| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Simple P-log Program Computation | robot | Preparation Time (s)0 | 16 | |
| Forecasting | Robot | MSE0.2473 | 12 | |
| Self-other distinction | Robot evaluation setting (Held-out) | Accuracy99.5 | 6 | |
| Object Grasping | Robot Policy In-domain (evaluation) | Success Rate65 | 6 | |
| HTN Planning | Robot | Median Plan Length7 | 6 | |
| HTN Planning | Robot | Coverage20 | 6 | |
| Task performance (Action Score) | Robot | Human Action Score63.49 | 3 | |
| Firmware Code Coverage Analysis | Robot | Min Basic Block Coverage1,295 | 1 |