ResearchTasksGeneral MLLM EvaluationFor AI assistantsMarkdownContent indexGeneral MLLM EvaluationFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedAverage V* HR-Bench POPESpecEyes84.26Accuracy13Mar 25, 2026