ResearchDatasetsSciSafetyBenchSciSafetyBenchFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsAutomated Scientific Research EvaluationSciSafetyBench0Reject Rate28Scientific Safety EvaluationSciSafetyBench4.93Safety Score12