ResearchTasksQuestion Generation EvaluationQuestion Generation EvaluationFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedEduAgent HumanQs (test)Human78.33AA8Feb 26, 2026EduAgent GenQs (test)ChatEval74.17Accuracy7Feb 26, 2026