TAAFT
Free mode
100% free
Freemium
Free Trial
Deals

BGE Reranker large

BGE Reranker large is the 560M flagship in BAAI’s first reranker series. The docs explain that rerankers take a question and document together and directly output similarity, which makes them useful for reranking candidates retrieved by simpler embedding models. This model is built on XLM-RoBERTa-Large, supports English and Chinese, is listed at 2.24 GB, and is positioned as the higher-accuracy first-generation BGE reranker.
Text Gen 7
Released: September 12, 2023

Overview

BGE Reranker large is BAAI’s larger first-generation cross-encoder reranker for English and Chinese. Instead of producing embeddings, it scores a query-document pair directly, making it suitable for reranking top-k retrieval results with higher accuracy after a first-pass embedder search.

About Beijing Academy of Artificial Intelligence (BAAI)

Beijing Academy of Artificial Intelligence (BAAI), also known as Zhiyuan Institute, is a Chinese non-profit AI research laboratory established in November 2018. BAAI conducts fundamental AI research, develops open-source models (including WuDao, BGE embeddings, Emu, and RoboBrain), and fosters collaboration between academia and industry. Known for creating the BGE (BAAI General Embedding) series of embedding models used in RAG systems worldwide.

Industry: Research
Company Size: 260
Location: Beijing, Beijing, CN
Website: baai.ac.cn
View Company Profile

Tools using BGE Reranker large

No tools found for this model yet.

Last updated: April 16, 2026
0 AIs selected
Clear selection
#
Name
Task