| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Safety Evaluation | CATQA FigStep | Safety Score100 | 8 | |
| Safety Evaluation | CATQA Direct | Safety Score (1-ASR)1 | 8 | |
| Unsafety evaluation | CATQA | Chinese Safety Score37.7 | 8 | |
| Jailbreak Attack | CatQA-en | Harmful Rate1.01 | 6 | |
| Safety evaluation | CATQA Chinese (test) | Chinese Accuracy55.67 | 4 | |
| Safety evaluation | CATQA Vietnamese (test) | Score (Chinese)0.5336 | 4 | |
| Safety Evaluation | CatQA-en (test) | Harmful Content Rate1.66 | 3 |