# Cognition — Introducing SWE-Check: 10x Faster Bug Detection

- Company: Cognition (cognition.com)
- Announced: 2026-04-14
- Category: new-model
- Coverage: not counted
- Announcement: yes
- Group: models
- Source: https://cognition.com/blog/swe-check-10x-faster
- Record: https://forck.live/items/7669-introducing-swe-check-10x-faster-bug-detection
- Subject: Devin / SWE
- Models affected: SWE-check

Cognition, in partnership with Applied Compute, introduced SWE-Check, a reinforcement learning-trained bug detection model that matches frontier performance on in-distribution evaluations and makes progress on out-of-distribution evaluations, while being faster and cheaper.

## Evidence

Verbatim from https://cognition.com/blog/swe-check-10x-faster:

> We've partnered with Applied Compute to put this to the test by collaborating to RL-train a bug detection model. The result is SWE-check , which matches frontier performance on internal in-distribution evals (delta F1 to Opus 4.6 goes from 0.09 to 0) and makes meaningful progress on out-of-distribution evals (delta F1 to Opus 4.6 goes from 0.49 to 0.29).

---

Record: https://forck.live/items/7669-introducing-swe-check-10x-faster-bug-detection
Catalogue: https://forck.live/llms.txt
Current issue: https://forck.live/feed.md