ResearchTasksLong-horizon task completionFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedCalvin ABC->DPriGo-DP98.1Success Rate (1)Long-horizon task completion on Calvin ABC->D performance trend72Jul 9, 2026CALVIN3D Diffuser Actor93.8Success Rate (1 Task)15Feb 26, 2026Minecraft long-horizon task suite (held-out)PEAM69.7Success Rate9May 28, 2026
Calvin ABC->DPriGo-DP98.1Success Rate (1)Long-horizon task completion on Calvin ABC->D performance trend72Jul 9, 2026