ResearchTasksMulti-modal Preference EvaluationMulti-modal Preference EvaluationFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedMM-RewardBenchOmni-RRM72.9Accuracy19Feb 26, 2026VL-RewardGemini-2.5-Pro79.6Accuracy19Feb 26, 2026Multi-modal Preference Benchmarks Aggregate OverallGemini-2.5-Pro72Accuracy11Feb 26, 2026