| HUS-II HPAA-applied | | Hate Detection Rate0 | | 10 | 1mo ago |
| STTD Original | G2F | Hate Detection Rate100 | | 10 | 1mo ago |
| WildJailbreak | prompt–response verification framework | F1 Score96.6 | | 4 | 1mo ago |
| Do-Not-Answer | prompt–response verification framework | F1 Score96.4 | | 2 | 1mo ago |
| WildGuardMix | prompt–response verification framework | F1 Score95.9 | | 2 | 1mo ago |
| Aegis-Safety 2.0 | prompt–response verification framework | F1 Score95.1 | | 2 | 1mo ago |
| BeaverTails | prompt–response verification framework | F1 Score96.2 | | 2 | 1mo ago |
| HarmBench | prompt–response verification framework | F1 Score95.6 | | 2 | 1mo ago |
| HarmBench cyber | prompt–response verification framework | F1 Score92.8 | | 2 | 1mo ago |
| CyberSecEval | prompt–response verification framework | F1 Score92.2 | | 2 | 1mo ago |
| MOCHA | prompt–response verification framework | F1 Score93.1 | | 2 | 1mo ago |
| PhishBots | prompt–response verification framework | F1 Score98.1 | | 2 | 1mo ago |
| InjecAgent | prompt–response verification framework | F1 Score92.8 | | 2 | 1mo ago |
| deepset prompt-injections | prompt–response verification framework | F1 Score93.9 | | 2 | 1mo ago |
| PINT | prompt–response verification framework | F1 Score93.1 | | 2 | 1mo ago |
| StrongReject | prompt–response verification framework | F1 Score95.8 | | 2 | 1mo ago |
| JailbreakBench | prompt–response verification framework | F1 Score96.2 | | 2 | 1mo ago |