ResearchTasksMulti-shot Audio-Visual GenerationFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedMAVINSet high-fidelity benchmark 1K-sample (test)MAVIN231.6FVD11Jun 30, 2026MAVINSet subjective 20 samplesMAVIN36.8AVQ11Jun 30, 2026