ResearchDatasetsARC Challenge, BoolQ, OpenbookQA, GSM8K, MMLUFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsDownstream Task EvaluationARC Challenge, BoolQ, OpenbookQA, GSM8K (Strict), MMLU66.72ARC Challenge Accuracy5
Downstream Task EvaluationARC Challenge, BoolQ, OpenbookQA, GSM8K (Strict), MMLU66.72ARC Challenge Accuracy5