ResearchDatasetsANLI, BoolQ, Winogrande, RTE, PiQA, ARCFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsAggregated Downstream EvaluationANLI, BoolQ, Winogrande, RTE, PiQA, ARC-Easy, ARC-Challenge61.94Average Accuracy8
Aggregated Downstream EvaluationANLI, BoolQ, Winogrande, RTE, PiQA, ARC-Easy, ARC-Challenge61.94Average Accuracy8