ResearchDatasetsProduction BenchmarksFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsSafety EvaluationProduction Benchmarks92.6Hate (Non-Violent)4Safety EvaluationProduction Benchmarks production-representative traffic May 202588.3Non-Violent Hate Score4
Safety EvaluationProduction Benchmarks production-representative traffic May 202588.3Non-Violent Hate Score4