ResearchTasksZero-shot Question Answering and Language ModelingFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedCommonsense and Reading Comprehension Suite (ARC-c, ARC-e, BoolQ, HellaSwag, LAMBADA, PIQA, RACE) zero-shotSTAR26.37ARC-c Accuracy8Jun 9, 2026
Commonsense and Reading Comprehension Suite (ARC-c, ARC-e, BoolQ, HellaSwag, LAMBADA, PIQA, RACE) zero-shotSTAR26.37ARC-c Accuracy8Jun 9, 2026