Text Embedding 3 Large

The text-embedding-3 series represents OpenAI’s latest and most capable embedding models to date. These models are designed to generate high-quality vector representations of text, enabling superior performance across a wide range of applications such as semantic search, clustering, and recommendation systems. They deliver enhanced average multilingual retrieval performance, as demonstrated by strong results on the MIRACL benchmark, while continuing to perform well on English-language tasks, as shown on the MTEB benchmark. With improved accuracy and broader language support, text-embedding-3 is a powerful tool for building scalable, cross-lingual information retrieval and understanding systems.