Alibaba open sources new version Qwen3 model, dominating text representation.

This morning, Alibaba open-sourced two new models in the Qwen3 series, Qwen3-Embedding and Qwen3-Reranker. These two models are designed for text representation, retrieval, and ranking tasks, based on the Qwen3 base model training, fully inheriting the advantages of Qwen3 in multilingual text understanding, supporting 119 languages. According to test data, Qwen3 Embedding performs very well in multilingual text representation benchmark tests. In particular, the 8B parameter ranks first with a high score of 70.58, surpassing many commercial API services, such as Google's Gemini-Embedding.