| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| SafeAgentBench | HomeGuard-8B | RIR80.77 | 12 | 2mo ago | |
| PaSBench | GPT-4o-mini | RIR89.06 | 12 | 2mo ago | |
| MSSBench | GPT-4o-mini | RIR96.05 | 12 | 2mo ago | |
| EARBench | HomeGuard-8B | RIR94.73 | 12 | 2mo ago | |
| FLUID | Ours | AUC0.792 | 6 | 2mo ago | |
| IS-Bench | GPT-5.1 | Step Accuracy69.9 | 5 | 2d ago |
