ResearchDatasetsHUMANUALHUMANUALFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsEvaluation SimulationHumanual Opinion46.2Primary Metric9Roleplay SimulationHumanual Politics43.5Primary Metric9Roleplay SimulationHumanual News42.7Primary Metric9Response AlignmentHUMANUAL (test)6.08Alignment Score (Chat)8User SimulationHUMANUAL (test)40.58News Score3