Cognition Releases SWE-2: A Kimi K3 Post-Trained Coding Model That Matches Fable 5.1 on FrontierCode at 64% Lower Cost
Cognition released SWE-2, an RL post-trained coding model from Kimi K3, scoring 50.0% on FrontierCode 1.1 Main and available only inside Devin.
Cognition released SWE-2, its most capable coding model, post-trained with reinforcement learning from Moonshot AI's 2.8T-parameter Kimi K3 base. It scores 50.0% on FrontierCode 1.1 Main, within 1 point of Fable 5.1 at 64% lower cost, and RL reportedly adds 5-6 points over the K3 base on many benchmarks. It is the first Cognition model with selectable reasoning-effort levels all trained in a single RL run using Pareto-slope-matched cost penalties. There are no open weights and no standalone API; it runs only inside Devin (Desktop, CLI, with Web and Fusion rolling out), free for paid tiers through October 10, 2026.
- Scores 50.0% on FrontierCode 1.1 Main, within 1 point of Fable 5.1 at 64% lower cost
- Post-trained from 2.8T-parameter Kimi K3; RL adds 5-6 points on most benchmarks
- Three effort levels trained in one RL run via slope-matched linear cost penalties
- SWE-2 medium cuts turns 58% and cost 81% versus SWE-1.7 on FrontierCode
- No open weights or API; Devin-only availability, free for paid tiers until October 2026
From the original article
4 min read at marktechpost.com
Cognition, the company behind the Devin coding agent, has released SWE-2, its most capable coding model to date. SWE-2 is post-trained with reinforcement learning from Kimi K3, Moonshot AI’s 2. 8T-parameter open model.
By Asif Razzaq · marktechpost.com
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.