Robot Manipulation on RoboLab Simple 120
23.3Vague Success RateCosmos3-Nano-Policy-DROID
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| Cosmos3-Nano-Policy-DROIDCheckpoint type=off-the-shelf, Training mode=fine-tuned on DROID dataset2026.06 | 23.3 | 40.6 | 42 | |
| Cosmos3-Nano (PT-init)Checkpoint type=off-the-shelf, Training mode=fine-tuned on DROID dataset2026.06 | 17.8 | 30.3 | 32.8 | |
| π0.5Checkpoint type=off-the-shelf, Training mode=fine-tuned on DROID dataset2026.06 | 16.2 | 29.7 | 29.8 | |
| DreamZeroCheckpoint type=off-the-shelf, Training mode=fine-tuned on DROID dataset2026.06 | 15 | 26.1 | 25.8 | |
| π0-FASTCheckpoint type=off-the-shelf, Training mode=fine-tuned on DROID dataset2026.06 | 9.5 | 20.2 | 19.4 | |
| GR00T N1.6Checkpoint type=off-the-shelf, Training mode=fine-tuned on DROID dataset2026.06 | 7.2 | 8.8 | 7.5 | |
| π0Checkpoint type=off-the-shelf, Training mode=fine-tuned on DROID dataset2026.06 | 2.8 | 7.2 | 5.3 | |
| paligemma-binningCheckpoint type=off-the-shelf, Training mode=fine-tuned on DROID dataset2026.06 | 2.2 | 3.4 | 4.1 |