ResearchDatasetsQwen-VL Evaluation SuiteQwen-VL Evaluation SuiteFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsVision-Language Multi-task EvaluationQwen2.5-VL Evaluation Suite MMB, MME, POPE, SQA, VQAText (test)82.8MMB Score10
Vision-Language Multi-task EvaluationQwen2.5-VL Evaluation Suite MMB, MME, POPE, SQA, VQAText (test)82.8MMB Score10