GitHub Copilot Fusion orchestrates between models at half the cost
Web page · https://twitter.com/ArtificialAnlys/status/2115477376981508419
First seen by Oriel on .
AI summary
Artificial Analysis reports that GitHub Copilot Fusion orchestrates Anthropic and OpenAI models, delivering near-frontier coding-agent performance at roughly half Claude Code’s Opus 5.5 task cost.
- Copilot Fusion selects and coordinates models including Claude Opus 5.5, Claude Sonnet 5.5, GPT-6 Astra, and GPT-6 Sol.
- In the Coding Agent Index v2.0, Copilot Fusion scored 71 on Terminal-Bench 4.0, 51 on FrontierCode, and 57 on SWE-Atlas-QnA-AA.
- Copilot Fusion cost $5.59 per task, compared with $11.42 for Claude Code using Opus 5.5 at max settings.
- It used 7.2M tokens per task, approximately half Claude Opus 5.5’s usage and 30% less than the compared Devin Fusion configuration.
- Token costs are charged according to the underlying models used to complete each request.
#github copilot #coding agents #llm orchestration #benchmarking
Generated by gpt-5.6-sol. Check the original for details.
Metric trends
Last 30 days · Up to 120 recorded samples per source and metric, with reposts kept separate · First and latest retained
Points
Score reported by the source.
- Hacker News: 4, latest observation ; 0 over observed period since
Comments
Comment count reported by the source.
- Hacker News: 0, latest observation ; 0 over observed period since
Aliases
| Source | External ID | URL |
|---|---|---|
| Hacker News | 50299030 | https://twitter.com/ArtificialAnlys/status/2115477376981508419 Read discussion |