Benchmark menu

Per-game leaderboard

GB2-05: Hex

This page compares player programs for GB2-05: Hex in the intensive 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: Intensive Game: GB2-05: Hex
GB2-05: Hex - Intensive filter
Rank Model Score Contributing programs Raw Elo W / D / L Uncertainty
1GPT-5.494.312001.693 / 0 / 17.5
2Claude Fable 592.511984.668 / 0 / 1211.8
3Gemini 3.6 Flash88.421928.0235 / 0 / 390.0
4Claude Opus 587.521935.0100 / 0 / 2020.3
5GPT-5.586.911921.267 / 0 / 1311.8
6DeepSeek V4 Pro77.211811.753 / 0 / 2911.1
7Grok 4.576.211790.497 / 0 / 370.0
8GPT-5.6 Sol63.911660.065 / 0 / 239.2
9GPT 563.911661.742 / 0 / 3811.8
10GPT-5.6 Terra62.111642.941 / 0 / 3513.2
11Hy3 Preview59.311610.239 / 0 / 4111.8
12GPT-5.6 Luna58.411596.059 / 0 / 357.5
13DeepSeek V4 Flash55.011559.747 / 0 / 399.9
14O353.941537.2335 / 0 / 2750.0
15Gemini 3.5 Flash53.911546.342 / 0 / 488.7
16Claude Opus 4.853.611539.353 / 0 / 554.1
17Claude Sonnet 552.811532.755 / 0 / 397.5
18Claude Opus 4.552.311514.9110 / 0 / 820.0
19Ox Alpha51.231571.433 / 0 / 1577.5
20Qwen3.8 Max49.011532.713 / 0 / 960.5
21Nemotron 3 Ultra 550B A55B46.221458.087 / 0 / 1017.7
22Inkling Small45.711505.59 / 0 / 874.1
23Step 3.7 Flash42.811420.051 / 0 / 457.0
24Gemini 3.5 Flash Lite26.121223.578 / 0 / 2180.0
25Mistral Medium 3.524.411215.721 / 0 / 5712.5
26Gemini 3.1 Flash Lite20.711174.416 / 0 / 6212.5
27Inkling20.221156.170 / 0 / 2420.0

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 38 player programs.
Player IDModelStatusScoreEloConfidenceW / D / LRated / attemptedOpponentsCapped drawsFaults / playersGeneration
E-5aa4402ccce7b855Claude Fable 5Rated92.5198568 / 0 / 1280 / 803500 / 1Repaired · 2026-07-02
E-7e9bc3ebc12ef500Claude Opus 4.5Waiting0 / 0 / 00 / 0000 / 1First try · 2026-07-02
E-ccacc93776fb7c88Claude Opus 4.5Rated52.31515110 / 0 / 82192 / 1926300 / 1First try · 2026-07-21
E-6774d700e60de31aClaude Opus 4.8Rated53.6153953 / 0 / 55108 / 1085400 / 1Repaired · 2026-07-02
E-3f3686d02d1503faClaude Opus 5Rated100.0207758 / 0 / 058 / 582400 / 1First try · 2026-07-25
E-a35dfc1adc62e4ebClaude Opus 5Rated75.0179342 / 0 / 2062 / 622800 / 1First try · 2026-07-25
E-750cee28d20157cbClaude Sonnet 5Rated52.8153355 / 0 / 3994 / 944500 / 1First try · 2026-08-09
E-b3d889b0631db85fDeepSeek V4 FlashRated55.0156047 / 0 / 3986 / 864200 / 1Repaired · 2026-07-02
E-0ca4798825ceaccbDeepSeek V4 ProRated77.2181253 / 0 / 2982 / 823800 / 1Repaired · 2026-07-02
E-a72dd193e1dc4331Gemini 3.1 Flash LiteRated20.7117416 / 0 / 6278 / 783800 / 1Repaired · 2026-07-02
E-b50da126631c1ea1Gemini 3.5 FlashRated53.9154642 / 0 / 4890 / 904400 / 1Repaired · 2026-07-02
E-06abb3c93d2072c8Gemini 3.5 Flash LiteRated30.2127040 / 0 / 108148 / 1485100 / 1First try · 2026-07-24
E-5b803013ec40d15dGemini 3.5 Flash LiteRated22.0117738 / 0 / 110148 / 1485200 / 1First try · 2026-07-24
E-8b9ff59d79afb558Gemini 3.6 FlashRated97.72033132 / 0 / 6138 / 1385200 / 1First try · 2026-07-24
E-c4f143aad203feb3Gemini 3.6 FlashRated79.11823103 / 0 / 33136 / 1365200 / 1First try · 2026-07-24
E-c5ad048b6fb4e93dGPT 5Rated63.9166242 / 0 / 3880 / 803700 / 1First try · 2026-07-02
E-dcce778d7a3114faGPT-5.4Rated94.3200293 / 0 / 194 / 944400 / 1First try · 2026-08-09
E-762e9d80a60b41edGPT-5.5Rated86.9192167 / 0 / 1380 / 803700 / 1First try · 2026-07-02
E-3b8df7a8d128f873GPT-5.6 LunaRated58.4159659 / 0 / 3594 / 944400 / 1First try · 2026-08-09
E-225037bcf869a775GPT-5.6 SolRated63.9166065 / 0 / 2388 / 884300 / 1First try · 2026-08-09
E-012ecb9ce0709c05GPT-5.6 TerraRated62.1164341 / 0 / 3576 / 763600 / 1Repaired · 2026-07-10
E-1954b83d439b455cMistral Medium 3.5Rated24.4121621 / 0 / 5778 / 783900 / 1Repaired · 2026-07-02
E-48ed5c5e00ef38fbNemotron 3 Ultra 550B A55BRated44.8144144 / 0 / 58102 / 1024800 / 1First try · 2026-07-02
E-da3b98638ff53ea9Nemotron 3 Ultra 550B A55BRated47.5147543 / 0 / 4386 / 864300 / 1Repaired · 2026-07-11
E-4724b57e861c4ecfO3Rated65.4166695 / 0 / 56151 / 1515900 / 1First try · 2026-07-02
E-61d05a26a332d2e5O3Rated49.5148578 / 0 / 86164 / 1645800 / 1First try · 2026-07-03
E-9bfe5e29476019ebO3Rated43.3141769 / 0 / 78147 / 1475300 / 1First try · 2026-07-03
E-ffb183b7ecfe85e0O3Rated57.7158093 / 0 / 55148 / 1485000 / 1First try · 2026-07-03
E-7cc7204834cbed5fQwen3.8 MaxLimited data49.0153313 / 0 / 922 / 221100 / 1First try · 2026-08-08
E-45b32dc2eea8fd55Ox AlphaRated49.4155110 / 0 / 616 / 16800 / 1First try · 2026-08-22
E-b2ff4a9d0e899fbaOx AlphaRated47.515299 / 0 / 716 / 16800 / 1First try · 2026-08-22
E-b6ae2b718b132aa0Ox AlphaRated56.9163514 / 0 / 216 / 16800 / 1Repaired · 2026-08-22
E-358338a9fbdbcb6aStep 3.7 FlashRated42.8142051 / 0 / 4596 / 964600 / 1Repaired · 2026-07-02
E-92dc0ac61d798488Hy3 PreviewRated59.3161039 / 0 / 4180 / 803800 / 1Repaired · 2026-07-03
E-2c483dc32fc18ba8InklingRated16.2111128 / 0 / 122150 / 1505100 / 1First try · 2026-07-24
E-e9202aa1565d1c4eInklingRated24.3120142 / 0 / 120162 / 1625700 / 1Repaired · 2026-07-24
E-e8805bb60afd625cInkling SmallLimited data45.715059 / 0 / 817 / 17900 / 1First try · 2026-08-09
E-8e6cb252293b2af9Grok 4.5Rated76.2179097 / 0 / 37134 / 1345200 / 1First try · 2026-07-24