Robot Policy Learning on LIBERO standard 4-suite protocol
98.8Spatial Achievement Rateπ0.5
Evaluation results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| π0.52026.06 | 98.8 | 98.2 | 98 | 92.4 | 96.9 | |
| CogVLA2026.06 | 98.6 | 98.8 | 96.6 | 95.4 | 97.4 | |
| A2World-policy2026.06 | 98.2 | 99.2 | 98.6 | 98.2 | 98.6 | |
| Cosmos Policy2026.06 | 98.1 | 100 | 98.2 | 97.6 | 98.5 | |
| OpenVLA-OFT2026.06 | 97.6 | 98.4 | 97.9 | 94.5 | 97.1 | |
| Dita2026.06 | 97.4 | 94.8 | 93.2 | 83.6 | 92.3 | |
| π02026.06 | 96.8 | 98.8 | 95.8 | 85.2 | 94.2 | |
| UniVLA2026.06 | 96.5 | 96.8 | 95.6 | 92 | 95.2 | |
| 4D-VLA2026.06 | 88.9 | 95.2 | 90.9 | 79.1 | 88.6 | |
| Diffusion Policy2026.06 | 78.3 | 92.5 | 68.3 | 50.5 | 72.4 |