ResearchDatasetsKey-Value RecallFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsGeneral Reasoning and CodingKey-Value Recall Non-Factoid64.1GSM8K Accuracy6Factoid Knowledge RecallKey-Value Recall Factoid10.6ID Score6Key-Value RecallKey-Value Recall47.5LAMA Recall2