ResearchDatasetsMeetingsFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsStep-level correctness assessmentMeetings (test)81.9PR-AUC22Step-level reasoning verificationMeetings73.4PR-AUC19MEP-Lobby link discoveryMeetings78AUC14