Robot Manipulation on SimplerEnv Google Robot (test)
98.7Pick Coke CanVilla-X
Evaluation Results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| Villa-XSettings=Visual Matching2026.03 | 98.7 | 75 | 59.3 | 5.6 | 59.6 | |
| FutureVLA-OTSettings=Visual Matching, Style=OFT-style2026.03 | 97 | 83.8 | 55.6 | 74.1 | 77.6 | |
| FutureVLA-GTSettings=Variant Aggregation, Style=GR00T-style2026.03 | 95.7 | 72.9 | 52.4 | 81.2 | 75.6 | |
| FutureVLA-GTSettings=Visual Matching, Style=GR00T-style2026.03 | 92.3 | 74.2 | 68.5 | 85.2 | 80.1 | |
| π0Settings=Visual Matching2026.03 | 87.3 | 35 | 72.6 | 16 | 52.7 | |
| π0Settings=Variant Aggregation2026.03 | 85.2 | 40.8 | 42.1 | 16 | 46 | |
| FutureVLA-OTSettings=Variant Aggregation, Style=OFT-style2026.03 | 80.5 | 61.5 | 31.7 | 23.8 | 49.4 | |
| OpenVLA-OFTSettings=Visual Matching, Style=OFT-style2026.03 | 72.3 | 69.6 | 47.2 | 0.9 | 47.5 | |
| GR00T-N1.5Settings=Variant Aggregation, Style=GR00T-style2026.03 | 69.3 | 68.7 | 35.8 | 4 | 44.5 | |
| OpenVLA-OFTSettings=Variant Aggregation, Style=OFT-style2026.03 | 65.3 | 59 | 12.2 | 0.5 | 34.3 | |
| GR00T-N1.5Settings=Visual Matching, Style=GR00T-style2026.03 | 51.7 | 54 | 27.8 | 7.4 | 35.2 |