BGE Reranker Large
bge-reranker-large
About
BGE Reranker Large is a cross-encoder reranking model that scores query-passage pairs for relevance by jointly encoding them through full attention. Based on XLM-RoBERTa, it supports Chinese and English and achieves a C-MTEB reranking average of 66.09. It is designed as a second-stage ranker in retrieval pipelines: first retrieve candidates with a BGE embedding model, then re-rank with this model for higher precision.
BGE Reranker Large has a 512-token context window.
Capabilities
VisionMultimodalReasoningFunction CallingTool UseStructured OutputsCode Execution
