| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| EB-ALFRED 1.0 (test) | ReAct | Success Rate (Avg)67.2 | 20 | 3d ago | |
| ALFRED seen 1.0 (test) | OPEX | GC54.81 | 20 | 3d ago | |
| ALFWorld official (val) | Llama 3.1 405B | Success Rate65.3 | 12 | 3d ago | |
| Alfworld | Explicit RM | Progress Rate96.3 | 11 | 3d ago | |
| ALFRED (Seen) | HELPER + ODIN | Success Rate (SR)33.5 | 3 | 3d ago | |
| TEACh (Seen) | HELPER + ODIN | SR13.8 | 2 | 3d ago | |
| TEACh (Unseen) | HELPER + ODIN | Success Rate0.186 | 2 | 3d ago |