ResearchBenchmarksText-to-Audio Generation on One-to-one evaluation benchmarks Text-to-AudioText-to-Audio Generation on One-to-one evaluation benchmarks Text-to-AudioFollow1.41FADTangoFlux1.07283.34895.6257.9011Dec 17, 2025Evaluation resultsMethodMethodLinksFADTangoFluxCategory=SpecialistsCategory=Specialists2025.121.41AudioXCategory=SpecialistsCategory=Specialists2025.123.09FlowBindCategory=GeneralistsCategory=Generalists2025.124.19OmniFlowCategory=GeneralistsCategory=Generalists2025.124.2UnifiedIO2-LCategory=GeneralistsCategory=Generalists2025.128.31CoDiCategory=GeneralistsCategory=Generalists2025.129.84