ResearchDatasetsARC, GSM8k, HellaSwag, MMLUARC, GSM8k, HellaSwag, MMLUFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsInstruction Tuning EvaluationARC, GSM8k, HellaSwag, MMLU (test val)52.31ARC Accuracy7