skip to content
gigarouter gigarouter
models / reranker · coming soon

Qwen3-VL-Reranker-8B

Qwen/Qwen3-VL-Reranker-8B

A popular open reranker model, with 431K downloads a month. gigarouter benchmarks and hosts it as an OpenAI-compatible API.

est. price
~$0.008
/ 1k docs · estimated, set at launch
API providers
0
downloads / mo
431K
license
apache-2.0

about this model

Qwen3-VL-Reranker-8B

The Qwen3-VL-Reranker-8B is a multimodal reranker built on the Qwen3-VL foundation model. It accepts diverse inputs — text, images, screenshots, videos, or any mixture of these — and outputs a precise relevance score for a (query, document) pair. In a two-stage retrieval pipeline, the embedding model performs initial recall, then the reranker refines results to significantly boost retrieval accuracy.

Key Strengths

  • High-Precision Reranking: Designed for multimodal retrieval refinement, delivering state-of-the-art performance across image-text, video-text, visual document, and cross-lingual tasks.
  • Multimodal Versatility: Handles single or mixed modalities in both query and document, including text, images, screenshots, and video.
  • Multilingual Support: Supports over 30 languages, making it suitable for global applications.
  • Instruction Aware: Supports custom instructions per task; using tailored instructions typically improves results by 1%–5% (English recommended).

Specifications

PropertyValue
Parameters8B
Context Length32K
Input ModalitiesText, image, screenshot, video, mixed
Languages30+
Instruction AwareYes

Benchmark Performance

Evaluated on retrieval tasks from MMEB-v2, MMTEB, JinaVDR, and ViDoRe v3. The 8B reranker consistently outperforms the base embedding model and baseline rerankers.

ModelSizeMMEB-v2 (Retrieval) - AvgMMEB-v2 - ImageMMEB-v2 - VideoMMEB-v2 - VisDocMMTEBJinaVDRViDoRe v3
Qwen3-VL-Embedding-2B2B73.474.853.679.268.171.052.9
jina-reranker-m02B-68.2-85.2-82.257.8
Qwen3-VL-Reranker-2B2B75.173.852.183.470.080.960.8
Qwen3-VL-Reranker-8B8B79.280.755.886.374.983.666.7

For detailed benchmark evaluation, hardware requirements, and inference performance, see the technical report, blog, and GitHub repository.

not yet live

We're benchmarking and onboarding Qwen3-VL-Reranker-8B 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.