| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| ALFWorld | Deepseek-V4-Pro | Overall Success Rate99.6 | 398 | 22d ago | |
| ALFWorld (test) | SELAUR | Success Rate96.87 | 81 | 25d ago | |
| ScienceWorld | Multi2 | Success Rate69.97 | 78 | 1mo ago | |
| WebShop | SAMPO | Success Rate84.02 | 77 | 18d ago | |
| ScienceWorld Seen | GRASP | Success Rate88.8 | 72 | 2mo ago | |
| ALFWorld Unseen | STEP-HRL | Success Rate97.76 | 67 | 18d ago | |
| Textcraft | GPT-4o-1120 | Success Rate99.6 | 60 | 1mo ago | |
| ALFWorld Seen | STEP-HRL | Success Rate97.86 | 47 | 18d ago | |
| InterCode NL2Bash | GRASP | Success Rate79.6 | 40 | 3mo ago | |
| WebShop (Seen) | GRASP | Average Reward62.3 | 40 | 3mo ago | |
| WebShop (test) | BPO | Success Rate97 | 37 | 2mo ago | |
| ALFWorld Seen (val) | SCPO | Pick Reward100 | 33 | 18d ago | |
| ScienceWorld Unseen | BPO | Success Rate85.15 | 32 | 2mo ago | |
| Virtualhome | HIPIF | Success Rate63.3 | 31 | 1mo ago | |
| WebShop | GPT-5 | Real39 | 24 | 3mo ago | |
| TextWorld | GPT-5 | Real100 | 24 | 3mo ago | |
| ScienceWorld Unseen (test) | ITPR | Success Rate58.94 | 24 | 4mo ago | |
| ScienceWorld Seen (val) | AdaPlan-H | Average Reward0.7349 | 20 | 2mo ago | |
| ALFWorld unseen (test) | AdaPlan-H | Average Reward88.81 | 20 | 2mo ago | |
| ALFWorld (OOD) | Multi2 | Success Rate56.43 | 18 | 1mo ago | |
| ScienceWorld (OOD) | MTRouter | Score9.9 | 14 | 2mo ago | |
| ScienceWorld (test) | MTRouter | Score53.8 | 14 | 2mo ago | |
| SciWorld | AMC (ReAct) | Score67.3 | 12 | 1mo ago | |
| WebShop (val) | GiGPO | Score85.8 | 11 | 18d ago | |
| ALFWorld | TurnOPD | Avg@4 (Least-Time)91.73 | 10 | 17d ago |