ResearchDatasetsGEMFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsGrounded ECG InterpretationGEM (test)83.3Diagnosis Accuracy18Logical ReasoningGEM mastermind v1 (test)78.6Pass@16Logical reasoning and game playingGEM99.3Sudoku pass@16RDF-to-text generationGEM2 Factual (test)98.4Grammaticality6RDF-to-text generationGEM2 Fictional (test)93.7Grammaticality6