ResearchTasksAutomated evaluation of tutor responsesAutomated evaluation of tutor responsesFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedMRBench extended (test)BJTU0.646Macro-F15Feb 26, 2026Kochmar 2025 (demonstration set)LoMTL68Accuracy3Feb 26, 2026Kochmar et al. 2025 (test)LoMTL0.72Accuracy3Feb 26, 2026