ResearchDatasetsFinePhyEvalFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsCorrelation with Human JudgmentsFinePhyEval0.478Pearson's r7Correlation with Human Likert ScoresFinePhyEval0.478Pearson's r5Video Generation EvaluationFinePhyEval0.98Object Coherence Score4