Embodied Task Completion on ALFWorld (test)
85.7Pick Success Rate
MASA
Updated 2d ago
Evaluation Results
| Method | Links | ||||||||
|---|---|---|---|---|---|---|---|---|---|
2026.05 | 85.7 | 53.8 | 81.5 | 56.2 | 44 | 45.8 | 64.3 | 25.7 | |
2026.05 | 68.6 | 46.2 | 44.4 | 25 | 20 | 33.3 | 42.1 | 34.1 | |
2026.05 | 68.6 | 53.8 | 40.7 | 18.8 | 40 | 29.2 | 44.3 | 34.8 | |
2026.05 | 65.7 | 38.5 | 25.9 | 43.8 | 16 | 29.2 | 37.9 | 36.7 | |
2026.05 | 62.9 | 38.5 | 70.4 | 75 | 56 | 37.5 | 57.9 | 29.2 | |
2026.05 | 57.1 | 46.2 | 77.8 | 81.3 | 76 | 54.2 | 65.7 | 24.3 | |
2026.05 | 54.3 | 46.2 | 29.6 | 6.2 | 24 | 20.8 | 32.1 | 39.1 | |
2026.05 | 51.4 | 38.5 | 59.3 | 37.5 | 44 | 29.2 | 45 | 32.2 | |
2026.05 | 48.6 | 46.2 | 44.4 | 25 | 32 | 16.7 | 36.4 | 37 | |
2026.05 | 48.6 | 46.2 | 40.7 | 50 | 44 | 20.8 | 41.4 | 35.6 | |
2026.05 | 28.6 | 30.8 | 37 | 18.8 | 32 | 12.5 | 27.1 | 40 | |
2026.05 | 25.7 | 53.8 | 40.7 | 37.5 | 24 | 20.8 | 31.4 | 38.4 | |
2026.05 | 25.7 | 38.5 | 44.4 | 25 | 16 | 16.7 | 27.1 | 39.6 | |
2026.05 | 20 | 15.4 | 18.5 | 18.8 | 16 | 12.5 | 17.1 | 44.6 | |
2026.05 | 20 | 30.8 | 29.6 | 12.5 | 20 | 8.3 | 20 | 42.3 | |
2026.05 | 17.1 | 38.5 | 40.7 | 31.2 | 20 | 12.5 | 25 | 40.5 |