Benchmark menu

Per-game leaderboard

GB2-05: Hex

This page shows the per-game leaderboard for GB2-05: Hex in the baseline filter. Entrants are ranked by their relative per-game 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 generated programs on DuelLab's encoded rules for Hex; they are not a broad measure of human play strength.

Entrants

Every admitted unique code identity for GB2-05: Hex. Elo and W/L/D use the public historical sequential-Elo result universe. Confidence and coverage use only evidence compatible with the active adaptive policy and can therefore be blank or lower. Capped draws are rated; unilateral model faults are listed separately.

Showing 47 entrants.
EntrantModelStatusScoreEloConfidenceW / L / DRated / attemptedOpponentsCapped drawsFaults / pluginsGeneration
E-934b5bc34a7e20b9Claude Opus 4.5Under-covered61.715255 / 3 / 08 / 8400 / 1First pass · 2026-07-02
E-233f9cae6335e53dClaude Opus 4.8Under-covered68.815276 / 4 / 010 / 10500 / 1First pass · 2026-07-02
E-09963ffe0b0fa5fdClaude Opus 5Under-covered43.715323 / 1 / 04 / 4200 / 1First pass · 2026-07-25
E-b53cb955b1d8baabClaude Opus 5Under-covered69.915605 / 1 / 06 / 6300 / 1First pass · 2026-07-25
E-0dca18c79b6ac9d7DeepSeek V4 FlashUnder-covered71.215326 / 4 / 010 / 10500 / 1First pass · 2026-07-02
E-b8554f0ccf0845daDeepSeek V4 FlashUnder-covered53.515074 / 4 / 08 / 8400 / 1First pass · 2026-07-02
E-efa8d9109b008ee9DeepSeek V4 FlashUnder-covered33.614523 / 7 / 010 / 10500 / 1Repaired · 2026-07-01
E-da5f3b1a4e370e1aDeepSeek V4 ProUnder-covered81.515448 / 4 / 012 / 12600 / 1Repaired · 2026-07-02
E-214f636367cbdac4Gemini 3.5 Flash LitePending0 / 0 / 00 / 0000 / 1Repaired · 2026-07-24
E-a870d09d3e1a40d4Gemini 3.5 Flash LitePending0 / 0 / 00 / 0000 / 1First pass · 2026-07-24
E-9bef179ce22a6c93Gemini 3.6 FlashPending0 / 0 / 00 / 0000 / 1First pass · 2026-07-24
E-e23af86eb5787555Gemini 3.6 FlashPending0 / 0 / 00 / 0000 / 1First pass · 2026-07-24
E-e8e17fbbdd12faa4Gemma 4 31BUnder-covered32.414623 / 5 / 08 / 8400 / 1First pass · 2026-07-02
E-6d3546010ef68f50GPT-5.4Under-covered81.215846 / 0 / 06 / 6300 / 1Repaired · 2026-07-02
E-427bdffeacc6c394GPT-5.4 MiniUnder-covered25.214174 / 10 / 014 / 14700 / 1Repaired · 2026-07-02
E-8ed627956c0a0292GPT-5.4 MiniUnder-covered11.514181 / 7 / 08 / 8400 / 1First pass · 2026-07-01
E-cdd304da89074d54GPT-5.4 MiniUnder-covered36.914723 / 5 / 08 / 8400 / 1First pass · 2026-07-02
E-3311575b341ee4a8GPT-5.4 NanoUnder-covered36.314584 / 6 / 010 / 10500 / 1Repaired · 2026-07-09
E-49b3c6006a3b9fccGPT-5.4 NanoUnder-covered38.214743 / 5 / 08 / 8400 / 1First pass · 2026-07-01
E-6c37eeef15b82287GPT-5.4 NanoUnder-covered48.314745 / 7 / 012 / 12600 / 1Repaired · 2026-07-02
E-6f42dbbf02274b56GPT-5.5Under-covered54.815104 / 4 / 08 / 8400 / 1First pass · 2026-07-02
E-59156a669808a24fGPT-5.6 LunaUnder-covered0.014110 / 6 / 06 / 6300 / 1Repaired · 2026-07-10
E-471e9297eea18ffdGPT-5.6 SolUnder-covered66.115525 / 1 / 06 / 6300 / 1First pass · 2026-07-10
E-1f00b423eab1c19dGPT-5.6 TerraUnder-covered27.714702 / 4 / 06 / 6300 / 1First pass · 2026-07-10
E-067ab716d64e3e9aLongCat 2.0Under-covered54.915564 / 0 / 04 / 4200 / 1Repaired · 2026-07-24
E-8cc657b7db4428cbLongCat 2.0Under-covered23.214432 / 6 / 08 / 8400 / 1First pass · 2026-07-24
E-33797d7b77c7800cMinimax M3Under-covered68.615276 / 4 / 010 / 10500 / 1Repaired · 2026-07-02
E-4a7d37b86196302fMistral Medium 3.5Under-covered52.315224 / 2 / 06 / 6300 / 1First pass · 2026-07-02
E-4419230379dcd41eKimi K3Pending0 / 0 / 00 / 0000 / 1First pass · 2026-07-24
E-91be72471ad409b6Kimi K3Under-covered72.015476 / 2 / 08 / 8400 / 1First pass · 2026-07-21
E-962a9da8812a74d4Nex N2 ProUnder-covered63.915295 / 3 / 08 / 8400 / 1Repaired · 2026-07-11
E-b556333d605791f4O3Under-covered48.414964 / 4 / 08 / 8400 / 1First pass · 2026-07-21
E-172336d3fd38632aGPT-OSS 120BUnder-covered1.013950 / 8 / 08 / 8400 / 1Repaired · 2026-07-21
E-1ca53619662c7f6fLaguna S 2.1Under-covered90.415638 / 4 / 012 / 12600 / 1First pass · 2026-07-24
E-21623e96b2b104e9Laguna S 2.1Under-covered31.514483 / 7 / 010 / 10500 / 1Repaired · 2026-07-24
E-c577c41440c17864Qwen3.7 MaxUnder-covered52.315234 / 2 / 06 / 6300 / 1First pass · 2026-07-02
E-94daaf1196d89c6cQwen3.7 PlusUnder-covered39.414773 / 5 / 08 / 8400 / 1First pass · 2026-07-02
E-386b7a319dfe25adStep 3.7 FlashUnder-covered29.314562 / 6 / 08 / 8400 / 1Repaired · 2026-07-21
E-1bb81f8a4ae78954Hy3 PreviewUnder-covered58.315174 / 4 / 08 / 8400 / 1First pass · 2026-07-02
E-0f05573125dedc2bInklingUnder-covered25.714662 / 4 / 06 / 6300 / 1Repaired · 2026-07-24
E-f7a1d86c7e241f8dInklingUnder-covered13.214671 / 3 / 04 / 4200 / 1First pass · 2026-07-24
E-f1d32edccc2b8ba2Grok 4.5Pending0 / 0 / 00 / 0000 / 1Repaired · 2026-07-24
E-fcfafa8fb4ccd299Grok 4.5Under-covered100.016068 / 0 / 08 / 8400 / 1Repaired · 2026-07-21
E-09d406abc15f7c9aMiMo-V2.5Under-covered84.615916 / 0 / 06 / 6300 / 1First pass · 2026-07-02
E-9490f08c56c27d13MiMo-V2.5Under-covered47.614725 / 7 / 012 / 12600 / 1Repaired · 2026-07-01
E-be8fc9653466bbe1MiMo-V2.5Under-covered35.114683 / 5 / 08 / 8400 / 1First pass · 2026-07-02
E-af55f57b03605914MiMo-V2.5-ProUnder-covered74.215516 / 2 / 08 / 8400 / 1First pass · 2026-07-02

GB2-05: Hex leaderboard

Entrants are ranked by relative per-game score (0–100). Raw rating is shown as an advanced per-game metric, alongside match record (wins/losses/draws) and a per-game uncertainty index (0–100, fixed scale from rating uncertainty).

Reasoning level: Baseline Game: GB2-05: Hex

Scroll sideways to see every column.

GB2-05: Hex - Baseline filter
Rank Model Score Contributing programs Raw Elo W / L / D Uncertainty
1Grok 4.5100.011606.48/0/0100.0
2Laguna S 2.190.411563.48/4/094.9
3MiMo-V2.584.611591.46/0/0100.0
4DeepSeek V4 Pro81.511544.58/4/094.9
5GPT-5.481.211584.16/0/0100.0
6MiMo-V2.5-Pro74.211551.36/2/0100.0
7Kimi K372.011546.76/2/0100.0
8DeepSeek V4 Flash71.211532.36/4/0100.0
9Claude Opus 569.911560.05/1/0100.0
10Claude Opus 4.868.811527.16/4/0100.0
11Minimax M368.611526.76/4/0100.0
12GPT-5.6 Sol66.111551.95/1/0100.0
13Nex N2 Pro63.911529.45/3/0100.0
14Claude Opus 4.561.711524.85/3/0100.0
15Hy3 Preview58.311517.34/4/0100.0
16LongCat 2.054.911555.84/0/0100.0
17GPT-5.554.811509.94/4/0100.0
18DeepSeek V4 Flash53.511507.14/4/0100.0
19Qwen3.7 Max52.311522.54/2/0100.0
20Mistral Medium 3.552.311522.54/2/0100.0
21O348.411496.24/4/0100.0
22GPT-5.4 Nano48.311473.65/7/094.9
23MiMo-V2.547.611472.15/7/094.9
24Claude Opus 543.711531.93/1/0100.0
25Qwen3.7 Plus39.411477.13/5/0100.0
26GPT-5.4 Nano38.211474.43/5/0100.0
27GPT-5.4 Mini36.911471.83/5/0100.0
28GPT-5.4 Nano36.311457.64/6/0100.0
29MiMo-V2.535.111467.83/5/0100.0
30DeepSeek V4 Flash33.611452.03/7/0100.0
31Gemma 4 31B32.411462.13/5/0100.0
32Laguna S 2.131.511447.53/7/0100.0
33Step 3.7 Flash29.311455.62/6/0100.0
34GPT-5.6 Terra27.711470.02/4/0100.0
35Inkling25.711465.72/4/0100.0
36GPT-5.4 Mini25.211416.74/10/085.3
37LongCat 2.023.211442.62/6/0100.0
38Inkling13.211466.61/3/0100.0
39GPT-5.4 Mini11.511417.51/7/0100.0
40GPT-OSS 120B1.011395.10/8/0100.0
41GPT-5.6 Luna0.011410.90/6/0100.0