| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Over-Refusal Attack Resistance Evaluation | Over Refusal | MMLU65.57 | 60 | |
| Over Refusal | Over Refusal scenario | ASR100 | 42 | |
| Over-refusal Evaluation | Over-refusal (test) | Refusal Rate0 | 36 | |
| Over-refusal | Over-refusal XSTest and OKTest | Over-refusal Accuracy (XSTest)99.2 | 12 |