GitHub debuts Copilot Fusion for model selection and orchestration

GitHub launched Copilot Fusion, a system that automatically selects and orchestrates models for coding tasks, combining Project HydraFusion runtime orchestration with Copilot Auto Model Selection. On the Artificial Analysis Coding Agent Index, Fusion Max scored 60 versus 58 for Claude Code with Opus 5.5 Max, at about half the average API cost per task and 40% less time.

• Fusion Max scored 60 on the Coding Agent Index vs 58 for Claude Code with Opus 5.5 Max
• About half the average API cost per task and half as many tokens
• Roughly 40% less time per task
• Three effort levels: Fusion Standard, High and Max