ResearchTasksConversation SimulationConversation SimulationFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedSimArena DocOSIM 8B84.1Primary Metric9Jun 15, 2026Humanual-ChatGPT 5.528.2Primary Quality Score9Jun 15, 2026MirrorBenchOSIM 8B68.3Primary Metric9Jun 15, 2026GSM8k and HumanEval 65 task intents4o-mini86.6Intent Coverage3Mar 24, 2026