# Cognition introduces SWE-2 Flash, a fast open-weight coding model

> Original title: Cognition's new flash model is post-trained on top of Inkling-small!

- Source: Soumith Chintala
- Published: 2026-11-04T20:02:42.000Z
- Bad Influence: https://badinfluence.news/items/zhd8nhzdaqe68jxk5zcb25a0u
- Original: https://x.com/soumithchintala/status/2118071460631834931

## Summary

Cognition introduces SWE-2 Flash, a fast and efficient coding model that it says outperforms all American open-weight models on leading evals, including ones three times larger. Cognition says it is building a program to securely share the weights with partners and researchers, balancing transparency against cyber risks.

## Post

Cognition's new flash model is post-trained on top of Inkling-small!

## Quoted post @cognition

> Introducing SWE-2 Flash, our new fast & efficient coding model.
> 
> On leading evals, it outperforms all American open-weight models, even ones 3x larger.
> 
> To balance transparency and cyber risks, we are building a program to securely share the weights with partners & researchers.

https://x.com/cognition/status/2118069614521241739