ResearchTasksHelpful and Harmless Response GenerationFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedPKU-SafeRLHF alpaca2-7b (test)DPO-bettersafe8.53Helpfulness14Apr 21, 2026