Today, Mistral AI released OCR 4, its latest document-understanding model. This new release adds bounding boxes, block classification, and inline confidence scores alongside extracted text. It supports 170 languages across 10 language groups and runs in a single container for fully self-hosted deployments. OCR 4 also serves as an ingestion component for enterprise search, RAG, and domain-specific retrieval pipelines.
TL;DR
OCR 4 returns bounding boxes, typed-block labels, and per-word confidence scores, not just text.
It supports 170 languages across 10 groups, with gains on rare and low-resource languages.
Independent annotators preferred OCR 4 over every system tested, averaging 72% win rates.
