| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| Nemotron Response | ML-GUARD | F1 Score92 | 13 | 1mo ago | |
| Nemotron Query | ML-GUARD | F1 Score92 | 13 | 1mo ago | |
| CSRT | PolyGuard-Qwen | F1 Score81 | 13 | 1mo ago | |
| RTP-LX Query | Nemotron | F1 Score97 | 13 | 1mo ago | |
| XSafety | ML-GUARD | F1 Score48 | 13 | 1mo ago | |
| PGP Response | F1 Score75 | 13 | 1mo ago | ||
| PGP Query | PolyGuard-Qwen | F1 Score89 | 13 | 1mo ago | |
| ML-BENCH (test) | ML-GUARD-7B | F1 (Seed Query)97 | 13 | 1mo ago | |
| UnsafeBench | Sexual35.5 | 13 | 3mo ago | ||
| ToxicChat jailbreaking | Gliner-Guard-Omni | Macro F170.54 | 11 | 5d ago | |
| wildguard prompt safety | Opir-multitask-large | Macro F197.91 | 11 | 5d ago | |
| oai_safety OpenAI moderation | Nemotron Safety Guard v3 | Macro F176.76 | 11 | 5d ago | |
| MindGuard (test) | MindGuard 8B | AUROC98.2 | 9 | 3mo ago |