# Cognition — Measuring the Trustworthiness of Open-Source-Derived Models

- Company: Cognition (cognition.com)
- Announced: 2026-07-08
- Category: research-paper
- Coverage: not counted
- Announcement: yes
- Group: announcements
- Source: https://cognition.com/blog/measuring-open-source-model-trustworthiness
- Record: https://forck.live/items/7649-measuring-the-trustworthiness-of-open-source-derived-models
- Subject: Devin / SWE
- Models affected: Kimi K2.7 Code, SWE-1.7, DeepSeek-V4, GLM 5.2, DeepSeek-R1

Cognition developed a trustworthiness evaluation suite combining direct questioning and realistic coding scenarios. They evaluated SWE-1.7, a model derived from the open-source Kimi K2.7 Code, and found it performed comparably or favorably to models from U.S. frontier labs on measures of propaganda, censorship, and security vulnerabilities. The results suggest that open-source models can be made at least as safe as leading closed models with targeted post-training.

## Evidence

Verbatim from https://cognition.com/blog/measuring-open-source-model-trustworthiness:

> SWE-1.7 performs comparably or favorably to models from U.S. frontier labs on these evaluations, and improves substantially over the base Kimi K2.7 Code model.

---

Record: https://forck.live/items/7649-measuring-the-trustworthiness-of-open-source-derived-models
Catalogue: https://forck.live/llms.txt
Current issue: https://forck.live/feed.md