ResearchDatasetsMM-EvalMM-EvalFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsMultilingual Reward ModelingMM-Eval Avg. 18 lang87.53Accuracy14Multimodal Summarization Quality EvaluationMM-Eval (test)0.374Kendall's Tau (Correlation)1