ResearchDatasetsI-HallAI-HallAFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsText-to-Image Factuality EvaluationI-HallA History87.76FAGER6Text-to-Image Factuality EvaluationI-HallA Science 9990.83FAGER Score6Factual A/B testI-HallA History 99 pairs (test)83Pairwise Accuracy3