E5-Mistral-7B
Large LLM-based embedding model for maximum retrieval quality
Verdict
LLM-scale embedding model — 7B params delivers top MTEB scores. Task-specific prompting improves quality. Needs GPU but excels where embedding quality is critical.
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
- BGE-M3Stable
BAAI multi-granularity multilingual embedding with dense + sparse
- Jina Embeddings v3Stable
8K context multilingual embedding with task-specific LoRAs