ResearchDatasetsHalluBenchFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsVisual ReasoningHalluBench71.85Accuracy24General-domain ReasoningHalluBench71Accuracy13AlignmentHalluBench63Accuracy10Hallucination EvaluationHALLUBENCH71.1Accuracy8Object Hallucination EvaluationHalluBench (test)76.6Accuracy6Math ReasoningHallubench68.45Accuracy@15