ResearchDatasetsCombined Safety and HelpfulnessFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsInstruction Following and Safety EvaluationCombined Safety and Helpfulness Alpaca, HarmfulQA, Jailbreak (test)2.77Helpful Score8
Instruction Following and Safety EvaluationCombined Safety and Helpfulness Alpaca, HarmfulQA, Jailbreak (test)2.77Helpful Score8