LabUtopia
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Runtime monitor execution | LabUtopia L1-L4 grounding 1.0 (source-held-out) | Unsafe Events23.8 | 10 | |
| Robot Manipulation | LabUtopia Out-of-Distribution | Pick Up Success Rate48.3 | 9 | |
| Robot Manipulation | LabUtopia In-Distribution | Pick Up Success Rate49.2 | 9 | |
| Runtime monitor execution | LabUtopia L1-L4 chemistry-held-out grounding 1.0 (hydrochloric acid) | Unsafe Events14.3 | 6 |
Showing 4 of 4 rows