ResearchTasksHuman PreferencesFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedL-Wilder smallGPT-4o85.9Preference Score14Feb 26, 2026WildVision 0617GPT-4o89.4Score14Feb 26, 2026