ResearchTasksOverall Performance EvaluationFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedConsolidated Evaluation BenchmarkAlphaToken49.49Overall Average Score18Jun 2, 2026Aggregate All DomainsVRPO38.14Average Accuracy16Jun 23, 2026Combined Suite (MME, MMStar, SQA, RealWorldQA, MMMU, MMMU-P, VisuLogic, LogicVista, CRPE, POPE, HallBench)Unicorn43.94Average Score4May 28, 2026
Combined Suite (MME, MMStar, SQA, RealWorldQA, MMMU, MMMU-P, VisuLogic, LogicVista, CRPE, POPE, HallBench)Unicorn43.94Average Score4May 28, 2026