ResearchTasksGenerative tasksGenerative tasksFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updated8-task generative suiteHF FP16100Accuracy21Apr 24, 2026Generative tasks multi-preference settingGPT-4.1 + RP-Reasoner63Macro Acc (IA)16Feb 26, 2026