Interactive Decision Making on ScienceWorld (test)
53.8Score
MTRouter
Updated 1mo ago
Evaluation Results
| Method | Links | ||
|---|---|---|---|
2026.04 | 53.8 | 5.7 | |
2026.04 | 48.4 | 13.9 | |
2026.04 | 42.1 | 12.6 | |
2026.04 | 36.8 | 4.1 | |
2026.04 | 30.4 | 5.6 | |
2026.04 | 26.6 | 0.5 | |
2026.04 | 23.1 | 3.3 | |
2026.04 | 21.7 | 3.9 | |
2026.04 | 19.8 | 12.2 | |
2026.04 | 13.1 | 2.9 | |
2026.04 | 5.2 | 2.5 | |
2026.04 | 4.2 | 0.3 | |
2026.04 | -0.5 | 3.2 | |
2026.04 | -26.4 | 3 |