Jina Reranker V3
jinaai/jina-reranker-v3
published Sep 2025 · updated Mar 2026
Jina Reranker V3 is a 0.6B parameter multilingual listwise document reranker that uses a novel last but not late interaction architecture to achieve state-of-the-art retrieval performance.
specs
| Task | Document Reranking |
| Architecture | Last but not late interaction (causal self-attention between query and documents) |
| Parameters | 0.6B total (0.44B non-embedding) |
| License | CC BY-NC 4.0 |
about this model
jinaai/jina-reranker-v3 is a 0.6B parameter multilingual listwise document reranker that uses a novel "last but not late interaction" architecture. Unlike late interaction models such as ColBERT which encode documents separately before multi-vector matching, this model applies causal self-attention between the query and all candidate documents within the same context window, extracting contextual embeddings from the last token of each document. This enables rich query-document interactions while keeping computational costs low.
Built on Qwen3-0.6B with 28 transformer layers and a lightweight MLP projector (1024→512→256 dimensions), the model processes up to 64 documents simultaneously within a 131K token context. Its 0.44B non-embedding parameters contribute to efficient inference while delivering state-of-the-art retrieval quality. On the BEIR benchmark, it achieves 61.94 nDCG@10 outperforming larger rerankers while being roughly 10× smaller than generative listwise models. The model maintains stable performance across different input document orderings, demonstrating robustness to permutation.
Multilingual capabilities are evaluated across 18 languages on MIRACL and 26 languages on MKQA, with scores of 66.83 and 67.92 respectively.
| Model | Size | BEIR | MIRACL | MKQA | CoIR |
|---|---|---|---|---|---|
| jina-reranker-v3 | 0.6B | 61.94 | 66.83 | 67.92 | 70.64 |
| jina-reranker-v2 | 0.3B | 57.06 | 63.65 | 67.90 | 56.14 |
| jina-reranker-m0 | 2.4B | 58.95 | 66.75 | 68.19 | 63.55 |
| bge-reranker-v2-m3 | 0.6B | 56.51 | 69.32 | 67.88 | 36.28 |
| mxbai-rerank-base-v2 | 0.5B | 58.40 | 55.32 | 64.24 | 65.71 |
| mxbai-rerank-large-v2 | 1.5B | 61.44 | 57.94 | 67.06 | 70.87 |
| Qwen3-Reranker-0.6B | 0.6B | 56.28 | 57.70 | 65.34 | 65.18 |
| Qwen3-Reranker-4B | 4.0B | 61.16 | 67.52 | 67.52 | 73.91 |
| jina-code-embeddings-0.5b | 0.5B | - | - | - | 73.94 |
This model is hosted as a managed, OpenAI-compatible API on gigarouter. For further technical details, see the arXiv paper.
best for
- ·Multilingual document retrieval and reranking across 18+ languages
- ·Improving search result relevance in RAG pipelines
- ·Listwise reranking of up to 64 documents in a single pass
FAQ
The API accepts a query string and a list of document strings via a POST request to the OpenAI-compatible endpoint, using your gigarouter API key.
At 0.6B parameters, it is 10x smaller than generative listwise rerankers while achieving state-of-the-art BEIR performance (61.94 nDCG@10).
The model is licensed under CC BY-NC 4.0. Commercial use requires contacting Jina AI.
It can process up to 64 documents simultaneously within a 131K token context window.
It supports multilingual retrieval, with strong performance on BEIR (English), MIRACL (18 languages), and MKQA (26 languages).
We're benchmarking and onboarding Jina Reranker V3 as a hosted, OpenAI-compatible API. Sign in for free credit and be ready when it lands, or tell us you want it and we'll prioritize it.