ResearchDatasetsGeneral Language Tasks SuiteGeneral Language Tasks SuiteFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsGeneral Language UnderstandingGeneral Language Tasks Suite (WikiText-2, MMLU, PIQA, HellaSwag, WinoGrande, ARC-Challenge) standard (various)4.88PPL13
General Language UnderstandingGeneral Language Tasks Suite (WikiText-2, MMLU, PIQA, HellaSwag, WinoGrande, ARC-Challenge) standard (various)4.88PPL13