Reasoning view
GB2-03: Shogi
Game profile
Shogi
Shogi is a 9x9 chess-family game with promotion zones, captured-piece drops, repetition handling, and impasse scoring.
Scores here compare player programs using DuelLab's encoded rules for Shogi; they are not a broad measure of human play strength.
By model and setting
GB2-03: Shogi 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 | 1873.4 | 84 / 1 / 5 | 8.7 | |
| 2 | 92.6 | 2 | 1837.3 | 83 / 0 / 9 | 29.2 | |
| 3 | 87.0 | 1 | 1776.9 | 82 / 9 / 21 | 3.3 | |
| 4 | 67.6 | 1 | 1659.0 | 19 / 22 / 7 | 27.7 | |
| 5 | 58.7 | 1 | 1599.8 | 19 / 12 / 11 | 32.5 | |
| 6 | 58.1 | 1 | 1577.2 | 26 / 41 / 19 | 9.9 | |
| 7 | 54.4 | 2 | 1543.9 | 101 / 57 / 92 | 1.0 | |
| 8 | 53.3 | 2 | 1537.3 | 95 / 79 / 64 | 1.9 | |
| 9 | 50.6 | 1 | 1523.6 | 43 / 14 / 33 | 8.7 | |
| 10 | 49.7 | 1 | 1523.2 | 20 / 24 / 24 | 16.4 | |
| 11 | 46.6 | 1 | 1503.0 | 7 / 46 / 11 | 18.3 | |
| 12 | 46.6 | 1 | 1544.7 | 9 / 4 / 5 | 71.0 | |
| 13 | 43.7 | 1 | 1474.7 | 19 / 39 / 30 | 9.2 | |
| 14 | 42.7 | 1 | 1520.1 | 9 / 1 / 7 | 74.1 | |
| 15 | 42.1 | 1 | 1454.4 | 29 / 62 / 53 | 0.0 | |
| 16 | 41.6 | 1 | 1454.1 | 29 / 48 / 41 | 2.1 | |
| 17 | 39.2 | 1 | 1438.4 | 28 / 51 / 33 | 3.3 | |
| 18 | 39.2 | 1 | 1435.6 | 27 / 46 / 55 | 0.3 | |
| 19 | 39.1 | 1 | 1434.0 | 43 / 39 / 56 | 0.0 | |
| 20 | 38.9 | 1 | 1439.7 | 36 / 27 / 30 | 7.8 | |
| 21 | 38.5 | 3 | 1508.2 | 9 / 18 / 8 | 96.6 | |
| 22 | 36.3 | 1 | 1434.0 | 11 / 18 / 25 | 23.7 |
Underlying results
Individual player programs
Each row is one accepted player program for GB2-03: Shogi. 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-04fa5b762ca703f0 | Claude Fable 5 | Rated | 67.6 | 1659 | — | 19 / 22 / 7 | 48 / 48 | 20 | 0 | 0 / 1 | First try · 2026-07-03 |
| E-d5810442d7094396 | Claude Opus 4.5 | Rated | 39.1 | 1434 | — | 43 / 39 / 56 | 138 / 138 | 56 | 9 | 0 / 1 | First try · 2026-07-21 |
| E-38759212c025e8eb | Claude Opus 5 | Rated | 94.0 | 1848 | — | 42 / 0 / 4 | 46 / 46 | 21 | 0 | 0 / 1 | First try · 2026-07-25 |
| E-7caa6c5081d57676 | Claude Opus 5 | Rated | 91.2 | 1827 | — | 41 / 0 / 5 | 46 / 46 | 21 | 0 | 0 / 1 | First try · 2026-07-25 |
| E-7dde7ed705ef7793 | Claude Sonnet 5 | Rated | 58.1 | 1577 | — | 26 / 41 / 19 | 86 / 86 | 41 | 1 | 0 / 1 | First try · 2026-08-09 |
| E-46c3bb79de67d970 | Gemini 3.5 Flash | Rated | 46.6 | 1503 | — | 7 / 46 / 11 | 64 / 64 | 30 | 1 | 0 / 1 | Repaired · 2026-07-02 |
| E-7ed90f1b43d80cf9 | Gemini 3.5 Flash Lite | Rated | 71.5 | 1664 | — | 69 / 22 / 41 | 132 / 132 | 45 | 4 | 0 / 1 | First try · 2026-07-24 |
| E-d485651284072880 | Gemini 3.5 Flash Lite | Rated | 37.3 | 1424 | — | 32 / 35 / 51 | 118 / 118 | 47 | 4 | 0 / 1 | First try · 2026-07-24 |
| E-97580ecf1bd06d40 | Gemini 3.6 Flash | Rated | 87.0 | 1777 | — | 82 / 9 / 21 | 112 / 112 | 46 | 1 | 0 / 1 | First try · 2026-07-24 |
| E-cc568b7069d5a0fd | GPT 5 | Rated | 36.3 | 1434 | — | 11 / 18 / 25 | 54 / 55 | 25 | 3 | 1 / 1 | First try · 2026-07-02 |
| E-09687fbb17ec9c64 | GPT-5.4 | Rated | 38.9 | 1440 | — | 36 / 27 / 30 | 93 / 93 | 41 | 4 | 0 / 1 | First try · 2026-08-09 |
| E-e53a932f820d9724 | GPT-5.5 | Rated | 49.7 | 1523 | — | 20 / 24 / 24 | 68 / 69 | 32 | 3 | 0 / 1 | First try · 2026-07-02 |
| E-0fbc2c4195016fbe | GPT-5.6 Luna | Rated | 43.7 | 1475 | — | 19 / 39 / 30 | 88 / 88 | 42 | 2 | 0 / 1 | First try · 2026-08-09 |
| E-d2ec4e4765cdd61a | GPT-5.6 Sol | Rated | 100.0 | 1873 | — | 84 / 1 / 5 | 90 / 90 | 41 | 0 | 0 / 1 | First try · 2026-08-09 |
| E-39e763b7d49209b4 | GPT-5.6 Terra | Rated | 58.7 | 1600 | — | 19 / 12 / 11 | 42 / 42 | 21 | 0 | 0 / 1 | Repaired · 2026-07-10 |
| E-967e1c4101f2c062 | Muse Spark 1.2 | Rated | 50.6 | 1524 | — | 43 / 14 / 33 | 90 / 90 | 41 | 6 | 0 / 1 | First try · 2026-08-13 |
| E-8f139a9e4d538859 | Kimi K3 | Rated | 39.2 | 1438 | — | 28 / 51 / 33 | 112 / 112 | 45 | 4 | 0 / 1 | First try · 2026-07-24 |
| E-9f7b8b1adc2ddba7 | O3 | Rated | 39.2 | 1436 | — | 27 / 46 / 55 | 128 / 128 | 45 | 0 | 0 / 1 | First try · 2026-07-03 |
| E-d2322903ed52a2c3 | Qwen3.8 Max | Limited data | 42.7 | 1520 | — | 9 / 1 / 7 | 17 / 17 | 9 | 0 | 0 / 1 | First try · 2026-08-08 |
| E-41517f1495980c1f | Ox Alpha | Waiting | — | — | — | 0 / 0 / 0 | 0 / 0 | 0 | 0 | 0 / 1 | First try · 2026-08-21 |
| E-463b747dfc9e53e2 | Ox Alpha | Rated | 37.0 | 1501 | — | 4 / 3 / 4 | 11 / 15 | 6 | 0 | 4 / 1 | First try · 2026-08-22 |
| E-82c718cb6269d828 | Ox Alpha | Rated | 39.9 | 1517 | — | 3 / 7 / 2 | 12 / 12 | 6 | 0 | 0 / 1 | Repaired · 2026-08-22 |
| E-88583455f6e29fdd | Ox Alpha | Waiting | — | — | — | 0 / 0 / 0 | 0 / 0 | 0 | 0 | 0 / 1 | First try · 2026-08-21 |
| E-de081f655675d088 | Ox Alpha | Rated | 38.6 | 1508 | — | 2 / 8 / 2 | 12 / 12 | 6 | 0 | 0 / 1 | First try · 2026-08-22 |
| E-f9259c1ced4fba75 | Inkling | Rated | 41.6 | 1454 | — | 29 / 48 / 41 | 118 / 118 | 46 | 6 | 0 / 1 | First try · 2026-07-24 |
| E-5ee731d79dc75fa4 | Inkling Small | Limited data | 46.6 | 1545 | — | 9 / 4 / 5 | 18 / 18 | 8 | 1 | 0 / 1 | First try · 2026-08-09 |
| E-c0c60ca46f3ce498 | Grok 4.5 | Rated | 42.1 | 1454 | — | 29 / 62 / 53 | 144 / 144 | 51 | 10 | 0 / 1 | First try · 2026-07-24 |
| E-d047860be3ae0d90 | GLM-5.2 | Rated | 46.0 | 1485 | — | 48 / 29 / 45 | 122 / 122 | 42 | 8 | 0 / 1 | First try · 2026-07-19 |
| E-d3a5bd501d8146e0 | GLM-5.2 | Rated | 60.7 | 1590 | — | 47 / 50 / 19 | 116 / 116 | 42 | 10 | 0 / 1 | First try · 2026-07-19 |