{"slug": "github-copilot-fusion-orchestrates-between-models-at-half-the-cost", "title": "GitHub Copilot Fusion orchestrates between models at half the cost", "summary": "GitHub released Copilot Fusion, a runtime orchestration system inside GitHub Copilot that selects among Anthropic and OpenAI models including Claude Opus 5.5, Claude Sonnet 5.5, GPT-6 Astra and GPT-6 Sol, and it scored 2 points below Opus 5.5 in Claude Code at half the cost per task in the Artificial Analysis Coding Agent Index v2.0. Copilot Fusion cost $5.59 per task versus $11.42 for Claude Code with Opus 5.5 (max), used 7.2M tokens per task — roughly half of Opus 5.5 in Claude Code and 30% less than Devin Fusion with Opus 5.5 (max) plus GPT-6 Luna (high) — and led Terminal-Bench 4.0 at 71 while ranking third on FrontierCode at 51 and scoring 57 on SWE-Atlas-QnA-AA. GitHub charges token costs based on the underlying models used to complete a request.", "body_md": "GitHub has released Copilot Fusion in GitHub Copilot, which orchestrates between Anthropic and OpenAI models. It scores 2 points below Opus 5.5 in Claude Code at half the Cost per Task in the Coding Agent Index\nGitHub describes Copilot Fusion as a runtime orchestration system, which selects and coordinates models to optimize performance, cost, and latency for each task. Copilot Fusion chooses between a number of models from Anthropic and OpenAI, including Claude Opus 5.5, Claude Sonnet 5.5, GPT-6 Astra, and GPT-6 Sol. We benchmarked its max setting in GitHub Copilot CLI in the Artificial Analysis Coding Agent Index v2.0.\nToken costs are charged based on the underlying models used to complete a request.\nKey takeaways:\n➤ Cost-efficient for near-frontier performance: Copilot Fusion in GitHub Copilot costs $5.59 per task, versus $11.42 for Claude Code with Opus 5.5 (max). Devin Fusion with Opus 5.5 (max) + GPT-6 Luna (high) scores 62 at $8.00 per task.\n➤ Slight lead in Terminal-Bench 4.0: The Coding Agent Index v2.0 weights its three constituent benchmarks equally. Copilot Fusion in GitHub Copilot leads Terminal-Bench 4.0 with a score of 71. It ranks third on FrontierCode in the chart at 51, behind Claude Code with Opus 5.5 (max) at 56 and Devin Fusion with Opus 5.5 (max) + GPT-6 Luna (high) at 54. Its SWE-Atlas-QnA-AA score lags at 57, between GPT-6 Astra in Codex and Gemini 4 Argon in Antigravity CLI.\n➤ Half the token use of Opus 5.5 in Claude Code: GitHub Copilot Fusion used 7.2M tokens per task in the Coding Agent Index, approximately half of the tokens used by Claude Opus 5.5 in Claude Code, and 30% less than Devin Fusion with Opus 5.5 (max) + GPT-6 Luna (high).", "url": "https://wpnews.pro/news/github-copilot-fusion-orchestrates-between-models-at-half-the-cost", "canonical_source": "https://twitter.com/ArtificialAnlys/status/2115477376981508419", "published_at": "2026-10-30 02:09:03+00:00", "updated_at": "2026-10-30 02:46:54.284331+00:00", "lang": "en", "topics": ["ai-agents", "ai-tools", "large-language-models", "developer-tools"], "entities": ["GitHub", "GitHub Copilot", "Copilot Fusion", "Anthropic", "OpenAI", "Claude Opus 5.5", "Claude Code", "Artificial Analysis Coding Agent Index"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/github-copilot-fusion-orchestrates-between-models-at-half-the-cost", "markdown": "https://wpnews.pro/news/github-copilot-fusion-orchestrates-between-models-at-half-the-cost.md", "text": "https://wpnews.pro/news/github-copilot-fusion-orchestrates-between-models-at-half-the-cost.txt", "jsonld": "https://wpnews.pro/news/github-copilot-fusion-orchestrates-between-models-at-half-the-cost.jsonld"}}