ResearchDatasetsGroundBenchFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsMulti-shot video generationGroundBench0.426ARC Score10Multi-shot Video GenerationGroundBench (40 randomly sampled scripts)4.18Identity Score5Long-form Question AnsweringGroundBench (test)87.5Faithfulness (Full)4