ResearchDatasetsCombined Prompt Harmfulness SuiteCombined Prompt Harmfulness SuiteFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsPrompt Harmfulness DetectionCombined Prompt Harmfulness Suite (ToxicChat, HarmBench, OpenAI Mod, Aegis SafetyTest, WildGuard Test)84.4Macro Avg Harmfulness Detection Rate17
Prompt Harmfulness DetectionCombined Prompt Harmfulness Suite (ToxicChat, HarmBench, OpenAI Mod, Aegis SafetyTest, WildGuard Test)84.4Macro Avg Harmfulness Detection Rate17