Reasoning view
GB2-05: Hex
Game profile
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.
By model and setting
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.
| Rank | Model | Score | Contributing programs | Raw Elo | W / D / L | Uncertainty |
|---|---|---|---|---|---|---|
| 1 | 94.3 | 1 | 2001.6 | 93 / 0 / 1 | 7.5 | |
| 2 | 92.5 | 1 | 1984.6 | 68 / 0 / 12 | 11.8 | |
| 3 | 88.4 | 2 | 1928.0 | 235 / 0 / 39 | 0.0 | |
| 4 | 87.5 | 2 | 1935.0 | 100 / 0 / 20 | 20.3 | |
| 5 | 86.9 | 1 | 1921.2 | 67 / 0 / 13 | 11.8 | |
| 6 | 77.2 | 1 | 1811.7 | 53 / 0 / 29 | 11.1 | |
| 7 | 76.2 | 1 | 1790.4 | 97 / 0 / 37 | 0.0 | |
| 8 | 63.9 | 1 | 1660.0 | 65 / 0 / 23 | 9.2 | |
| 9 | 63.9 | 1 | 1661.7 | 42 / 0 / 38 | 11.8 | |
| 10 | 62.1 | 1 | 1642.9 | 41 / 0 / 35 | 13.2 | |
| 11 | 59.3 | 1 | 1610.2 | 39 / 0 / 41 | 11.8 | |
| 12 | 58.4 | 1 | 1596.0 | 59 / 0 / 35 | 7.5 | |
| 13 | 55.0 | 1 | 1559.7 | 47 / 0 / 39 | 9.9 | |
| 14 | 53.9 | 4 | 1537.2 | 335 / 0 / 275 | 0.0 | |
| 15 | 53.9 | 1 | 1546.3 | 42 / 0 / 48 | 8.7 | |
| 16 | 53.6 | 1 | 1539.3 | 53 / 0 / 55 | 4.1 | |
| 17 | 52.8 | 1 | 1532.7 | 55 / 0 / 39 | 7.5 | |
| 18 | 52.3 | 1 | 1514.9 | 110 / 0 / 82 | 0.0 | |
| 19 | 51.2 | 3 | 1571.4 | 33 / 0 / 15 | 77.5 | |
| 20 | 49.0 | 1 | 1532.7 | 13 / 0 / 9 | 60.5 | |
| 21 | 46.2 | 2 | 1458.0 | 87 / 0 / 101 | 7.7 | |
| 22 | 45.7 | 1 | 1505.5 | 9 / 0 / 8 | 74.1 | |
| 23 | 42.8 | 1 | 1420.0 | 51 / 0 / 45 | 7.0 | |
| 24 | 26.1 | 2 | 1223.5 | 78 / 0 / 218 | 0.0 | |
| 25 | 24.4 | 1 | 1215.7 | 21 / 0 / 57 | 12.5 | |
| 26 | 20.7 | 1 | 1174.4 | 16 / 0 / 62 | 12.5 | |
| 27 | 20.2 | 2 | 1156.1 | 70 / 0 / 242 | 0.0 |
Underlying results
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.
| Player ID | Model | Status | Score | Elo | Confidence | W / D / L | Rated / attempted | Opponents | Capped draws | Faults / players | Generation |
|---|---|---|---|---|---|---|---|---|---|---|---|
| E-5aa4402ccce7b855 | Claude Fable 5 | Rated | 92.5 | 1985 | — | 68 / 0 / 12 | 80 / 80 | 35 | 0 | 0 / 1 | Repaired · 2026-07-02 |
| E-7e9bc3ebc12ef500 | Claude Opus 4.5 | Waiting | — | — | — | 0 / 0 / 0 | 0 / 0 | 0 | 0 | 0 / 1 | First try · 2026-07-02 |
| E-ccacc93776fb7c88 | Claude Opus 4.5 | Rated | 52.3 | 1515 | — | 110 / 0 / 82 | 192 / 192 | 63 | 0 | 0 / 1 | First try · 2026-07-21 |
| E-6774d700e60de31a | Claude Opus 4.8 | Rated | 53.6 | 1539 | — | 53 / 0 / 55 | 108 / 108 | 54 | 0 | 0 / 1 | Repaired · 2026-07-02 |
| E-3f3686d02d1503fa | Claude Opus 5 | Rated | 100.0 | 2077 | — | 58 / 0 / 0 | 58 / 58 | 24 | 0 | 0 / 1 | First try · 2026-07-25 |
| E-a35dfc1adc62e4eb | Claude Opus 5 | Rated | 75.0 | 1793 | — | 42 / 0 / 20 | 62 / 62 | 28 | 0 | 0 / 1 | First try · 2026-07-25 |
| E-750cee28d20157cb | Claude Sonnet 5 | Rated | 52.8 | 1533 | — | 55 / 0 / 39 | 94 / 94 | 45 | 0 | 0 / 1 | First try · 2026-08-09 |
| E-b3d889b0631db85f | DeepSeek V4 Flash | Rated | 55.0 | 1560 | — | 47 / 0 / 39 | 86 / 86 | 42 | 0 | 0 / 1 | Repaired · 2026-07-02 |
| E-0ca4798825ceaccb | DeepSeek V4 Pro | Rated | 77.2 | 1812 | — | 53 / 0 / 29 | 82 / 82 | 38 | 0 | 0 / 1 | Repaired · 2026-07-02 |
| E-a72dd193e1dc4331 | Gemini 3.1 Flash Lite | Rated | 20.7 | 1174 | — | 16 / 0 / 62 | 78 / 78 | 38 | 0 | 0 / 1 | Repaired · 2026-07-02 |
| E-b50da126631c1ea1 | Gemini 3.5 Flash | Rated | 53.9 | 1546 | — | 42 / 0 / 48 | 90 / 90 | 44 | 0 | 0 / 1 | Repaired · 2026-07-02 |
| E-06abb3c93d2072c8 | Gemini 3.5 Flash Lite | Rated | 30.2 | 1270 | — | 40 / 0 / 108 | 148 / 148 | 51 | 0 | 0 / 1 | First try · 2026-07-24 |
| E-5b803013ec40d15d | Gemini 3.5 Flash Lite | Rated | 22.0 | 1177 | — | 38 / 0 / 110 | 148 / 148 | 52 | 0 | 0 / 1 | First try · 2026-07-24 |
| E-8b9ff59d79afb558 | Gemini 3.6 Flash | Rated | 97.7 | 2033 | — | 132 / 0 / 6 | 138 / 138 | 52 | 0 | 0 / 1 | First try · 2026-07-24 |
| E-c4f143aad203feb3 | Gemini 3.6 Flash | Rated | 79.1 | 1823 | — | 103 / 0 / 33 | 136 / 136 | 52 | 0 | 0 / 1 | First try · 2026-07-24 |
| E-c5ad048b6fb4e93d | GPT 5 | Rated | 63.9 | 1662 | — | 42 / 0 / 38 | 80 / 80 | 37 | 0 | 0 / 1 | First try · 2026-07-02 |
| E-dcce778d7a3114fa | GPT-5.4 | Rated | 94.3 | 2002 | — | 93 / 0 / 1 | 94 / 94 | 44 | 0 | 0 / 1 | First try · 2026-08-09 |
| E-762e9d80a60b41ed | GPT-5.5 | Rated | 86.9 | 1921 | — | 67 / 0 / 13 | 80 / 80 | 37 | 0 | 0 / 1 | First try · 2026-07-02 |
| E-3b8df7a8d128f873 | GPT-5.6 Luna | Rated | 58.4 | 1596 | — | 59 / 0 / 35 | 94 / 94 | 44 | 0 | 0 / 1 | First try · 2026-08-09 |
| E-225037bcf869a775 | GPT-5.6 Sol | Rated | 63.9 | 1660 | — | 65 / 0 / 23 | 88 / 88 | 43 | 0 | 0 / 1 | First try · 2026-08-09 |
| E-012ecb9ce0709c05 | GPT-5.6 Terra | Rated | 62.1 | 1643 | — | 41 / 0 / 35 | 76 / 76 | 36 | 0 | 0 / 1 | Repaired · 2026-07-10 |
| E-1954b83d439b455c | Mistral Medium 3.5 | Rated | 24.4 | 1216 | — | 21 / 0 / 57 | 78 / 78 | 39 | 0 | 0 / 1 | Repaired · 2026-07-02 |
| E-48ed5c5e00ef38fb | Nemotron 3 Ultra 550B A55B | Rated | 44.8 | 1441 | — | 44 / 0 / 58 | 102 / 102 | 48 | 0 | 0 / 1 | First try · 2026-07-02 |
| E-da3b98638ff53ea9 | Nemotron 3 Ultra 550B A55B | Rated | 47.5 | 1475 | — | 43 / 0 / 43 | 86 / 86 | 43 | 0 | 0 / 1 | Repaired · 2026-07-11 |
| E-4724b57e861c4ecf | O3 | Rated | 65.4 | 1666 | — | 95 / 0 / 56 | 151 / 151 | 59 | 0 | 0 / 1 | First try · 2026-07-02 |
| E-61d05a26a332d2e5 | O3 | Rated | 49.5 | 1485 | — | 78 / 0 / 86 | 164 / 164 | 58 | 0 | 0 / 1 | First try · 2026-07-03 |
| E-9bfe5e29476019eb | O3 | Rated | 43.3 | 1417 | — | 69 / 0 / 78 | 147 / 147 | 53 | 0 | 0 / 1 | First try · 2026-07-03 |
| E-ffb183b7ecfe85e0 | O3 | Rated | 57.7 | 1580 | — | 93 / 0 / 55 | 148 / 148 | 50 | 0 | 0 / 1 | First try · 2026-07-03 |
| E-7cc7204834cbed5f | Qwen3.8 Max | Limited data | 49.0 | 1533 | — | 13 / 0 / 9 | 22 / 22 | 11 | 0 | 0 / 1 | First try · 2026-08-08 |
| E-45b32dc2eea8fd55 | Ox Alpha | Rated | 49.4 | 1551 | — | 10 / 0 / 6 | 16 / 16 | 8 | 0 | 0 / 1 | First try · 2026-08-22 |
| E-b2ff4a9d0e899fba | Ox Alpha | Rated | 47.5 | 1529 | — | 9 / 0 / 7 | 16 / 16 | 8 | 0 | 0 / 1 | First try · 2026-08-22 |
| E-b6ae2b718b132aa0 | Ox Alpha | Rated | 56.9 | 1635 | — | 14 / 0 / 2 | 16 / 16 | 8 | 0 | 0 / 1 | Repaired · 2026-08-22 |
| E-358338a9fbdbcb6a | Step 3.7 Flash | Rated | 42.8 | 1420 | — | 51 / 0 / 45 | 96 / 96 | 46 | 0 | 0 / 1 | Repaired · 2026-07-02 |
| E-92dc0ac61d798488 | Hy3 Preview | Rated | 59.3 | 1610 | — | 39 / 0 / 41 | 80 / 80 | 38 | 0 | 0 / 1 | Repaired · 2026-07-03 |
| E-2c483dc32fc18ba8 | Inkling | Rated | 16.2 | 1111 | — | 28 / 0 / 122 | 150 / 150 | 51 | 0 | 0 / 1 | First try · 2026-07-24 |
| E-e9202aa1565d1c4e | Inkling | Rated | 24.3 | 1201 | — | 42 / 0 / 120 | 162 / 162 | 57 | 0 | 0 / 1 | Repaired · 2026-07-24 |
| E-e8805bb60afd625c | Inkling Small | Limited data | 45.7 | 1505 | — | 9 / 0 / 8 | 17 / 17 | 9 | 0 | 0 / 1 | First try · 2026-08-09 |
| E-8e6cb252293b2af9 | Grok 4.5 | Rated | 76.2 | 1790 | — | 97 / 0 / 37 | 134 / 134 | 52 | 0 | 0 / 1 | First try · 2026-07-24 |