ModelLLMsv1.0

BGE-M3

by BAAI · open-source · Last verified 2026-03-17

BAAI's versatile embedding model supporting multi-linguality, multi-functionality, and multi-granularity. Handles dense, sparse, and ColBERT-style retrieval in a single model across 100+ languages.

https://huggingface.co/BAAI/bge-m3 ↗

C+

C+—Average

Adoption: BQuality: AFreshness: BCitations: C+Engagement: F

Specifications

License: MIT
Pricing: open-source
Capabilities: embedding, semantic-search, multilingual-embedding, hybrid-retrieval, colbert-retrieval
Integrations: huggingface, langchain, llama-index, milvus
Use Cases: multilingual-search, cross-lingual-retrieval, hybrid-search, document-retrieval
API Available: No
Parameters: 568M
Context Window: 8K tokens
Modalities: text
Training Cutoff: Late 2023
Tags: embedding, multilingual, open-source, hybrid-retrieval, baai
Added: 2026-03-17
Completeness: 93%

Index Score

55.3

Adoption

Quality

Freshness

Citations

Engagement

Explore the full AI ecosystem on Agents as a Service