ResearchDatasetsSCONEFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsSequential Instruction UnderstandingSCONE 1.0 (test)74.5Score (Sce)6Grounded ReasoningSCONE STREET72.4Answer Accuracy3Sequential instruction understandingSCONE (dev)64.1Sce. Score3