Alibaba· QwenNew model

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

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.

From the source

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.

qwen.ai

Announced

07 Jan 2026 20:00 UTC

Detected

28 Aug 2026 13:23 UTC (+232d after)