| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Over-refusal Assessment | XS (test) | F1 Score93.1 | 24 | |
| Safety Evaluation | Xs (test) | Safety Score100 | 16 | |
| Safety-Utility Trade-off | XS (test) | XS Test Score45.56 | 12 | |
| Over-refusal Compliance | XS (test) | Compliance Rate (Keyword Filter)98 | 5 |