PH
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Tabletop manipulation | PH Toolhang (test) | Success Rate86 | 6 | |
| Tabletop manipulation | PH Square (test) | Success Rate94 | 6 | |
| Tabletop manipulation | PH Lift (test) | Success Rate100 | 6 | |
| Tabletop manipulation | PH Can (test) | Success Rate98 | 6 | |
| Over-refusal Compliance | PH Seemingly Toxic | Compliance Rate (Keyword Filter)87 | 5 |
Showing 5 of 5 rows