Reasoning view
GB2-08: Tumbleweed
Game profile
Tumbleweed
Tumbleweed is a hex-grid territory game where players grow visible stacks and final control is determined by line-of-sight strength.
Scores here compare player programs using DuelLab's encoded rules for Tumbleweed; they are not a broad measure of human play strength.
By model and setting
GB2-08: Tumbleweed 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 | 100.0 | 1 | 2039.8 | 87 / 1 / 4 | 8.1 | |
| 2 | 91.3 | 1 | 1945.9 | 148 / 2 / 20 | 0.0 | |
| 3 | 83.6 | 1 | 1883.3 | 77 / 0 / 13 | 8.7 | |
| 4 | 81.0 | 1 | 1857.8 | 75 / 0 / 17 | 8.1 | |
| 5 | 73.8 | 1 | 1788.8 | 58 / 12 / 22 | 8.1 | |
| 6 | 72.3 | 2 | 1777.8 | 119 / 0 / 39 | 12.2 | |
| 7 | 70.2 | 1 | 1756.3 | 63 / 0 / 23 | 9.9 | |
| 8 | 59.0 | 1 | 1649.4 | 52 / 11 / 23 | 9.9 | |
| 9 | 51.5 | 1 | 1577.3 | 43 / 13 / 30 | 9.9 | |
| 10 | 50.9 | 2 | 1561.7 | 115 / 97 / 86 | 0.0 | |
| 11 | 45.3 | 3 | 1507.7 | 130 / 187 / 137 | 0.0 | |
| 12 | 44.5 | 3 | 1570.5 | 25 / 10 / 7 | 85.3 | |
| 13 | 41.1 | 1 | 1476.2 | 31 / 26 / 37 | 7.5 | |
| 14 | 35.9 | 1 | 1425.2 | 15 / 59 / 28 | 5.5 | |
| 15 | 34.7 | 1 | 1468.6 | 0 / 16 / 1 | 74.1 | |
| 16 | 33.9 | 1 | 1409.9 | 3 / 61 / 18 | 11.1 | |
| 17 | 33.8 | 2 | 1408.6 | 11 / 120 / 41 | 10.0 | |
| 18 | 33.8 | 1 | 1406.8 | 1 / 69 / 22 | 8.1 | |
| 19 | 33.4 | 1 | 1453.4 | 2 / 12 / 4 | 71.0 | |
| 20 | 33.1 | 1 | 1405.6 | 2 / 65 / 3 | 15.6 | |
| 21 | 33.0 | 1 | 1403.0 | 2 / 55 / 19 | 13.2 | |
| 22 | 32.2 | 1 | 1391.3 | 4 / 66 / 22 | 8.1 | |
| 23 | 32.0 | 1 | 1392.7 | 0 / 63 / 17 | 11.8 | |
| 24 | 28.3 | 1 | 1343.0 | 17 / 93 / 68 | 0.0 | |
| 25 | 27.9 | 1 | 1339.1 | 2 / 101 / 67 | 0.0 | |
| 26 | 26.8 | 1 | 1329.9 | 6 / 100 / 56 | 0.0 | |
| 27 | 24.2 | 1 | 1316.0 | 2 / 51 / 35 | 9.2 | |
| 28 | 24.2 | 1 | 1316.0 | 0 / 57 / 29 | 9.9 |
Underlying results
Individual player programs
Each row is one accepted player program for GB2-08: Tumbleweed. 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-12891afa894223fd | Claude Fable 5 | Rated | 100.0 | 2040 | — | 87 / 1 / 4 | 92 / 92 | 43 | 1 | 0 / 1 | Repaired · 2026-07-02 |
| E-6a0c04b4335bfea0 | Claude Opus 4.5 | Waiting | — | — | — | 0 / 0 / 0 | 0 / 0 | 0 | 0 | 0 / 1 | First try · 2026-07-02 |
| E-877eec51affacb3a | Claude Opus 4.5 | Rated | 28.3 | 1343 | — | 17 / 93 / 68 | 178 / 178 | 61 | 93 | 0 / 1 | First try · 2026-07-21 |
| E-22dc6fe5ae5fb8b1 | Claude Opus 4.8 | Rated | 70.2 | 1756 | — | 63 / 0 / 23 | 86 / 86 | 41 | 0 | 0 / 1 | First try · 2026-07-03 |
| E-a40851c4f03704e5 | Claude Opus 5 | Rated | 83.1 | 1882 | — | 65 / 0 / 13 | 78 / 78 | 33 | 0 | 0 / 1 | First try · 2026-07-25 |
| E-f5914ca845403384 | Claude Opus 5 | Rated | 61.4 | 1674 | — | 54 / 0 / 26 | 80 / 80 | 36 | 0 | 0 / 1 | First try · 2026-07-25 |
| E-df0550ce48a0b895 | Claude Sonnet 5 | Rated | 83.6 | 1883 | — | 77 / 0 / 13 | 90 / 90 | 42 | 0 | 0 / 1 | First try · 2026-08-09 |
| E-a7310645c3b96434 | DeepSeek V4 Flash | Rated | 33.8 | 1407 | — | 1 / 69 / 22 | 92 / 92 | 46 | 69 | 0 / 1 | Repaired · 2026-07-02 |
| E-3a5b5c4507a989d3 | DeepSeek V4 Pro | Rated | 33.0 | 1403 | — | 2 / 55 / 19 | 76 / 76 | 37 | 55 | 0 / 1 | Repaired · 2026-07-02 |
| E-b335c9f92035f80b | Gemini 3.1 Flash Lite | Rated | 32.2 | 1391 | — | 4 / 66 / 22 | 92 / 92 | 45 | 66 | 0 / 1 | Repaired · 2026-07-02 |
| E-fa332e578ae97122 | Gemini 3.5 Flash | Rated | 24.2 | 1316 | — | 0 / 57 / 29 | 86 / 86 | 43 | 57 | 0 / 1 | Repaired · 2026-07-02 |
| E-2a14d2f80ade1bda | Gemini 3.5 Flash Lite | Rated | 26.8 | 1330 | — | 6 / 100 / 56 | 162 / 162 | 58 | 100 | 0 / 2 | First try · 2026-07-24 |
| E-620b5ca2bcd82419 | Gemini 3.6 Flash | Rated | 72.9 | 1771 | — | 107 / 18 / 25 | 150 / 150 | 58 | 18 | 0 / 1 | First try · 2026-07-24 |
| E-efad9f3f4e9183a0 | Gemini 3.6 Flash | Rated | 29.0 | 1352 | — | 8 / 79 / 61 | 148 / 148 | 58 | 79 | 0 / 1 | First try · 2026-07-24 |
| E-ebca8ea756b4a4ad | GPT 5 | Rated | 35.9 | 1425 | — | 15 / 59 / 28 | 102 / 102 | 51 | 59 | 0 / 1 | First try · 2026-07-02 |
| E-431ff31b9cd599e1 | GPT-5.4 | Rated | 59.0 | 1649 | — | 52 / 11 / 23 | 86 / 86 | 42 | 11 | 0 / 1 | First try · 2026-08-09 |
| E-3e859a6b27767128 | GPT-5.5 | Rated | 73.8 | 1789 | — | 58 / 12 / 22 | 92 / 92 | 42 | 12 | 0 / 1 | First try · 2026-07-02 |
| E-ca2978e1aca13fec | GPT-5.6 Luna | Rated | 24.2 | 1316 | — | 2 / 51 / 35 | 88 / 88 | 42 | 51 | 0 / 1 | First try · 2026-08-09 |
| E-58adff67f80afed1 | GPT-5.6 Sol | Rated | 81.0 | 1858 | — | 75 / 0 / 17 | 92 / 92 | 42 | 0 | 0 / 1 | First try · 2026-08-09 |
| E-b061663dc342c859 | GPT-5.6 Terra | Rated | 51.5 | 1577 | — | 43 / 13 / 30 | 86 / 86 | 42 | 13 | 0 / 1 | Repaired · 2026-07-10 |
| E-2e3c01d0103fc439 | Nemotron 3 Ultra 550B A55B | Rated | 34.0 | 1409 | — | 8 / 62 / 22 | 92 / 92 | 45 | 62 | 0 / 1 | Repaired · 2026-07-11 |
| E-8c24e8bcbe9b1228 | Nemotron 3 Ultra 550B A55B | Rated | 33.7 | 1409 | — | 3 / 58 / 19 | 80 / 80 | 38 | 58 | 0 / 1 | First try · 2026-07-02 |
| E-2270b9df7d2b32cc | O3 | Rated | 75.2 | 1794 | — | 114 / 1 / 35 | 150 / 150 | 58 | 1 | 0 / 1 | First try · 2026-07-03 |
| E-9fbb8e6c69f575f4 | O3 | Rated | 25.5 | 1319 | — | 6 / 82 / 56 | 144 / 144 | 58 | 82 | 0 / 1 | First try · 2026-07-03 |
| E-afa6c09eebc859c4 | O3 | Rated | 35.2 | 1410 | — | 10 / 104 / 46 | 160 / 160 | 60 | 104 | 0 / 1 | First try · 2026-07-02 |
| E-24a75273941e6ea3 | GPT-OSS 120B | Rated | 33.9 | 1410 | — | 3 / 61 / 18 | 82 / 82 | 39 | 61 | 0 / 1 | Repaired · 2026-07-02 |
| E-eef649e110a96b98 | Qwen3.8 Max | Limited data | 33.4 | 1453 | — | 2 / 12 / 4 | 18 / 18 | 8 | 12 | 0 / 1 | First try · 2026-08-18 |
| E-27b1ec2d9d5762a4 | Ox Alpha | Rated | 54.9 | 1671 | — | 14 / 0 / 0 | 14 / 14 | 7 | 0 | 0 / 1 | First try · 2026-08-22 |
| E-ec8f506d56ff547e | Ox Alpha | Rated | 35.1 | 1481 | — | 3 / 7 / 4 | 14 / 14 | 7 | 7 | 0 / 1 | First try · 2026-08-22 |
| E-f84aa60bad19339a | Ox Alpha | Rated | 43.3 | 1560 | — | 8 / 3 / 3 | 14 / 14 | 7 | 3 | 0 / 1 | First try · 2026-08-22 |
| E-8b265019ada47f24 | Step 3.7 Flash | Rated | 32.0 | 1393 | — | 0 / 63 / 17 | 80 / 80 | 38 | 63 | 0 / 1 | Repaired · 2026-07-02 |
| E-81a5e5ef15f371dc | Hy3 Preview | Rated | 41.1 | 1476 | — | 31 / 26 / 37 | 94 / 94 | 46 | 26 | 0 / 1 | First try · 2026-07-02 |
| E-d21921560d198b28 | Inkling | Rated | 27.9 | 1339 | — | 2 / 101 / 67 | 170 / 170 | 63 | 101 | 0 / 1 | Repaired · 2026-07-24 |
| E-888363fef76ee16a | Inkling Small | Limited data | 34.7 | 1469 | — | 0 / 16 / 1 | 17 / 17 | 8 | 16 | 0 / 1 | Repaired · 2026-08-09 |
| E-707dd709e358a173 | Grok 4.5 | Rated | 91.3 | 1946 | — | 148 / 2 / 20 | 170 / 170 | 64 | 2 | 0 / 1 | First try · 2026-07-24 |
| E-5f664f9580459829 | MiMo-V2.5 | Rated | 33.1 | 1406 | — | 2 / 65 / 3 | 70 / 70 | 35 | 65 | 0 / 1 | Repaired · 2026-07-02 |