Cognition launches new SWE-2 model, Rivaling Fable 5.1 and GPT-Astra

一句话概要

Today we’re introducing SWE-2, our most advanced coding model yet. SWE-2 delivers highly competitive agentic coding performance across multiple effort…

原文开头节选

Menu Close Today we’re introducing SWE-2, our most advanced coding model yet. It pushes the Pareto frontier of capability and cost, achieving 50.0% on FrontierCode 1.1 Main 1 , within one point of Fable 5.1 while being 64% cheaper.

With SWE-2, we scaled RL to the multi-trillion-parameter regime for the first time, building on the SWE-1.7 2 training infrastructure and recipe. The key addition is an RL algorithm that trains all reasoning-effort levels in a single run, advancing the whole cost–performance frontier.

The result is our closest model yet to the frontier. On FrontierCode 1.1 Main and DeepSWE 1.1, SWE-2 beats SWE-1.7 and Grok 4.6 on both score and cost, matches GPT-5.6 Sol and Fable 5/5.1 at a fraction of their price, and comes within a few points of GPT-6 Astra at a quarter of the cost.

SWE-2 is post-trained from Kimi K3 3 , a 2.8T-parameter model that had already undergone extensive RL for agentic coding. As with SWE-1.7, our RL still finds substantial headroom, adding 5–6 points on many benchmarks and shifting K3’s entire cost–performance frontier.

(以上为原文节选,完整内容见下方”原文来源”)

这条动态今日登上 Hacker News 首页(307 赞 / 126 评论,来源 cognition.com)。技术雷达每日自动聚合 AI 工程、后端架构、DevOps 方向的前沿动态;相关工程落地可浏览下方的相关服务与延伸阅读,或直接与我们团队交流。