BGE-M3
BAAI multi-granularity multilingual embedding with dense + sparse
Verdict
Unique hybrid model supporting dense, sparse, and ColBERT retrieval in one model. 100+ languages, 8K context. Best open-source choice for multilingual RAG systems.
Other Embedding Models
- text-embedding-3-largeProduction
OpenAI's most capable embedding model with 3072 dimensions
- Gemini EmbeddingProduction
Google's unified embedding model — topped the MTEB multilingual leaderboard at launch
- Cohere Embed v3Production
Multilingual embedding model optimised for search and RAG
- Voyage AI 3Production
Specialised embeddings for code, legal, finance, and multilingual
- E5-Mistral-7BStable
Large LLM-based embedding model for maximum retrieval quality
- Jina Embeddings v3Stable
8K context multilingual embedding with task-specific LoRAs