ResearchTasksLanguage Modeling Downstream EvaluationLanguage Modeling Downstream EvaluationFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedDownstream tasks Average (test)BlockPruner58.02Average Score28Jun 16, 2026English Downstream Tasks 12 tasksMuRater47.13Reading Comprehension6Mar 6, 2026