Shieldstral

#14 in Multimodal Models

Mistral AI · 6× · last seen Aug 05, 2026

42

Momentum

Shieldstral is a 3-billion-parameter content moderation model published by Mistral AI, available as an Open-Weight model under the Apache 2.0 license. It builds on Ministral-3B and uses a Pixtral vision encoder for multimodal inputs (text and image). Rather than relying on fixed categories, the model processes moderation policies as freely formulated natural language queries at runtime and delivers a calibrated safety score without requiring Fine-Tuning. According to the technical report, it achieves performance comparable to models up to 7 times larger on text safety Benchmarks and sets new records for multimodal moderation.

Sources (6)