Embodied Agent Task Completion on MCU task suite
100Wooden Success Rate (SR)
Human-level
Updated 1mo ago
Evaluation Results
| Method | Links | ||||||||
|---|---|---|---|---|---|---|---|---|---|
2026.03 | 100 | 100 | 100 | 100 | 100 | 100 | 100 | 100 | |
2026.03 | 98.97 | 94.19 | 57.07 | 14.64 | 35.12 | 15.77 | 28.36 | 53.37 | |
2026.03 | 98.71 | 93.48 | 55.83 | 13.79 | 31.24 | 17.06 | 27.63 | 52.52 | |
2026.03 | 98.7 | 91.76 | 45.92 | 6.85 | 24.48 | 13.06 | 18.98 | 46.73 | |
2026.03 | 98.63 | 93.37 | 55.28 | 13.52 | 33.73 | 12.78 | 27.18 | 52.04 | |
2026.03 | 98.3 | 92.75 | 45.24 | 8.07 | 28.17 | 8.21 | 14.8 | 45.83 | |
2026.03 | 98.28 | 94.3 | 46.41 | 8.58 | 25.09 | 14.93 | 19.43 | 47.63 | |
2026.03 | 98.09 | 92.61 | 52.43 | 10.11 | 30.77 | 14.58 | 23.47 | 50.09 | |
2026.03 | 97.91 | 93.6 | 46.06 | 7.05 | 32.03 | 11.42 | 19.09 | 47.42 | |
2026.03 | 97.36 | 91.18 | 50.55 | 8.63 | 29.08 | 10.92 | 22.07 | 48.43 | |
2026.03 | 96.63 | 91.4 | 44.13 | 7.79 | 23.06 | 7.95 | 18.04 | 45.23 | |
2026.03 | 93.57 | 89.09 | 35.93 | 11.27 | 23.49 | 9.21 | 15.94 | 42.67 | |
2026.03 | 93.08 | 88.73 | 35.57 | 11.12 | 26.18 | 9.03 | 15.58 | 42.59 | |
2026.03 | 92.99 | 88.58 | 35.21 | 9.79 | 22.96 | 8.92 | 15.52 | 42.04 | |
2026.03 | 92.37 | 88.14 | 34.76 | 10.83 | 23.41 | 8.39 | 14.92 | 41.75 | |
2026.03 | 91.79 | 86.87 | 33.94 | 8.87 | 21.82 | 8.08 | 14.19 | 40.79 | |
2026.03 | 25.61 | 18.72 | 2.47 | 0 | 0 | 0 | 0 | 7.26 |