tech
December 3, 2025
Jina Reranker v3: 0.6B Listwise Reranker for SOTA Multilingual Retrieval
We're excited to release jina-reranker-v3, our latest-generation reranker that delivers state-of-the-art performance across multilingual retrieval benchmarks. This 0.6B-parameter document reranker introduces a novel last but not late interaction that takes a fundamentally different approach from existing methods. jina-reranker-v3 works listwise: it applies causal attention between the query and all candidate documents within a single context window, enabling rich cross-document interactions before extracting contextual embeddings from each document's final token. Our new model achieves 61.94 nDCG@10 on BEIR outperforming Qwen3-Reranker-4B while being 6× smaller in size.
TL;DR
- jina-reranker-v3 is a 0.6B parameter multilingual document reranker.
- It introduces a novel 'last but not late' interaction mechanism.
- The model processes the query and all candidate documents within a single context window.
- It achieves state-of-the-art performance on the BEIR benchmark with 61.94 nDCG@10.
- The reranker shows robust performance regardless of input document order.
- It exhibits cross-lingual consistency across 18 diverse languages.
- Available via API and the `transformers` library.
Continue reading
the original article