ResearchDatasetsProverQAFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsDeductive logical reasoningProverQA hard (test)0Error Rate12Linguistically Diverse ReasoningProverQA94Accuracy (Easy)8Logical ReasoningProverQA hard split0.686Accuracy8Deductive logical reasoningProverQA OOD hard subset 500 records (test)—Error Rate0