ResearchDatasetsProduction PromptsFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsModel safety training evaluationFiltered sample of production prompts (adversarial)96.8Not Unsafe Rate3
Model safety training evaluationFiltered sample of production prompts (adversarial)96.8Not Unsafe Rate3