| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Safety | MSSBench | Safety Score93.1 | 25 | |
| Multimodal Safety Evaluation | MSSBench | Safety Score2.55 | 22 | |
| Safety Evaluation | MSSbench (test) | Effectiveness Score99.66 | 20 | |
| Risk Identification | MSSBench | RIR96.05 | 12 | |
| Safety-Awareness | MSSBench | Safety Rate70.5 | 12 | |
| Vision-text safety classification | MSSBench Embodied | AUPRC (Prompt)61.97 | 9 | |
| Vision-text safety classification | MSSBench Chat | AUPRC (Prompt)52.07 | 9 | |
| Safety Alignment | MSSBench | Safety Score79.18 | 4 |