ResearchTasksLinguistic EvaluationLinguistic EvaluationFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedSafeEditPaCE8.07Fluency10Feb 26, 2026T-Story ClozeSpiritLM-base-7B84.6T-Story Cloze Accuracy7Mar 6, 2026sBLIMPFlow-SLM-1B-ext60.6sBLIMP Score7Mar 6, 2026sWUGGYMoshi-7B (Base)74.3sWUGGY Score7Mar 6, 2026