ResearchDatasetsQuestions across domainsFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsEvaluation score correlation with ground-truth correctness37k questions across 85 domains0.238Pearson's rho18
Evaluation score correlation with ground-truth correctness37k questions across 85 domains0.238Pearson's rho18