ResearchTasksMulti-image hallucination evaluationMulti-image hallucination evaluationFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedMUIRBenchQwen2.5-VL + CAPL62Accuracy12Mar 10, 2026BLINKGLM4.1VBase + CAPL61.33Accuracy12Mar 10, 2026