A reranker takes documents found by search and reorders them by how well they answer the question. This noticeably improves the accuracy of an assistant that answers from a knowledge base. Check quality in your languages, speed at your document volume and the license terms.
Strong multilingual rerankers; m0 also ranks pages as images (scans, slides). The latest versions are open for non-commercial use only.
A pair of small Tencent models based on Qwen3 that pick the right skill for an AI agent for a given request: the embedding model finds candidates, the reranker chooses the best one.
A small 1B reranker from NVIDIA. The vl version also takes document pages as images, not just text. The card states multilingual support without listing the languages.
Rerankers built on Qwen3. The model card lists the target domains — finance, law, code, medicine, science; the stated language is English.
Embeddings and rerankers from Germany's Mixedbread. mxbai-embed-large is one of the most downloaded English search models; the v2 rerankers cover 100+ languages, including Russian.
A different search principle: every word of the question is compared with every word of the document, not the two texts as a whole. The index is heavier than with ordinary embeddings. The model cards list English.
A reranker for document pages as images: after a visual search it reorders the found pages by how well they answer the question. The card does not state the languages.
Rerankers: they take passages found by search and reorder them by how well they actually match the question. v2-m3 is multilingual and lightweight, often paired with bge-m3.
Rerankers that are language models: they receive the whole list of retrieved passages and reorder it as a list, instead of scoring passages one by one. Heavier than ordinary rerankers.
An embedding-plus-reranker pair for knowledge bases. The card lists English, Chinese, Japanese and Korean — Russian is not among the stated languages.
The most downloaded open rerankers: a tiny model reads a question-passage pair and scores how well they match. The multilingual mMARCO version covers Russian.
An open model can run on your own server: data stays in-house, there is no per-request fee, and the model can be fine-tuned on your documents.
