GitHub promotes Copilot Fusion Max against Claude Code on Artificial Analysis coding index
Article timeline
The articles in this story. Times are ET.
GitHubOfficialGitHub commissions Artificial Analysis evaluation of coding agentsAIGitHub commissioned and funded an evaluation of coding agents by Artificial Analysis. The post links to full results and methodology on the Artificial Analysis website.
- GitHubOfficialGitHub's Copilot Fusion Max nears Claude Code's coding score at half the cost
AIIn the Artificial Analysis Coding Agent Index, GitHub says Copilot Fusion Max scored within two points of Claude Code with Opus 5.5 Max at about half the API cost per task. GitHub is offering 30% off Copilot Fusion through November 30.
- GitHub Copilot ChangelogOfficialPickGitHub Copilot Fusion becomes generally available with automatic model routing
AIGitHub says Copilot Fusion is now generally available. Instead of choosing a model for each task, users select Fusion Standard, High, or Max, and Copilot routes and orchestrates models as needed. In an Artificial Analysis Coding Agent Index test, Fusion Max scored 60, within two points of Claude Code with Opus 5.5 Max, at about half the average API cost per task.