| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| Keys and Doors Strict OOD | TBS-20 | Exact Match22.7 | 6 | 1mo ago | |
| Keys and Doors Hard ID | TBS-20 | Exact Match Rate99 | 6 | 1mo ago | |
| Keys and Doors Med | TBS-20 | Exact Match (%)99 | 6 | 1mo ago | |
| Keys and Doors Easy | TBS-20 | Exact Match Accuracy100 | 6 | 1mo ago | |
| Keys and Doors Overall | TBS-20 | Exact Match Percentage99.2 | 6 | 1mo ago | |
| Sliding Puzzle Hard | TBS-20 | Exact Match Rate88.7 | 6 | 1mo ago | |
| Sliding Puzzle Med. | TBS-20 | Success Rate89 | 6 | 1mo ago | |
| Sliding Puzzle Easy | BoN-20 | Exact Match Rate77 | 6 | 1mo ago | |
| Sliding Puzzle Overall | TBS-20 | Exact Match (%)86.5 | 6 | 1mo ago | |
| Sokoban Hard | TBS-20 | Exact Match79.7 | 6 | 1mo ago | |
| Sokoban Med. | BoN-20 | Exact Match (%)79.5 | 6 | 1mo ago | |
| Sokoban Easy | TBS-20 | Exact Match (%)99 | 6 | 1mo ago | |
| Sokoban Overall | TBS-20 | Exact Match Rate82.7 | 6 | 1mo ago | |
| Maze3D Hard | TBS-20 | Exact Match95.3 | 6 | 1mo ago | |
| Maze3D Med. | TBS-10 | Exact Match Rate100 | 6 | 1mo ago | |
| Maze3D Easy | BoN-1 | Exact Match Percentage100 | 6 | 1mo ago | |
| Maze3D Overall | TBS-20 | Exact Match (%)97.7 | 6 | 1mo ago | |
| Maze Hard | TBS-20 | Exact Match Rate81 | 6 | 1mo ago | |
| Maze Med | TBS-20 | Exact Match Rate99.5 | 6 | 1mo ago | |
| Maze Easy | BoN-5 | Exact Match Accuracy100 | 6 | 1mo ago | |
| Maze Overall | TBS-20 | Exact Match Percentage90.3 | 6 | 1mo ago |
