# Mistral releases Shieldstral, a 3B open-weights multimodal safety classifier

> Mistral released Shieldstral, a 3-billion-parameter open-weights multimodal safety classifier that it claims beats models up to seven times its size. Relevant to anyone running content moderation or guardrails locally, though the source gives no benchmark names or license terms.

| | |
|---|---|
| **Tool** | Mistral AI |
| **Version** | — |
| **Kind** | announcement |
| **Published** | 2026-08-04 |
| **Observed** | 2026-08-11 |
| **Significance** | 4/5 |
| **Breaking** | no |
| **Categories** | new-model, security, capability |

## What changed


- New model: Shieldstral, safety classifier
- 3B parameters, open weights
- Multimodal input
- Claimed to outperform models up to 7x its size (no benchmarks named in source)


## Sources

- [blog_rss](https://mistral.ai/news/shieldstral/) — retrieved 2026-08-11


## Community

_No curated reactions recorded. Facts and community takes are kept in separate layers
and never blended._

---
Canonical: https://changelogs.info/mistral/mistral-releases-shieldstral-a-3b-open-weights-multimodal-safety-classifier
Entity: https://changelogs.info/mistral
Event ID: `evt_2026-08-04_mistral_introducing-shieldstral`
Licence: event synthesis © changelogs.info, CC BY 4.0. Linked sources belong to their vendors.