ResearchDatasetsStandard Benchmarks (ARC-Challenge, HellaSwag, Lambada, PIQA, WinoGrande)Standard Benchmarks (ARC-Challenge, HellaSwag, Lambada, PIQA, WinoGrande)FollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsMultiple Choice ClassificationStandard Benchmarks (ARC-Challenge, HellaSwag, Lambada, PIQA, WinoGrande) Zero-Shot56.31ARC-C Accuracy9
Multiple Choice ClassificationStandard Benchmarks (ARC-Challenge, HellaSwag, Lambada, PIQA, WinoGrande) Zero-Shot56.31ARC-C Accuracy9