ResearchDatasetsPrimaryFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsPrompt Injection DetectionPrimary OOD75.28Macro-F13Prompt Injection DetectionPrimary HarmBench + Alpaca (OOD)75.28Macro-F12Handwritten Character RecognitionPrimary (train)99.71Accuracy2Handwritten Character RecognitionPrimary (val)98.5Accuracy2Handwritten Character RecognitionPrimary (test)98.84Accuracy2