Multi-turn embodied reasoning on BabyAI
73Success Rate
ReMem
Updated 8d ago
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
2025.11 | 73 | 83 | - | |
2025.11 | 63 | 73 | - | |
2025.11 | 62 | 72 | - | |
2025.11 | 61 | 71 | - | |
2025.11 | 57 | 72 | - | |
2025.11 | 56 | 65 | - | |
2026.05 | 55.35 | - | 70.07 | |
2025.11 | 54 | 66 | - | |
2025.11 | 53 | 64 | - | |
2025.11 | 53 | 64 | - | |
2025.11 | 53 | 66 | - | |
2025.11 | 53 | 64 | - | |
2025.11 | 53 | 61 | - | |
2025.11 | 53 | 68 | - | |
2025.11 | 52 | 64 | - | |
2025.11 | 52 | 65 | - | |
2025.11 | 52 | 64 | - | |
2025.11 | 52 | 68 | - | |
2025.11 | 51 | 66 | - | |
2025.11 | 50 | 67 | - | |
2026.05 | 50 | - | 63.12 | |
2026.05 | 48.21 | - | 60.25 | |
2026.05 | 48.2 | - | 64.1 | |
2025.11 | 48 | 63 | - | |
2025.11 | 48 | 66 | - | |
2025.11 | 48 | 66 | - | |
2026.05 | 47.3 | - | 61.4 | |
2025.11 | 46 | 64 | - | |
2025.11 | 46 | 64 | - | |
2026.05 | 41.96 | - | 58.15 | |
2026.05 | 40.17 | - | 50.62 | |
2026.05 | 37.5 | - | 50.4 | |
2026.05 | 37.5 | - | 50.16 | |
2026.05 | 35.71 | - | 46.41 | |
2026.05 | 26.78 | - | 42.44 | |
2026.05 | 25 | - | 35.3 | |
2026.05 | 23.21 | - | 35.55 |