Devin Fusion hits 61.7 on Coding Agent Index, costs 36% less than Claude Code per task
ArtificialAnlys · x · 2026-09-12
Artificial Analysis published detailed per-eval results for both Devin Fusion configurations.
Devin Fusion CLI with Claude Fable 5.1 (xhigh) + SWE-2 (medium) scores 61.7 on the Coding Agent Index v1.5, nearly tied with Claude Code's Fable 5.1 (max, with fallback) at 62.2, while costing 36% less ($7.9 vs $12.4 per task) with essentially flat speed (35.8 vs 34.8 min/task). Per-eval: DeepSWE 1.1 63.1 vs 64.3, SWE-Atlas QnA 65.9 vs 64.8, Terminal-Bench 4.0 56.1 vs 57.6. Both configs sit on the Pareto frontier of score vs cost.
More from coding & agent
- HABIT-Bench: Best agent memory system scores just 33.61% at inferring user habits — SJTU · 2026-10-28
- Memory Tax study: dedicated agent memory systems often lose to naive RAG — UIUC-CS · 2026-10-28
- Regehr's 'Piano Test': would you trust formally verified code with your life? — moyix · 2026-10-28
- Vibe-coded 'AI 浮生记' game satirizes AI startup life with compute black-market trading — vista8 · 2026-10-28
- Cursor ships Annotate in design mode: agents take visual prompts via on-page markup — soleio · 2026-10-28
- The legendary fake Go generics: Unicode Canadian Syllabics as angle brackets — rickasaurus · 2026-10-28