Task Performance on Sokoban
56.2Success Rate
Claude Opus 4.7
Updated 1d ago
Evaluation Results
| Method | Links | ||
|---|---|---|---|
2026.05 | 56.2 | 5.04 | |
2026.05 | 51.6 | 5.65 | |
2026.05 | 39.1 | 5.63 | |
2026.05 | 35.2 | 9.02 | |
2026.05 | 7 | 10.77 |
Claude Opus 4.7
| Method | Links | ||
|---|---|---|---|
2026.05 | 56.2 | 5.04 | |
2026.05 | 51.6 | 5.65 | |
2026.05 | 39.1 | 5.63 | |
2026.05 | 35.2 | 9.02 | |
2026.05 | 7 | 10.77 |