Skip to content
Why did we open-source our inference engine? Read the post

Reranker Models

Supported Models

Section titled “Supported Models”
ModelMax LengthNotes
BAAI/bge-reranker-v2-m38192Multilingual
jinaai/jina-reranker-v2-base-multilingual8192Multilingual
Alibaba-NLP/gte-reranker-modernbert-base8192ModernBERT architecture
cross-encoder/ms-marco-MiniLM-L-12-v2512Smaller, faster

See Full model catalog for the complete list.

Model Selection

Section titled “Model Selection”

By Language Support

Section titled “By Language Support”

English only:

  • BAAI/bge-reranker-base, BAAI/bge-reranker-large
  • cross-encoder/ms-marco-MiniLM-L-6-v2, cross-encoder/ms-marco-MiniLM-L-12-v2

Multilingual (100+ languages):

  • BAAI/bge-reranker-v2-m3
  • jinaai/jina-reranker-v2-base-multilingual
  • jinaai/jina-colbert-v2

By Context Length

Section titled “By Context Length”

Short context (512 tokens):

  • BAAI/bge-reranker-base, BAAI/bge-reranker-large
  • cross-encoder/ms-marco-MiniLM-L-*
  • colbert-ir/colbertv2.0, mixedbread-ai/mxbai-colbert-large-v1

Long context (8192 tokens):

  • BAAI/bge-reranker-v2-m3
  • jinaai/jina-reranker-v2-base-multilingual
  • Alibaba-NLP/gte-reranker-modernbert-base
  • mixedbread-ai/mxbai-rerank-base-v2, mixedbread-ai/mxbai-rerank-large-v2
  • jinaai/jina-colbert-v2, lightonai/GTE-ModernColBERT-v1, lightonai/Reason-ModernColBERT

By Size

Section titled “By Size”

Compact (fast inference):

  • cross-encoder/ms-marco-MiniLM-L-6-v2 — smallest cross-encoder
  • mixedbread-ai/mxbai-edge-colbert-v0-32m — 32M parameters
  • answerdotai/answerai-colbert-small-v1 — compact ColBERT

Large (higher capacity):

  • BAAI/bge-reranker-large
  • mixedbread-ai/mxbai-rerank-large-v2
  • mixedbread-ai/mxbai-colbert-large-v1
  • lightonai/Reason-ModernColBERT — long context (8192), ModernBERT family
  • nvidia/llama-nemoretriever-colembed-3b-v1 — 3B parameters

Benchmarking

Section titled “Benchmarking”

Use the eval harness to benchmark rerankers on your data:

Terminal window
# Quality evaluation
mise run eval BAAI/bge-reranker-v2-m3 -t mteb/AskUbuntuDupQuestions --type quality


# Performance evaluation
mise run eval BAAI/bge-reranker-v2-m3 -t mteb/AskUbuntuDupQuestions --type perf


# Compare multiple models
mise run eval BAAI/bge-reranker-base -t mteb/AskUbuntuDupQuestions --type quality
mise run eval cross-encoder/ms-marco-MiniLM-L-12-v2 -t mteb/AskUbuntuDupQuestions --type quality

What’s Next

Section titled “What’s Next”