ResearchDatasetsMEBenchFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsMulti-entity ReasoningMEBench Set3 (>100)94.6Comparison Accuracy5Multi-entity ReasoningMEBench Set2 (11-100)95.2Comparison Accuracy5Multi-entity ReasoningMEBench Set1 (0-10)96.8Comparison Accuracy5Multi-entity ReasoningMEBench All sets93.4Comparison Acc5