ResearchDatasetsCross-LVLMFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsTruthfulness and Calibration EvaluationCross-LVLM Pooled Average (GQA, POPE, etc.)7.1ECE8Multimodal UnderstandingCross-LVLM (Aggregate of GQA, GMAI-MMBench, POPE, MME-Finance, MMMU_Pro, LLaVA-Wild) (test)13.8ECE8
Multimodal UnderstandingCross-LVLM (Aggregate of GQA, GMAI-MMBench, POPE, MME-Finance, MMMU_Pro, LLaVA-Wild) (test)13.8ECE8