Modelembeddingsv1.0

Multilingual-E5-Large

by Microsoft Research · free · Last verified 2026-03-17

Multilingual-E5-Large is Microsoft's large-scale multilingual text embedding model supporting 100 languages, trained using a weakly supervised contrastive learning approach on billions of multilingual text pairs. It delivers strong cross-lingual retrieval and semantic similarity across diverse languages, making it a standard baseline for multilingual embedding benchmarks.

https://huggingface.co/intfloat/multilingual-e5-large ↗

B—Above Average

Adoption: B+Quality: AFreshness: B+Citations: B+Engagement: F

Specifications

License: MIT
Pricing: free
Capabilities: text-embeddings, multilingual, cross-lingual-retrieval, semantic-search, sentence-similarity
Integrations: Hugging Face, Sentence Transformers, LangChain, LlamaIndex
Use Cases: multilingual-search, cross-lingual-retrieval, multilingual-rag, sentence-similarity, information-retrieval
API Available: Yes
Parameters: 560M
Context Window: 512
Modalities: text
Training Cutoff: 2023
Tags: microsoft, embeddings, multilingual, open-source, retrieval
Added: 2026-03-17
Completeness: 100%

Index Score

64.2

Adoption

Quality

Freshness

Citations

Engagement

Explore the full AI ecosystem on Agents as a Service