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.
about this model
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
| Property | Value |
|---|---|
| Parameters | 8B |
| Context Length | 32K |
| Input Modalities | Text, image, screenshot, video, mixed |
| Languages | 30+ |
| Instruction Aware | Yes |
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.
| Model | Size | MMEB-v2 (Retrieval) - Avg | MMEB-v2 - Image | MMEB-v2 - Video | MMEB-v2 - VisDoc | MMTEB | JinaVDR | ViDoRe v3 |
|---|---|---|---|---|---|---|---|---|
| Qwen3-VL-Embedding-2B | 2B | 73.4 | 74.8 | 53.6 | 79.2 | 68.1 | 71.0 | 52.9 |
| jina-reranker-m0 | 2B | - | 68.2 | - | 85.2 | - | 82.2 | 57.8 |
| Qwen3-VL-Reranker-2B | 2B | 75.1 | 73.8 | 52.1 | 83.4 | 70.0 | 80.9 | 60.8 |
| Qwen3-VL-Reranker-8B | 8B | 79.2 | 80.7 | 55.8 | 86.3 | 74.9 | 83.6 | 66.7 |
For detailed benchmark evaluation, hardware requirements, and inference performance, see the technical report, blog, and GitHub repository.
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.