| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| Public Prompt Harmfulness Benchmarks (ToxicChat, OpenAI Moderation, AegisSafetyTest, SimpleSafetyTests, HarmBenchPrompt) | OAI Score81 | 26 | 2mo ago | ||
| WildG | HaloGuard 1.0 | F1 Score96.2 | 22 | 17d ago | |
| WILDGUARD (test) | COLAGUARD | F1 Score89.44 | 18 | 1mo ago | |
| OAI | HaloGuard 1.0 | F1 Score87.4 | 10 | 22d ago |
