Long-horizon manipulation on BEHAVIOR-1K (Simulation)
51Radio Score
ForesightFlow
Updated 1mo ago
Evaluation Results
| Method | Links | ||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
2026.06 | 51 | 51 | 57 | 38 | 28 | 20 | 62 | 59 | 34 | 30 | 46 | 39.6 | |
2026.06 | 47 | 47 | 48 | 36 | 23 | 21 | 68 | 66 | 34 | 25 | 44 | 39 | |
2026.06 | 44 | 44 | 43 | 30 | 18 | 14 | 51 | 46 | 33 | 24 | 38 | 31.6 | |
2026.06 | 42 | 42 | 46 | 35 | 2 | 0 | 68 | 65 | 19 | 13 | 35 | 31 | |
2026.06 | 42 | 42 | 47 | 32 | 19 | 18 | 62 | 59 | 24 | 21 | 39 | 34.4 |