ResearchTasksOverall Multi-benchmark PerformanceOverall Multi-benchmark PerformanceFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedCombined MLLM Evaluation Suite AI2D, ChartQA, POPE, MME, MMBenchQwen2.5-VL-7B100Average Performance13Jul 1, 2026
Combined MLLM Evaluation Suite AI2D, ChartQA, POPE, MME, MMBenchQwen2.5-VL-7B100Average Performance13Jul 1, 2026