ResearchDatasetsBeaverTails & WildChatBeaverTails & WildChatFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsSafety and Utility EvaluationBeaverTails & WildChat97.5Rule Adherence11Safety EvaluationBeaverTails & WildChat (test)97.5Rule Adherence Score8