Jina Reranker
Jina AIJina AI's reranker line, from the v1 turbo and tiny English cross-encoders through v2-base-multilingual to the v3 and v3.5 listwise rerankers. v3 is a 0.6B Qwen3-derived model with a "last but not late interaction" architecture that attends across query and up to 64 documents inside one 131K-token window, reporting 61.94 nDCG@10 on BEIR. The weights are published on the Hub, but under a non-commercial licence.
Added 2026-09-11 for the embeddings_retrieval promotion. Scope is the TEXT line: the m0 multimodal reranker is excluded on every axis under the category's rule that a vision-language line is a separate product from the text line, matching how jina-embeddings treats v4 and v5-omni. The licence is the thing to read carefully - the v2, v3 and v3.5 cards all read cc-by-nc-4.0 and v3's own licence section says commercial use outside AWS and Azure needs a separate conversation, while the older v1-turbo-en and v1-tiny-en are Apache-2.0. The most restrictive distributed SKU governs. Verified 2026-09-11 via the jina-reranker-v3 model card.
Openness
2 high confidence- weights
- open(ungated safetensors on the Hub for v1 through v3.5)
- data
- closed(no training data or construction scripts released)
- code
- partial(remote inference code shipped with the card
- license
- Apache-2.0(OSI, and only the superseded v1-turbo-en and v1-tiny-en)+CC-BY-NC-4.0(non-commercial
The current SKUs are licensed CC-BY-NC-4.0 and the superseded v1-turbo-en and v1-tiny-en are Apache-2.0, so the compound resolves on the non-commercial half. commercial_forbidden asks one question - does the licence permit commercial use at all - and the card answers no, saying commercial use beyond AWS and Azure requires contacting sales. The m0 multimodal reranker is excluded from this record on every axis under the category's vision-language rule; it reads cc-by-nc-4.0 as well, so its exclusion moves nothing here.
- https://huggingface.co/jinaai/jina-reranker-v3/raw/main/README.md recorded 2026-09-11
Front matter reads license: cc-by-nc-4.0; the License section says the model is licensed under CC BY-NC 4.0 for use beyond the AWS and Azure listings and directs commercial usage inquiries to contact sales. Weights are ungated, inference is via trust_remote_code with no training pipeline or corpus named.
- https://huggingface.co/api/models/jinaai/jina-reranker-v2-base-multilingual recorded 2026-09-11
license cc-by-nc-4.0 recorded in cardData for jinaai/jina-reranker-v2-base-multilingual, confirming the non-commercial terms are not unique to v3.
Adoption
4 high confidenceAbout 2.0M downloads in the trailing 30 days across the text line - v2-base-multilingual 1.16M, v3 780K, v3.5 32K, plus the two v1 checkpoints. The v2 and v3 figures alone clear the 1M band. The m0 multimodal reranker is excluded under the category's rule that a vision-language line is a separate product from the text line; counting its 379K gives about 2.4M and the same band.
- https://huggingface.co/api/models/jinaai/jina-reranker-v2-base-multilingual recorded 2026-09-11
downloads: 1155086; gated: false; private: false for jinaai/jina-reranker-v2-base-multilingual.
- https://huggingface.co/api/models/jinaai/jina-reranker-v3 recorded 2026-09-11
downloads: 780543; gated: false; private: false for jinaai/jina-reranker-v3.
Capability
4 high confidenceRung 4, competitive frontier. Level with qwen3-reranker: 61.94 BEIR against Qwen3-Reranker-4B at 61.16 on the same table, at a sixth of the parameters, and multilingual with a long context in both cases. Note the numbers come from the publisher own card, which is the instrument available for this product and is why the comparison is drawn against a peer scored from the same table.
- https://huggingface.co/jinaai/jina-reranker-v3/raw/main/README.md recorded 2026-09-11
Card reports jina-reranker-v3 at 61.94 BEIR, 66.83 MIRACL, 67.92 MKQA and 70.64 CoIR at 0.6B parameters, in a table that also lists Qwen3-Reranker-4B at 61.16 BEIR and bge-reranker-v2-m3 at 56.51; describes 64 documents within a 131K context window.
Verified 2026-09-11