ResearchTasksFactuality and Hallucination DetectionFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedFactScoreGPT-5-mini96.1FactScore9Jul 2, 2026LongFact ConceptsGPT-5.2 High99.7Overall Score9Jul 2, 2026LongFact ObjectsGPT-5.2 High99.2Factuality Score9Jul 2, 2026