Github Copilot Fusion Orchestrates Anthropic And Openai Models To Balance Performance And Cost
Source
artificialanalysis.ai
Author
Artificial Analysis articles
Date
Why it matters
Copilot Fusion routes between Anthropic and OpenAI models and reaches near-frontier coding scores at $5.59 per task versus $11.42 for Claude Code with Opus 5.5. That makes routing a credible cost lever for coding agents.
Key takeaways · AI-distilled
Copilot Fusion is a runtime orchestrator that picks among Anthropic and OpenAI models, including Claude Opus 5.5, Sonnet 5.5, GPT-6 Astra and GPT-6 Sol, per task. Artificial Analysis measured its max setting 2 points below Claude Code with Opus 5.5 on its Coding AI agentAn AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.Full definition → Index.
Fusion cost $5.59 per task versus $11.42 for Claude Code with Opus 5.5 (max), and used 7.2M tokenThe chunk of text a model reads and writes in — roughly three-quarters of a word — and the unit AI usage is billed in.Full definition → per task, about half of Opus 5.5 in Claude Code and 30% less than Devin Fusion. Token charges follow whichever underlying models handle the request.
Its scores are uneven across the index's three equally weighted benchmarks: it leads Terminal-Bench 4.0 at 71, ranks third on FrontierCode at 51 behind Claude Code with Opus 5.5 (56), and lags on SWE-Atlas-QnA-AA at 57.
Terms in this piece · Glossary
AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
token — The chunk of text a model reads and writes in — roughly three-quarters of a word — and the unit AI usage is billed in.
