{"slug": "devin-fusion-the-first-multi-model-coding-agent-on-the-pareto-frontier", "title": "Devin Fusion: the first multi-model coding agent on the Pareto frontier", "summary": "Devin Fusion, released today by Cognition, became the first multi-model coding agent placed on the Artificial Analysis Coding Agent Index, scoring 61.7 on Coding Agent Index v1.5 in its Devin Fusion CLI configuration with Claude Fable 5.1 (xhigh) plus SWE-2 (medium), nearly tied with Claude Fable 5.1 (max, with fallback) in Claude Code at 62.2. Artificial Analysis reported the Fusion configuration costs 36% less at $7.9 per task versus $12.4 for Claude Code, with essentially flat speed at 35.8 versus 34.8 minutes per task. The pattern held across underlying evaluations: Fusion scored 63.1 versus 64.3 on DeepSWE 1.1, 65.9 versus 64.8 on SWE-Atlas QnA, and 56.1 versus 57.6 on Terminal-Bench 4.0.", "body_md": "Artificial Analysis on X: \"Devin Fusion performs well for cost efficiency and performance, and currently sits on the Pareto frontier for Coding Agent Index score vs. Cost per Task in both configurations we tested\nDevin Fusion CLI with Claude Fable 5.1 (xhigh) + SWE-2 (medium) scores 61.7 on the Ar… / X\n\nArtificial Analysis on X: \"Devin Fusion performs well for cost efficiency and performance, and currently sits on the Pareto frontier for Coding Agent Index score vs. Cost per Task in both configurations we tested\nDevin Fusion CLI with Claude Fable 5.1 (xhigh) + SWE-2 (medium) scores 61.7 on the Artificial Analysis Coding Agent Index v1.5. This is almost tied with Claude Fable 5.1 (max, with fallback) in Claude Code at 62.2 despite the lower effort, and costs 36% less at $7.9 per task for the Fusion configuration vs. $12.4 for Claude Code. Speed is also essentially flat, with time per task of 35.8 vs. 34.8 minutes.\nThis pattern holds across the underlying evaluations: Fusion scores 63.1 vs. 64.3 on DeepSWE 1.1, 65.9 vs. 64.8 on SWE-Atlas QnA, and 56.1 vs. 57.6 on Terminal-Bench 4.0.\"\n\nDevin Fusion performs well for cost efficiency and performance, and currently sits on the Pareto frontier for Coding Agent Index score vs. Cost per Task in both configurations we tested\nDevin Fusion CLI with Claude Fable 5.1 (xhigh) + SWE-2 (medium) scores 61.7 on the Artificial Analysis Coding Agent Index v1.5. This is almost tied with Claude Fable 5.1 (max, with fallback) in Claude Code at 62.2 despite the lower effort, and costs 36% less at $7.9 per task for the Fusion configuration vs. $12.4 for Claude Code. Speed is also essentially flat, with time per task of 35.8 vs. 34.8 minutes.\nThis pattern holds across the underlying evaluations: Fusion scores 63.1 vs. 64.3 on DeepSWE 1.1, 65.9 vs. 64.8 on SWE-Atlas QnA, and 56.1 vs. 57.6 on Terminal-Bench 4.0.\n\nWe independently benchmarked Devin Fusion for its release today - this is the first time a multi-model coding agent has been included on the Artificial Analysis Coding Agent Index, and it effectively retains Claude Fable 5.1 and GPT-6 Astra performance while reducing costs\nDevinShow more\n\nDevin Fusion performs well for cost efficiency and performance, and currently sits on the Pareto frontier for Coding Agent Index score vs. Cost per Task in both configurations we tested\nDevin Fusion CLI with Claude Fable 5.1 (xhigh) + SWE-2 (medium) scores 61.7 on the Artificial Analysis Coding Agent Index v1.5. This is almost tied with Claude Fable 5.1 (max, with fallback) in Claude Code at 62.2 despite the lower effort, and costs 36% less at $7.9 per task for the Fusion configuration vs. $12.4 for Claude Code. Speed is also essentially flat, with time per task of 35.8 vs. 34.8 minutes.\nThis pattern holds across the underlying evaluations: Fusion scores 63.1 vs. 64.3 on DeepSWE 1.1, 65.9 vs. 64.8 on SWE-Atlas QnA, and 56.1 vs. 57.6 on Terminal-Bench 4.0.\n\nAstra and SWE together lands perfectly in the green zone. BTW Fusion works in both CLI and Devin Desktop (if you are more of a GUI guy like myself)\nFusion is a great concept and it's not a simple model router - encourage to read cognition.com/blog/devin-fus…\nThis is the futureShow more", "url": "https://wpnews.pro/news/devin-fusion-the-first-multi-model-coding-agent-on-the-pareto-frontier", "canonical_source": "https://twitter.com/ArtificialAnlys/status/2098504939781906684", "published_at": "2026-09-22 12:39:16+00:00", "updated_at": "2026-09-22 12:54:33.327239+00:00", "lang": "en", "topics": ["ai-agents", "ai-tools", "ai-products", "artificial-intelligence", "developer-tools"], "entities": ["Devin Fusion", "Cognition", "Artificial Analysis", "Claude Fable 5.1", "SWE-2", "Claude Code", "GPT-6 Astra", "Devin Desktop"], "alternates": {"html": "https://wpnews.pro/news/devin-fusion-the-first-multi-model-coding-agent-on-the-pareto-frontier", "markdown": "https://wpnews.pro/news/devin-fusion-the-first-multi-model-coding-agent-on-the-pareto-frontier.md", "text": "https://wpnews.pro/news/devin-fusion-the-first-multi-model-coding-agent-on-the-pareto-frontier.txt", "jsonld": "https://wpnews.pro/news/devin-fusion-the-first-multi-model-coding-agent-on-the-pareto-frontier.jsonld"}}