| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| AMA-Bench SA | OPD-Evolver-9B | Success Metric52.92 | 20 | 1mo ago | |
| Corridor-Rooms 16 (|S|=400) | |S|400 | 7 | 1mo ago | ||
| Corridor-Rooms-9 (|S|=196) | Abstract State Count196 | 7 | 1mo ago | ||
| Corridor-Rooms-4 (|S|=64) | Abstract State Count64 | 7 | 1mo ago | ||
| Taxi | Tangle-Core | Abstract State Count (|S|)11 | 7 | 1mo ago | |
| Synth-Fold | Abstract State Count5,000 | 7 | 1mo ago | ||
| Multi-Goal | Abstract State Count1,600 | 7 | 1mo ago | ||
| Corridor-9 | Abstract State Count196 | 7 | 1mo ago | ||
| FourRooms | Tangle-Core | Abstract State Count4 | 7 | 1mo ago | |
| Corridor-Rooms-9 | Tangle-Core | Abstraction Size (≥ 90% Return)6 | 7 | 1mo ago | |
| MiniGrid FourRooms 16×16 | Return100 | 5 | 1mo ago |