ResearchDatasetsVLSBenchVLSBenchFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsRefusal SuppressionVLSBench100TCR20Safety and Helpfulness EvaluationVLSBench84.41Safety Score18Multimodal SafetyVLSBench99.39F1 Score15Safety Alignment EvaluationVLSBench100Safety Score14