Introducing SWE-2: Pushing the Pareto Frontier
Today we’re introducing SWE-2, our most advanced coding model yet. SWE-2 delivers highly competitive agentic coding performance across multiple effort…
The Cognition Team
SWE-2
Cognition
A coding model post-trained from Kimi K3 with reinforcement learning across reasoning effort levels. Available in Devin Desktop and CLI, with rollout to Devin Web and Fusion.
Specs
Model
- Family
- SWE
- Parameters
- 2.8T
- Weights
- Proprietary
Dates
- Announced
- 10 Sept 2026
Articles
All articlescognition.com