Model Terminal

BGE Reranker v2-M3

BGE Reranker v2-M3 is a multilingual cross-encoder reranker model from BAAI that scores query-passage relevance pairs to reorder candidate results in search and RAG pipelines. It is lightweight and optimized for fast inference while retaining the multilingual coverage of the BGE-M3 family. Source: supabase.

Value score
Not scored
Context
tokens
Max output
tokens
Price

Capability radar

Peer value bars

Identity

Developer
Hugging Face
Openness
Modalities
Text-classification
Release
Knowledge cutoff
Deprecation
API docs

Benchmarks

No benchmark scores yet.

Compare nearby

Pricing

Input / 1M
Output / 1M
Speed