ResearchDatasetsGeneral-purpose benchmarksFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsGeneral Knowledge EvaluationGeneral-purpose benchmarks average (test)73.8Accuracy12Text-to-Image GenerationGeneral-Purpose Benchmarks Wise, DPG, Aesthetic, PickScore (test)0.52Wise Score4
Text-to-Image GenerationGeneral-Purpose Benchmarks Wise, DPG, Aesthetic, PickScore (test)0.52Wise Score4