Cognition Releases SWE-1.7 Model and Details RL Training Method
Original title:SWE-1.7: Frontier Intelligence at a Fraction of the Cost
AI summary
Cognition released SWE-1.7, which it says reaches frontier intelligence at lower cost. Trained on the Kimi K2.7 base, the model achieves 42.3% on FrontierCode 1.1 Main and 81.5% on Terminal-Bench 2.1, and is available in Devin (Web, Desktop and CLI) via Cerebras at 1000 TPS.
Key Takeaways
- Cognition released SWE-1.
- 7,which it says reaches frontier intelligence at lower cost.
- Trained on the Kimi K2.
- 7 base,the model achieves 42.
- 3% on FrontierCode 1.
Quick Facts
- Published
- Updated
- Source
- Cognition 模型 / Devin 博客(网页)
- Category
- Model Releases
- AI score
- 67
官方既公布基准成绩也详解训练方法,读者可以了解多集群 RL 训练、熵稳定和自压缩等具体做法。
Related entities
Source & copyright
This article is based on curated titles and AI summaries from the AIHOT public API, with attribution and links back. Original copyright remains with the original publishers and authors; this site does not mirror full texts.
How to Cite
When citing this article, keep the title, date, and permalink, and credit Orange News as the source.
Orange News: Cognition Releases SWE-1.7 Model and Details RL Training Method. July 8, 2026. https://new.nat6.net/en/news/cmtym40hy000erosk9j8hkc10/