# Cognition — Devin Fusion: Frontier Performance at 60% Lower Cost

- Company: Cognition (cognition.com)
- Announced: 2026-06-29
- Category: capability-change
- Coverage: not counted
- Announcement: yes
- Group: announcements
- Source: https://cognition.com/blog/devin-fusion
- Record: https://forck.live/items/7652-devin-fusion-frontier-performance-at-60-lower-cost
- Subject: Devin / SWE
- Models affected: Fable 5, Opus, GPT-5.5

Cognition introduced Devin Fusion, a multi-model harness that uses a frontier model and a cost-effective 'sidekick' model in parallel, achieving up to 60% cost reduction on the FrontierCode benchmark while maintaining performance. The system is available in preview on Devin.

## Evidence

Verbatim from https://cognition.com/blog/devin-fusion:

> we're sharing our work on a new kind of multi-model harness, Devin Fusion, that is substantially better at mixing models while reducing costs and maintaining intelligence on real-world usage.

---

Record: https://forck.live/items/7652-devin-fusion-frontier-performance-at-60-lower-cost
Catalogue: https://forck.live/llms.txt
Current issue: https://forck.live/feed.md