ResearchTasksBenign Prompt FilteringBenign Prompt FilteringFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedOR-BenchPerplexity Filter0False Positive Rate12Apr 3, 2026AlpacaEvalGradientCuff0False Positive Rate10Apr 3, 2026HumanEvalPerplexity Filter0False Positive Rate10Apr 3, 2026GSM8KPerplexity Filter0False Positive Rate10Apr 3, 2026