Report

GitHub launches Copilot Fusion with model routing for cost-optimized developer workflows

One post says Fusion picks a model for each task and claims frontier-level quality at up to 77% lower cost.

4 Sources, 6h ago, first seen 6h ago

Chart titled "Coding Agent Index vs. Cost per Task" by Artificial Analysis. The chart displays Artificial Analysis Coding Agent Index vs. average pay-per-token API cost per task (USD). It compares various agents, including some from Claude Code, Codex, Antigravity CLI, DeepSeek Harness, Grok Build, Opencode, Muse Code, Kimi Code CLI, and GitHub Copilot. The x-axis represents higher cost per task (USD) to lower cost per task (USD), and the y-axis represents the coding agent index. The chart highlights a "Most Attractive Quadrant" in green and uses dots to differentiate agents. Copilot Fusion (max) sits within the most attractive quadrant.

TLDR

A post says GitHub unveiled Copilot Fusion, which selects a model for each task and claims frontier-level quality at up to 77% lower cost. Another user cites Artificial Analysis Coding Agent Index scores of 60 for Fusion and 62 for Claude Code with Opus 5.5 Max, alongside costs of $5.59 versus $11.42 per task. The user describes Fusion as a cheaper router, not a better model.

Today's Rank

Combined views

—

4 Sources, first seen 6h ago