Embodied task planning on BEHAVIOR-1K B-100 1.0
97.5SP%
Gemini-3.1-Pro
Updated 25d ago
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
2026.06 | 97.5 | 97.5 | 99.19 | 0 | |
2026.06 | 97 | 97 | 99.2 | 1 | |
2026.06 | 95.2 | 95.5 | 99.32 | 1.5 | |
2026.06 | 94.5 | 96.5 | 99.21 | 2 | |
2026.06 | 94.3 | 95.7 | 98.67 | 2 | |
| 94 | 95.2 | 99.22 | 2.2 | ||
2026.06 | 93 | 97.5 | 99.36 | 4.5 | |
2026.06 | 93 | 96.5 | 98.4 | 5.5 | |
2026.06 | 90.5 | 96.5 | 98.49 | 6.5 | |
2026.06 | 90 | 96 | 98.74 | 6.5 | |
2026.06 | 87 | 93.5 | 97.7 | 9.5 | |
2026.06 | 86.5 | 95.5 | 98.24 | 9.5 | |
2026.06 | 83 | 94 | 96.62 | 15.5 | |
2026.06 | 82.5 | 93 | 96.93 | 13.5 | |
2026.06 | 80 | 92.5 | 94.91 | 18.5 | |
2026.06 | 72 | 87 | 95.17 | 23 | |
2026.06 | 69 | 82.5 | 86.81 | 23.5 |