ResearchTasksSafety Dialogue EvaluationSafety Dialogue EvaluationFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedSafeDialBenchFull-Context8.42Score33Feb 26, 2026SafeDialBenchQwen3-Max-Thinking61.33Normalized Score5Mar 25, 2026