| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Robotic Manipulation | Simpler WidowX Simulation | Success Rate: Spoon on Towel82 | 23 | |
| Robotic Manipulation | WidowX | Spoon Success Rate100 | 17 | |
| Failure Detection | WidowX (unseen) | Brier Score0.153 | 11 | |
| Failure Detection | WidowX seen | Brier Score0.096 | 11 | |
| Slide Pot Manipulation | WidowX Real Robot | Success Rate4 | 4 | |
| Microwave Manipulation | WidowX Real Robot | Success Rate0.08 | 4 | |
| Button Manipulation | WidowX Real Robot | Success Rate0.85 | 4 | |
| Block Manipulation | WidowX Real Robot | Success Rate7 | 4 | |
| Robotic Manipulation | WidowX Real-world Open drawer BridgeData V2 (test) | Success Rate90 | 4 | |
| Robotic Manipulation | WidowX Real-world Pick-and-place monkey BridgeData V2 (test) | Success Rate75 | 4 | |
| Put corn in pot | WidowX real-world | Success Rate65 | 4 | |
| Pick up banana | WidowX real-world | Banana Pick Success Rate80 | 4 | |
| Push pumpkin to the left | WidowX 250s Real-world 1.0 (test) | Standard Setup Success Rate85 | 3 | |
| Robotic Manipulation | WidowX Evaluation Tasks | Visual Generalization Score6.8 | 3 |