| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| WILDJAILBREAK (val) | WILDGUARD | ASR0.7 | 18 | 4d ago | |
| Wild Guard Response | WildGuard | F1 Score88.9 | 12 | 4d ago | |
| GuarEval Prompt | WildGuard | F1 Score88.9 | 10 | 4d ago | |
| RobloxGuard Eval | Roblox Guard 1.0 | F1 Score79.6 | 7 | 4d ago | |
| SafeRLHF | Roblox Guard 1.0 | F1 Score69.9 | 7 | 4d ago | |
| Harmbench | BingoGuard | F1 Score86.4 | 7 | 4d ago | |
| Aegis Response 2.0 | NemoGuard | F1 Score87.6 | 7 | 4d ago | |
| XSTest | BingoGuard | F1 Score94.9 | 7 | 4d ago | |
| WildGuard Prompt | Roblox Guard 1.0 | F1 Score89.5 | 7 | 4d ago | |
| SimpleSafetyTest | Roblox Guard 1.0 | F1 Score100 | 7 | 4d ago | |
| OAI Mod | ShieldGemma | F1 Score82.1 | 7 | 4d ago | |
| Aegis Prompt 2.0 | Roblox Guard 1.0 | F1 Score87.9 | 7 | 4d ago | |
| Aegis Prompt 1.0 | Roblox Guard 1.0 | F1 Score91.9 | 7 | 4d ago | |
| Beaver Response | WildGuard | F1 Score84.4 | 5 | 4d ago | |
| Nemo-Safety Response | WildGuard | F1 Score0.835 | 5 | 4d ago | |
| GuarEval Response | GGuard | F1 Score (Safety Moderation)79.4 | 5 | 4d ago | |
| Beaver Prompt | GGuard | F1 Score77.2 | 5 | 4d ago | |
| Nemo-Safety Prompt | GGuard | F1 Score82 | 5 | 4d ago |