BGE Large EN v1.5
bge-large-en-v1.5
About
BGE Large EN v1.5 is BAAI's high-performance English embedding model, producing 1,024-dimensional dense vectors. It ranked 1st on the MTEB leaderboard at release with an average score of 64.23 across 56 tasks. Version 1.5 addresses similarity distribution issues from earlier releases, improving retrieval quality even when query instructions are omitted. Based on BERT-large architecture.
BGE Large EN v1.5 has a 512-token context window.
Capabilities
VisionMultimodalReasoningFunction CallingTool UseStructured OutputsCode Execution
