| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| BeaverTails | Roblox Guard 1.0 | F1 Score87.3 | 46 | 12d ago | |
| OpenAI | GPT-4o | F1 Score82.3 | 26 | 1mo ago | |
| Toxic Chat | GGuard | F1 Score82 | 24 | 1mo ago | |
| WildGuard | OMNIGUARD-7B | F1 Score78.6 | 12 | 1mo ago | |
| Aegis | OMNIGUARD-7B | F1 Score84 | 12 | 1mo ago |