Data as of Jul 25, 2026 · Based on 2,718,867 AI responses across 9,511 prompts · See how Parse measures this
AOrchestragithub.comAOrchestra automates the creation of sub-agents for agentic orchestration by modeling each sub-agent as a four-tuple interface (I, C, T, M) that an orchestrator concretizes at runtime. It achieves a 16.28% relative improvement over the strongest baseline on benchmarks like GAIA, SWE-Bench, and TerminalBench when paired with Gemini 3 Flash.
Parse Score
Sources
arxiv.org shapes more of what AI says about AOrchestra than any other source, at 100% of its citations.
