ResearchTasksZero-shot Question Answering and Commonsense ReasoningFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedZero-shot Downstream Tasks (ARC, HellaSwag, WinoGrande, BoolQ, PiQA)FP1681Average Accuracy (Zero-Shot)48May 19, 2026
Zero-shot Downstream Tasks (ARC, HellaSwag, WinoGrande, BoolQ, PiQA)FP1681Average Accuracy (Zero-Shot)48May 19, 2026