• Home
  • Technology
  • Gaming
  • Entertainment
  • World & Business
  • Science
  • Sports
  • AI
HomeTechnologyGamingEntertainmentWorld & BusinessScienceSportsAI
  • HomeTechnologyGamingEntertainmentWorld & BusinessScienceSportsAI
    • Home
    • Technology
    • Gaming
    • Entertainment
    • World & Business
    • Science
    • Sports
    • AI
    AI

    Cognition introduces Fusion in Devin CLI, claiming 39% lower costs across coding benchmarks

    Cognition says Fusion lets users pick their preferred model for planning and a cost-effective model for execution.

    CO
    AA
    4 Sources, 19d ago, first seen 19d ago

    TLDR

    Cognition introduced Fusion in Devin CLI for Fable and Astra, claiming it is 39% cheaper across coding benchmarks. The company says it partnered with @ArtificialAnlys and @ValsAI to evaluate Fusion across several coding-agent benchmarks, with cost savings across the board while maintaining what it calls “frontier performance.”

    Combined views

    45.3K

    4 Sources, first seen 19d ago

    Combined views

    45.3K

    4 Sources, first seen 19d ago

    245 likes
    245 likes
    9 comments
    31 saves
    9 reposts

    Sentiment

    Positive——Negative

    Summary

    Not enough discussion yet.

    No sentiment analysis available yet.

    9 comments
    31 saves
    9 reposts

    Sentiment

    Positive——Negative

    Summary

    Not enough discussion yet.

    No sentiment analysis available yet.

    Today's Rank

    —

    Not ranked yet

    Today's Rank

    —

    Not ranked yet

    4 Sources

    @cognitionWe partnered with @ArtificialAnlys and @ValsAI to evaluate Fusion across several coding agent benchmarks. The cost savings hold across the board while maintaining frontier performance.
    @ArtificialAnlysDevin 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 Devin 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. This 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.

    4 Sources

    @cognitionWe partnered with @ArtificialAnlys and @ValsAI to evaluate Fusion across several coding agent benchmarks. The cost savings hold across the board while maintaining frontier performance.
    @ArtificialAnlysDevin 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 Devin 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. This 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.