# Cross-lingual retrieval

The Qwen3 Embedding model series is the latest self-developed model of the Tongyi family, designed specifically for text embedding and ranking tasks, supporting more than 100 languages, and ranking first on the MTEB multilingual leaderboard.

The Multilingual e5 Large Instruction Model supports multiple languages and performs excellently in various tasks such as classification, retrieval, and clustering. It can be widely applied in various natural language processing scenarios.

Jina Embeddings V3 is a multilingual sentence embedding model supporting over 100 languages, focusing on sentence similarity calculation and feature extraction tasks.

Snowflake Arctic Embed M v2.0 is a multilingual sentence embedding model focused on sentence similarity tasks, supporting over 50 languages.

This is a multilingual sentence embedding model that maps text to a 512-dimensional vector space, suitable for semantic search and clustering tasks.

LaBSE is a BERT-based multilingual sentence embedding model that supports 109 languages, suitable for sentence similarity calculation and bilingual text retrieval.

A streamlined version of the LaBSE model specialized for English and Russian, significantly reducing model size while preserving original embedding quality