tech
April 24, 2026
jina-reranker-m0: Multilingual Multimodal Document Reranker
Today we're releasing jina-reranker-m0, our new multilingual multimodal reranker model for ranking visual documents across multiple languages: it accepts a query alongside a collection of visually rich document images, including pages with text, figures, tables, infographics, and various layouts across multiple domains and over 29 languages. It outputs a ranked list of documents ordered by their relevance to the query. Compared to jina-reranker-v2-base-multilingual, jina-reranker-m0 also improves text reranking for multilingual content, long documents, and code searching tasks.
TL;DR
- jina-reranker-m0 is a new multilingual multimodal reranker model.
- It ranks visually rich documents across multiple languages.
- It accepts queries and document images with text, figures, tables, and infographics.
- The model supports over 29 languages and various domains.
- It outputs a ranked list of documents by relevance.
- jina-reranker-m0 improves upon jina-reranker-v2-base-multilingual for text reranking, long documents, and code searching.
Continue reading the original article