| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Lid Placement | Robotic Manipulation Tasks | Success Rate65.71 | 8 | |
| Bimanual Lifting | Robotic Manipulation Tasks | Success Rate97.14 | 8 | |
| Hand-over | Robotic Manipulation Tasks | Success Rate28.57 | 8 | |
| Block Pushing | Robotic Manipulation Tasks | Success Rate100 | 8 | |
| Dual Picking | Robotic Manipulation Tasks | Success Rate94.29 | 8 | |
| Shape dough | Robotic Manipulation Tasks (real-world) | Success Rate80 | 8 | |
| Robotic Manipulation | Robotic Manipulation Tasks Large perturbation | Average Success Rate62.2 | 7 | |
| Video Generation | Robotic Manipulation Tasks (test) | PSNR19.577 | 6 | |
| Aggregate Manipulation Tasks | Robotic Manipulation Tasks occluded | Success Rate60 | 4 | |
| Aggregate Manipulation Tasks | Robotic Manipulation Tasks no occlusion | Success Rate0.675 | 4 | |
| Insert Coin | Robotic Manipulation Tasks occluded | Success Rate (Insert Coin)2 | 4 | |
| Insert Coin | Robotic Manipulation Tasks no occlusion | Success Rate30 | 4 | |
| Retrieve Pack | Robotic Manipulation Tasks occluded | Success Rate90 | 4 | |
| Open Drawer | Robotic Manipulation Tasks occluded | Success Rate0.4 | 4 | |
| Open Drawer | Robotic Manipulation Tasks no occlusion | Success Rate60 | 4 | |
| Hammer Nail | Robotic Manipulation Tasks occluded | Success Rate7 | 4 | |
| Hammer Nail | Robotic Manipulation Tasks no occlusion | Success Rate100 | 4 | |
| Pick Mug | Robotic Manipulation Tasks occluded | Success Rate8 | 4 | |
| Pick Mug | Robotic Manipulation Tasks no occlusion | Success Rate8 | 4 | |
| Robotic Control | Robotic manipulation tasks Average | Inference Time (ms)10.76 | 4 | |
| Shape rope | Robotic Manipulation Tasks (real-world) | Success Rate9,000 | 4 | |
| Pivoting | Robotic Manipulation Tasks (real-world) | Success Rate4,000 | 4 | |
| Non-toppling push | Robotic Manipulation Tasks (real-world) | Success Rate8,000 | 4 | |
| Robotic Manipulation | Robotic Manipulation Tasks Galaxea A1 & UR7e (real-world) | Move Banana Success Rate73.2 | 2 | |
| Failure-revealing testing for VLA models | Robotic Manipulation Tasks Simulation (test) | Failure Detection90.38 | 2 |