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 | 91.0 | 2 | 1963.1 | 181 / 0 / 17 | 6.3 | |
| 2 | 65.3 | 1 | 1727.9 | 17 / 0 / 0 | 74.1 | |
| 3 | 63.5 | 1 | 1642.7 | 117 / 0 / 62 | 0.0 | |
| 4 | 61.4 | 1 | 1630.6 | 61 / 0 / 31 | 8.1 | |
| 5 | 59.7 | 1 | 1615.3 | 47 / 0 / 29 | 13.2 | |
| 6 | 57.9 | 2 | 1591.7 | 113 / 0 / 63 | 9.3 | |
| 7 | 56.6 | 1 | 1576.3 | 50 / 0 / 42 | 8.1 | |
| 8 | 56.6 | 1 | 1576.6 | 58 / 0 / 32 | 8.7 | |
| 9 | 55.2 | 1 | 1564.7 | 46 / 0 / 30 | 13.2 | |
| 10 | 54.0 | 1 | 1550.0 | 46 / 0 / 32 | 12.5 | |
| 11 | 52.2 | 2 | 1516.0 | 191 / 0 / 144 | 0.0 | |
| 12 | 52.2 | 1 | 1525.5 | 47 / 0 / 49 | 7.0 | |
| 13 | 51.5 | 1 | 1519.5 | 54 / 0 / 36 | 8.7 | |
| 14 | 51.1 | 2 | 1519.8 | 72 / 0 / 74 | 14.6 | |
| 15 | 50.8 | 3 | 1514.9 | 116 / 0 / 114 | 13.0 | |
| 16 | 49.5 | 1 | 1486.7 | 76 / 0 / 81 | 0.0 | |
| 17 | 48.5 | 1 | 1484.0 | 45 / 0 / 49 | 7.5 | |
| 18 | 47.7 | 1 | 1474.7 | 48 / 0 / 48 | 7.0 | |
| 19 | 47.4 | 1 | 1470.1 | 52 / 0 / 52 | 5.0 | |
| 20 | 45.1 | 3 | 1501.8 | 25 / 0 / 23 | 77.5 | |
| 21 | 44.2 | 1 | 1433.9 | 46 / 0 / 56 | 5.5 | |
| 22 | 43.8 | 1 | 1432.3 | 48 / 0 / 40 | 9.2 | |
| 23 | 41.9 | 1 | 1411.1 | 44 / 0 / 46 | 8.7 | |
| 24 | 39.9 | 1 | 1388.6 | 40 / 0 / 50 | 8.7 | |
| 25 | 38.1 | 1 | 1367.3 | 29 / 0 / 63 | 8.1 | |
| 26 | 38.0 | 1 | 1366.1 | 43 / 0 / 47 | 8.7 | |
| 27 | 35.2 | 1 | 1334.1 | 39 / 0 / 55 | 7.5 | |
| 28 | 34.1 | 2 | 1320.2 | 71 / 0 / 135 | 5.3 | |
| 29 | 33.9 | 1 | 1311.3 | 49 / 0 / 99 | 0.0 | |
| 30 | 31.1 | 1 | 1289.4 | 27 / 0 / 59 | 9.9 | |
| 31 | 30.8 | 1 | 1285.1 | 33 / 0 / 59 | 8.1 | |
| 32 | 25.7 | 1 | 1277.8 | 1 / 0 / 17 | 71.0 | |
| 33 | 21.1 | 2 | 1177.5 | 38 / 0 / 128 | 10.8 | |
| 34 | 18.8 | 1 | 1154.1 | 17 / 0 / 57 | 14.0 | |
| 35 | 18.6 | 1 | 1147.6 | 25 / 0 / 63 | 9.2 | |
| 36 | 18.5 | 1 | 1146.4 | 26 / 0 / 64 | 8.7 | |
| 37 | 17.3 | 2 | 1134.4 | 46 / 0 / 124 | 10.2 | |
| 38 | 15.5 | 1 | 1100.5 | 33 / 0 / 148 | 0.0 | |
| 39 | 10.6 | 2 | 1046.2 | 47 / 0 / 277 | 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-934b5bc34a7e20b9 | Claude Opus 4.5 | Rated | 61.4 | 1631 | — | 61 / 0 / 31 | 92 / 92 | 46 | 0 | 0 / 1 | First try · 2026-07-02 |
| E-233f9cae6335e53d | Claude Opus 4.8 | Rated | 39.9 | 1389 | — | 40 / 0 / 50 | 90 / 90 | 45 | 0 | 0 / 1 | First try · 2026-07-02 |
| E-09963ffe0b0fa5fd | Claude Opus 5 | Rated | 92.5 | 1980 | — | 92 / 0 / 8 | 100 / 100 | 50 | 0 | 0 / 1 | First try · 2026-07-25 |
| E-b53cb955b1d8baab | Claude Opus 5 | Rated | 89.5 | 1946 | — | 89 / 0 / 9 | 98 / 98 | 49 | 0 | 0 / 1 | First try · 2026-07-25 |
| E-66c9ddb5d274adfe | Claude Sonnet 5 | Rated | 38.1 | 1367 | — | 29 / 0 / 63 | 92 / 92 | 45 | 0 | 0 / 1 | First try · 2026-08-09 |
| E-0dca18c79b6ac9d7 | DeepSeek V4 Flash | Rated | 44.2 | 1434 | — | 46 / 0 / 56 | 102 / 102 | 51 | 0 | 0 / 1 | First try · 2026-07-02 |
| E-da5f3b1a4e370e1a | DeepSeek V4 Pro | Rated | 41.9 | 1411 | — | 44 / 0 / 46 | 90 / 90 | 45 | 0 | 0 / 1 | Repaired · 2026-07-02 |
| E-d979b43c3aeea657 | Gemini 3.1 Flash Lite | Rated | 18.8 | 1154 | — | 17 / 0 / 57 | 74 / 74 | 37 | 0 | 0 / 1 | First try · 2026-07-02 |
| E-a13c4c9fdf6b244d | Gemini 3.5 Flash | Waiting | — | — | — | 0 / 0 / 0 | 0 / 0 | 0 | 0 | 0 / 1 | First try · 2026-07-21 |
| E-214f636367cbdac4 | Gemini 3.5 Flash Lite | Rated | 14.2 | 1087 | — | 23 / 0 / 141 | 164 / 164 | 60 | 0 | 0 / 1 | Repaired · 2026-07-24 |
| E-a870d09d3e1a40d4 | Gemini 3.5 Flash Lite | Rated | 6.9 | 1005 | — | 24 / 0 / 136 | 160 / 160 | 58 | 0 | 0 / 1 | First try · 2026-07-24 |
| E-9bef179ce22a6c93 | Gemini 3.6 Flash | Rated | 58.4 | 1587 | — | 84 / 0 / 73 | 157 / 157 | 64 | 0 | 0 / 1 | First try · 2026-07-24 |
| E-e23af86eb5787555 | Gemini 3.6 Flash | Rated | 46.0 | 1445 | — | 107 / 0 / 71 | 178 / 178 | 66 | 0 | 0 / 1 | First try · 2026-07-24 |
| E-e8e17fbbdd12faa4 | Gemma 4 31B | Rated | 18.6 | 1148 | — | 25 / 0 / 63 | 88 / 88 | 44 | 0 | 0 / 1 | First try · 2026-07-02 |
| E-1b9f1f7b70f02927 | GPT 4.1 | Rated | 18.5 | 1146 | — | 26 / 0 / 64 | 90 / 90 | 45 | 0 | 0 / 1 | First try · 2026-07-02 |
| E-d03d2c6a69fc3e16 | GPT 5 | Waiting | — | — | — | 0 / 0 / 0 | 0 / 0 | 0 | 0 | 0 / 1 | Repaired · 2026-07-21 |
| E-a09c0b14cae46193 | GPT-5.4 | Rated | 56.6 | 1577 | — | 58 / 0 / 32 | 90 / 90 | 43 | 0 | 0 / 1 | First try · 2026-08-09 |
| E-427bdffeacc6c394 | GPT-5.4 Mini | Rated | 31.1 | 1289 | — | 27 / 0 / 59 | 86 / 86 | 43 | 0 | 0 / 1 | Repaired · 2026-07-02 |
| E-3311575b341ee4a8 | GPT-5.4 Nano | Rated | 22.9 | 1198 | — | 19 / 0 / 63 | 82 / 82 | 41 | 0 | 0 / 1 | Repaired · 2026-07-09 |
| E-6c37eeef15b82287 | GPT-5.4 Nano | Rated | 19.3 | 1157 | — | 19 / 0 / 65 | 84 / 84 | 42 | 0 | 0 / 1 | Repaired · 2026-07-02 |
| E-6f42dbbf02274b56 | GPT-5.5 | Rated | 54.0 | 1550 | — | 46 / 0 / 32 | 78 / 78 | 39 | 0 | 0 / 1 | First try · 2026-07-02 |
| E-6879be00992f95f0 | GPT-5.6 Luna | Rated | 30.8 | 1285 | — | 33 / 0 / 59 | 92 / 92 | 43 | 0 | 0 / 1 | First try · 2026-08-09 |
| E-d29c6c5eb08da2d9 | GPT-5.6 Sol | Rated | 51.5 | 1519 | — | 54 / 0 / 36 | 90 / 90 | 43 | 0 | 0 / 1 | First try · 2026-08-09 |
| E-1f00b423eab1c19d | GPT-5.6 Terra | Rated | 55.2 | 1565 | — | 46 / 0 / 30 | 76 / 76 | 38 | 0 | 0 / 1 | First try · 2026-07-10 |
| E-067ab716d64e3e9a | LongCat 2.0 | Rated | 15.1 | 1109 | — | 19 / 0 / 69 | 88 / 90 | 44 | 0 | 2 / 1 | Repaired · 2026-07-24 |
| E-8cc657b7db4428cb | LongCat 2.0 | Rated | 19.5 | 1160 | — | 27 / 0 / 55 | 82 / 84 | 41 | 0 | 2 / 1 | First try · 2026-07-24 |
| E-1fbf9ab6a0c6d3ee | Muse Spark 1.2 | Rated | 56.6 | 1576 | — | 50 / 0 / 42 | 92 / 92 | 43 | 0 | 0 / 1 | First try · 2026-08-13 |
| E-33797d7b77c7800c | Minimax M3 | Rated | 47.4 | 1470 | — | 52 / 0 / 52 | 104 / 104 | 52 | 0 | 0 / 1 | Repaired · 2026-07-02 |
| E-4a7d37b86196302f | Mistral Medium 3.5 | Rated | 38.0 | 1366 | — | 43 / 0 / 47 | 90 / 90 | 45 | 0 | 0 / 1 | First try · 2026-07-02 |
| E-4419230379dcd41e | Kimi K3 | Rated | 63.5 | 1643 | — | 117 / 0 / 62 | 179 / 179 | 74 | 0 | 0 / 1 | First try · 2026-07-24 |
| E-962a9da8812a74d4 | Nex N2 Pro | Rated | 47.7 | 1475 | — | 48 / 0 / 48 | 96 / 96 | 48 | 0 | 0 / 1 | Repaired · 2026-07-11 |
| E-4477e0de2e04aad4 | Nemotron 3 Ultra 550B A55B | Rated | 59.7 | 1615 | — | 47 / 0 / 29 | 76 / 76 | 38 | 0 | 0 / 1 | First try · 2026-07-02 |
| E-172336d3fd38632a | GPT-OSS 120B | Rated | 15.5 | 1101 | — | 33 / 0 / 148 | 181 / 181 | 67 | 0 | 0 / 1 | Repaired · 2026-07-21 |
| E-1ca53619662c7f6f | Laguna S 2.1 | Rated | 77.4 | 1813 | — | 67 / 0 / 19 | 86 / 86 | 43 | 0 | 0 / 1 | First try · 2026-07-24 |
| E-21623e96b2b104e9 | Laguna S 2.1 | Rated | 38.3 | 1370 | — | 46 / 0 / 44 | 90 / 90 | 45 | 0 | 0 / 1 | Repaired · 2026-07-24 |
| E-c577c41440c17864 | Qwen3.7 Max | Rated | 52.2 | 1526 | — | 47 / 0 / 49 | 96 / 96 | 48 | 0 | 0 / 1 | First try · 2026-07-02 |
| E-94daaf1196d89c6c | Qwen3.7 Plus | Rated | 48.5 | 1484 | — | 45 / 0 / 49 | 94 / 94 | 47 | 0 | 0 / 1 | First try · 2026-07-02 |
| E-776235fa35035a89 | Qwen3.8 Max | Limited data | 65.3 | 1728 | — | 17 / 0 / 0 | 17 / 17 | 9 | 0 | 0 / 1 | First try · 2026-08-08 |
| E-070bbd8b3ce0460a | Ox Alpha | Rated | 41.4 | 1461 | — | 7 / 0 / 9 | 16 / 16 | 8 | 0 | 0 / 1 | Repaired · 2026-08-22 |
| E-575e460fdd8ace42 | Ox Alpha | Rated | 46.1 | 1513 | — | 9 / 0 / 7 | 16 / 16 | 8 | 0 | 0 / 1 | First try · 2026-08-22 |
| E-c69bc9b31ddf984b | Ox Alpha | Rated | 47.7 | 1532 | — | 9 / 0 / 7 | 16 / 16 | 8 | 0 | 0 / 1 | First try · 2026-08-22 |
| E-50f22f1c15a8fd4a | Step 3.7 Flash | Rated | 33.9 | 1311 | — | 49 / 0 / 99 | 148 / 152 | 55 | 0 | 0 / 1 | First try · 2026-07-21 |
| E-1bb81f8a4ae78954 | Hy3 Preview | Rated | 35.2 | 1334 | — | 39 / 0 / 55 | 94 / 94 | 47 | 0 | 0 / 1 | First try · 2026-07-02 |
| E-0f05573125dedc2b | Inkling | Rated | 33.6 | 1314 | — | 34 / 0 / 66 | 100 / 100 | 50 | 0 | 0 / 1 | Repaired · 2026-07-24 |
| E-f7a1d86c7e241f8d | Inkling | Rated | 34.7 | 1326 | — | 37 / 0 / 69 | 106 / 106 | 53 | 0 | 0 / 1 | First try · 2026-07-24 |
| E-7c80d62319ac1a53 | Inkling Small | Limited data | 25.7 | 1278 | — | 1 / 0 / 17 | 18 / 18 | 7 | 0 | 0 / 1 | First try · 2026-08-09 |
| E-3c5879def34f7d38 | Grok 4.5 | Rated | 49.5 | 1487 | — | 76 / 0 / 81 | 157 / 157 | 63 | 0 | 0 / 1 | First try · 2026-07-24 |
| E-09d406abc15f7c9a | MiMo-V2.5 | Rated | 64.9 | 1674 | — | 49 / 0 / 27 | 76 / 76 | 38 | 0 | 0 / 1 | First try · 2026-07-02 |
| E-9490f08c56c27d13 | MiMo-V2.5 | Rated | 33.4 | 1318 | — | 30 / 0 / 48 | 78 / 78 | 39 | 0 | 0 / 1 | Repaired · 2026-07-01 |
| E-be8fc9653466bbe1 | MiMo-V2.5 | Rated | 40.0 | 1393 | — | 37 / 0 / 39 | 76 / 76 | 38 | 0 | 0 / 1 | First try · 2026-07-02 |
| E-af55f57b03605914 | MiMo-V2.5-Pro | Rated | 43.8 | 1432 | — | 48 / 0 / 40 | 88 / 88 | 44 | 0 | 0 / 1 | First try · 2026-07-02 |
| E-38e323f4ce233fa1 | GLM-5.2 | Rated | 42.2 | 1417 | — | 40 / 0 / 40 | 80 / 80 | 40 | 0 | 0 / 1 | First try · 2026-07-11 |
| E-d8655d29a4806df8 | GLM-5.2 | Rated | 60.1 | 1623 | — | 32 / 0 / 34 | 66 / 66 | 33 | 0 | 0 / 1 | Repaired · 2026-07-02 |