ResearchTasksMulti-modal ChatMulti-modal ChatFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedMM-Vet v2 0613 (test)Proprietary API SOTA (Anthropic, 2024)71.8Score4Feb 26, 2026MM-MT (val)Proprietary API SOTA (Hurst et al., 2024)7.72Score4Feb 26, 2026MIA (val)Proprietary API SOTA (Hurst et al., 2024)88.6Score4Feb 26, 2026WildVision 0617 (test)Proprietary API SOTA (Hurst et al., 2024)89.2General Score4Feb 26, 2026