ResearchTasksTask DecompositionFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedVoxMind Agentic Core Capabilities DatasetVoxMind95.24TS8Apr 20, 20263D-LLM Held-In 1.0 (test)Agentic Collaborative Cognition43.8BLEU-16Jun 24, 2026Disaster Response DocumentationRAPTOR-AI75TDA Score5Feb 26, 2026