Mistral AI Releases Shieldstral 1.0 3B: An Open-Weights Policy-Adaptive Multimodal Safety Classifier Matching Models 7× Its Size

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.

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. The 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 .