17900 / 1First try · 2026-08-08
E-070bbd8b3ce0460aOx AlphaRated41.414617 / 0 / 916 / 16800 / 1Repaired · 2026-08-22
E-575e460fdd8ace42Ox AlphaRated46.115139 / 0 / 716 / 16800 / 1First try · 2026-08-22
E-c69bc9b31ddf984bOx AlphaRated47.715329 / 0 / 716 / 16800 / 1First try · 2026-08-22
E-50f22f1c15a8fd4aStep 3.7 FlashRated33.9131149 / 0 / 99148 / 1525500 / 1First try · 2026-07-21
E-1bb81f8a4ae78954Hy3 PreviewRated35.2133439 / 0 / 5594 / 944700 / 1First try · 2026-07-02
E-0f05573125dedc2bInklingRated33.6131434 / 0 / 66100 / 1005000 / 1Repaired · 2026-07-24
E-f7a1d86c7e241f8dInklingRated34.7132637 / 0 / 69106 / 1065300 / 1First try · 2026-07-24
E-7c80d62319ac1a53Inkling SmallLimited data25.712781 / 0 / 1718 / 18700 / 1First try · 2026-08-09
E-3c5879def34f7d38Grok 4.5Rated49.5148776 / 0 / 81157 / 1576300 / 1First try · 2026-07-24
E-09d406abc15f7c9aMiMo-V2.5Rated64.9167449 / 0 / 2776 / 763800 / 1First try · 2026-07-02
E-9490f08c56c27d13MiMo-V2.5Rated33.4131830 / 0 / 4878 / 783900 / 1Repaired · 2026-07-01
E-be8fc9653466bbe1MiMo-V2.5Rated40.0139337 / 0 / 3976 / 763800 / 1First try · 2026-07-02
E-af55f57b03605914MiMo-V2.5-ProRated43.8143248 / 0 / 4088 / 884400 / 1First try · 2026-07-02
E-38e323f4ce233fa1GLM-5.2Rated42.2141740 / 0 / 4080 / 804000 / 1First try · 2026-07-11
E-d8655d29a4806df8GLM-5.2Rated60.1162332 / 0 / 3466 / 663300 / 1Repaired · 2026-07-02