| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Sliding Puzzle | Sliding Puzzle | Solve Rate56.3 | 7 | |
| Structured video reasoning | Sliding Puzzle Hard | Exact Match Rate88.7 | 6 | |
| Structured video reasoning | Sliding Puzzle Med. | Success Rate89 | 6 | |
| Structured video reasoning | Sliding Puzzle Easy | Exact Match Rate77 | 6 | |
| Structured video reasoning | Sliding Puzzle Overall | Exact Match (%)86.5 | 6 |