ResearchDatasetsSciSafetyBenchFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsAutomated Scientific Research EvaluationSciSafetyBench0Reject Rate28Scientific Safety EvaluationSciSafetyBench4.93Safety Score12