Tool selection benchmark
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Intent Shifting | Tool selection benchmark | Certified Upper Bound (pu)80 | 6 | |
| Privilege Escalation | Tool selection benchmark | Certified Upper Bound82 | 6 | |
| Distractor Selection | Tool selection benchmark | Certified Upper Bound (pu)30 | 6 |
Showing 3 of 3 rows