# Alibaba — Qwen3-VL-Embedding and Qwen3-VL-Reranker: For the Next Generation of Multimodal Retrieval

- Company: Alibaba (alibaba.com)
- Announced: 2026-01-07T20:00:00+00:00
- Category: new-model
- Subject: Qwen
- Models affected: Qwen3-VL-Embedding, Qwen3-VL-Reranker, Qwen3-VL-Embedding-8B
- Source: https://qwen.ai/blog?id=qwen3-vl-embedding
- Record: https://forck.live/items/4594-qwen3-vl-embedding-and-qwen3-vl-reranker-for-the-next-generation-of-multimodal

Alibaba releases Qwen3-VL-Embedding and Qwen3-VL-Reranker, new multimodal retrieval models built on Qwen3-VL, supporting text, images, screenshots, and video. The embedding model generates semantic vectors, and the reranker provides relevance scores. The 8B embedding model achieves state-of-the-art results on MMEB-v2 benchmark.

## Evidence

Verbatim from https://qwen.ai/blog?id=qwen3-vl-embedding:

> Today, we are thrilled to announce the release of the Qwen3-VL-Embedding and Qwen3-VL-Reranker series, the newest models in the Qwen family.

---

Record: https://forck.live/items/4594-qwen3-vl-embedding-and-qwen3-vl-reranker-for-the-next-generation-of-multimodal
Catalogue: https://forck.live/llms.txt
Feed: https://forck.live/feed.md