ResearchDatasetsTripsFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsStep-level correctness assessmentTrips (test)79.9PR-AUC22Step-level reasoning verificationTrips82.5PR-AUC19PlanningTrips (test)15.6Accuracy6