{"slug": "mistral-ai-releases-shieldstral-1-0-3b-an-open-weights-policy-adaptive-safety-7x", "title": "Mistral AI Releases Shieldstral 1.0 3B: An Open-Weights Policy-Adaptive Multimodal Safety Classifier Matching Models 7× Its Size", "summary": "Mistral AI released Shieldstral 1.0 3B, an open-weights, policy-adaptive multimodal safety classifier that matches models 7× its size, reporting 84.9% average F1 on text safety, 83.8% on multimodal safety, and 91.3% on adaptability, while fitting in 16GB of VRAM under an Apache 2.0 license. Built on Ministral-3-3B-Base-2512 with a Pixtral vision encoder and trained on roughly 54.1M samples, it allows operators to supply a policy as a plain-language query at inference time, eliminating retraining.", "body_md": "Mistral AI has released Shieldstral 1.0 3B, an open-weights, policy-adaptive multimodal safety classifier that frames content moderation as a single yes/no question instead of a fixed harm taxonomy. Operators supply the policy as a plain-language query at inference time and get back a calibrated safety score from one forward pass — no retraining required to re-target the model. Built on Ministral-3-3B-Base-2512 with a Pixtral vision encoder and trained on roughly 54.1M samples, it reports 84.9% average F1 on text safety (matching GPT-OSS-Safeguard-20B), 83.8% on multimodal safety, and 91.3% on Mistral's adaptability benchmark — while fitting in 16GB of VRAM under an Apache 2.0 license.\n\nThe post [Mistral AI Releases Shieldstral 1.0 3B: An Open-Weights Policy-Adaptive Multimodal Safety Classifier Matching Models 7× Its Size](https://www.marktechpost.com/2026/08/07/mistral-ai-releases-shieldstral-1-0-3b/) appeared first on [MarkTechPost](https://www.marktechpost.com).", "url": "https://wpnews.pro/news/mistral-ai-releases-shieldstral-1-0-3b-an-open-weights-policy-adaptive-safety-7x", "canonical_source": "https://www.marktechpost.com/2026/08/07/mistral-ai-releases-shieldstral-1-0-3b/", "published_at": "2026-08-08 04:36:26+00:00", "updated_at": "2026-08-09 13:04:15.855887+00:00", "lang": "en", "topics": ["artificial-intelligence", "ai-safety", "ai-products"], "entities": ["Mistral AI", "Shieldstral 1.0 3B", "Ministral-3-3B-Base-2512", "Pixtral", "GPT-OSS-Safeguard-20B", "Apache 2.0"], "alternates": {"html": "https://wpnews.pro/news/mistral-ai-releases-shieldstral-1-0-3b-an-open-weights-policy-adaptive-safety-7x", "markdown": "https://wpnews.pro/news/mistral-ai-releases-shieldstral-1-0-3b-an-open-weights-policy-adaptive-safety-7x.md", "text": "https://wpnews.pro/news/mistral-ai-releases-shieldstral-1-0-3b-an-open-weights-policy-adaptive-safety-7x.txt", "jsonld": "https://wpnews.pro/news/mistral-ai-releases-shieldstral-1-0-3b-an-open-weights-policy-adaptive-safety-7x.jsonld"}}