| Maze (test) | Fed-SE | Success Rate0.8 | | 25 | 4d ago |
| Maze Hard | | Accuracy97.66 | | 14 | 4d ago |
| Maze (Standard) | | Accuracy0.9961 | | 14 | 4d ago |
| Maze Navigation Hard | TART | Success Rate72.8 | | 7 | 4d ago |
| Maze Navigation Medium | TART | Success Rate90.8 | | 7 | 4d ago |
| Maze Navigation Easy | TART | Success Rate97.2 | | 7 | 4d ago |
| MAZENAVIGATION OOD Both 8x8 Long 1.0 | Wan2.2-TI2V-5B | EM3,200 | | 7 | 4d ago |
| MAZENAVIGATION 7x7 Long OOD Both 1.0 | Wan2.2-TI2V-5B | EM4,000 | | 7 | 4d ago |
| MAZENAVIGATION OOD Path Length 6x6 Long 1.0 | Wan2.2-TI2V-5B | Exact Match4,200 | | 7 | 4d ago |
| MAZENAVIGATION OOD Path Length 5x5 Long 1.0 | Wan2.2-TI2V-5B | EM4,400 | | 7 | 4d ago |
| MAZENAVIGATION OOD Maze Sizes 8x8 1.0 | Wan2.2-TI2V-5B | EM80 | | 7 | 4d ago |
| MAZENAVIGATION OOD Maze Sizes 7x7 1.0 | Wan2.2-TI2V-5B (Unseen Visual Icons) | EM92 | | 7 | 4d ago |
| MAZENAVIGATION 3x3 - 6x6 1.0 (In Distribution) | Wan2.2-TI2V-5B | EM96 | | 7 | 4d ago |
| 32x32 Small Mazes (test) | Spiral RL | Mean Completion Time39.6 | | 6 | 4d ago |
| 16x16 Small Mazes pseudo-randomly generated (test) | Spiral RL | Mean Completion Time11 | | 6 | 4d ago |
| 64x64 Mazes | Spiral RL | Mean Time160.6 | | 6 | 4d ago |
| 128x128 Mazes | | Best Time (s)322 | | 6 | 4d ago |
| Maze Navigation | SSL | Success Rate86.6 | | 6 | 4d ago |