ResearchTasksMultimodal JudgmentFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedMM-VetPerception-Judge-Flex37.4Overall Score16Jun 2, 2026C.C.Perception-Judge-Flex46.2Score16Jun 2, 2026COCOGPT-4V41Score16Jun 2, 2026DiffGPT-4V0.361Score15Jun 2, 2026