[Models](/models)/[Reranking](/models?category=reranking)/jinaai/jina-reranker-v3

HFRerankingcc-by-nc-4.0

# jina-reranker-v3

by jinaai

Compact Qwen3-based reranker for multilingual text retrieval precision

815Kdl/month

144likes

597Mparams

[HuggingFace](https://huggingface.co/jinaai/jina-reranker-v3)[Run it on your own data, free](https://studio.mixpeek.com/namespaces/create?mode=managed&utm_source=homepage&utm_medium=model_page&utm_campaign=mvs_onramp)

Identifiers

Model ID

`jinaai/jina-reranker-v3`

## Deploy jina-reranker-v3

Single-tenant

Mixpeek has no managed extractor for this model. On a single-tenant deployment you upload the weights and a custom plugin serves them next to the rest of your pipeline.

[Read the customer-hosted guide](https://mixpeek.com/docs/customer-hosted/overview) [Talk to us about single-tenant](/demo)

## Overview

Jina Reranker v3 is a production text-ranking model from Jina AI built on Qwen3-0.6B. It is useful as a second-stage reranker after dense, sparse, or hybrid retrieval, especially when agents need cleaner evidence from transcripts, OCR spans, documents, and other text-heavy payloads.

On Mixpeek, Jina Reranker v3 fits after a broad first-stage search. Retrieve a larger candidate set with embeddings, BM25, or hybrid search, then rerank the candidates before sending compact evidence to an agent. This is particularly useful when a video or document pipeline has many short evidence spans that look similar in embedding space.

## Architecture

Transformer cross-encoder text-ranking model based on Qwen3-0.6B. The model scores query and document pairs directly, so inference cost scales with the number of candidate pairs reranked.

## Mixpeek SDK Integration

IngestRetrieve

// Reranking is a retriever STAGE in Mixpeek, not an ingest-time extractor.
// The rerank stage runs a cross-encoder inference service; the shipped default
// is BAAI/bge-reranker-v2-m3. Pointing it at jina-reranker-v3 means registering that
// model as a custom reranker plugin and naming it in feature\_uri, which is an
// Enterprise path. Stage contract read from GET /v1/discovery/stages.
const retriever = await mx.retrievers.create({
  namespace\_id: "my-namespace",
  retriever\_name: "search-then-rerank",
  stages: \[
    {
      stage\_name: "candidates",
      stage\_id: "feature\_search",
      parameters: { limit: 100 },
    },
    {
      stage\_name: "rerank\_results",
      stage\_id: "rerank",
      parameters: {
        inference\_name: "BAAI\_\_bge\_reranker\_v2\_m3",
        query: "{{INPUT.query}}",
        document\_field: "content",
        top\_k: 10,
      },
    },
  \],
});

## Capabilities

*   Second-stage reranking for dense, sparse, and hybrid candidate sets
*   Multilingual text-ranking model based on Qwen3-0.6B
*   Useful for transcript, OCR, caption, and document span precision
*   Compact 596M-parameter footprint compared with larger rerankers
*   Works well as the precision stage before agent context assembly

## Use Cases on Mixpeek

Rerank transcript spans from video and audio search before an agent answers

Rerank OCR blocks from screenshots, PDFs, and slide decks

Improve precision for hybrid search over support tickets, docs, and media captions

Select the best evidence packets before payload projection and citation generation

## Benchmarks

Dataset

Metric

Score

Source

Hugging Face

Pipeline tag

text-ranking

Jina AI, 2026 Model Card

Hugging Face

Base model

Qwen3-0.6B

Jina AI, 2026 Model Card

Hugging Face

Parameters

596M

Jina AI, 2026 Model Card

## Performance

Input SizeText query and candidate text pairs

GPU LatencyScales with reranked candidate count

GPU ThroughputUse after top-K candidate generation

GPU MemoryCompact 596M-parameter reranker

## Common Pipeline Companions

[

BAAI/bge-m3

Dense and sparse first-stage retrieval

](/model/BAAI/bge-m3)[

Qwen/Qwen3-Embedding-0.6B

Compact text embedding first stage

](/model/Qwen/Qwen3-Embedding-0.6B)[

jinaai/jina-reranker-m0

Multimodal reranking when candidates include images or mixed documents

](/model/jinaai/jina-reranker-m0)

## Explore on Mixpeek

[

More Reranking models

Compare alternatives in this category

](/models?category=reranking)[

Best Hybrid Search Engines

Hand-picked tools & platforms compared

](/curated-lists/best-hybrid-search-engines)[

Cross-Encoder Reranking

Deep-dive technical guide

](/guides/cross-encoder-reranking)[

Feature Extractors

See how Mixpeek runs models as extractors

](/extractors)[

Mixpeek Vector Store

Store & search embeddings at scale

](/mvs)[

Pricing

Usage-based pricing for pipelines

](/pricing)[

All Curated Lists

Compare models, APIs & infrastructure

](/curated-lists)

### Specification

FrameworkHF

Organizationjinaai

FeatureReranking

OutputRelevance score per candidate

Modalities

RetrieverCross-Modal Reranker

Parameters597M

Licensecc-by-nc-4.0

Downloads/mo815K

Likes144

[

### Research Paper

Jina Reranker v3

arxiv.org](https://huggingface.co/jinaai/jina-reranker-v3)

### Build a pipeline with jina-reranker-v3

Add this model to a processing pipeline alongside other extractors. Combine with retrieval stages for end-to-end search.

[Run it on your own data, free](https://studio.mixpeek.com/namespaces/create?mode=managed&utm_source=homepage&utm_medium=model_page&utm_campaign=mvs_onramp)

### Alternative Models

[

Qwen/Qwen3-VL-Reranker-2B

Reranking

](/model/Qwen/Qwen3-VL-Reranker-2B)[

Qwen/Qwen3-VL-Reranker-8B

Reranking

](/model/Qwen/Qwen3-VL-Reranker-8B)[

nvidia/llama-nemotron-rerank-1b-v2

Reranking

](/model/nvidia/llama-nemotron-rerank-1b-v2)[

nvidia/llama-nemotron-rerank-vl-1b-v2

Reranking

](/model/nvidia/llama-nemotron-rerank-vl-1b-v2)