| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| TextWorld Cooking (test) | Accuracy75.5 | 14 | 21d ago | ||
| TextWorld Treasure (test) | Agent-BRACE | Accuracy81.5 | 14 | 21d ago | |
| TextWorld Quest (test) | Agent-BRACE | Accuracy88 | 14 | 21d ago | |
| TextWorld Cooking | Accuracy76 | 6 | 21d ago | ||
| TextWorld Treasure | Agent-BRACE | Accuracy81 | 6 | 21d ago | |
| TextWorld Quest | Agent-BRACE | Accuracy88 | 6 | 21d ago |