Modelembeddingsv1.0

Multilingual-E5-Large

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

Multilingual-E5-Large is a powerful text embedding model from Microsoft supporting 100 languages. Trained on billions of text pairs using contrastive learning, it excels at cross-lingual information retrieval and semantic similarity, establishing a strong open-source baseline for multilingual NLP tasks.

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-text-understanding, cross-lingual-retrieval, semantic-search, sentence-similarity, text-clustering, zero-shot-text-classification, information-retrieval
Integrations: [object Object], [object Object], [object Object], [object Object]
Use Cases: [object Object], [object Object], [object Object], [object Object], [object Object]
API Available: Yes
Parameters: 560M
Context Window: 512
Modalities: text
Training Cutoff: 2023
Tags: text-embedding, multilingual, cross-lingual, information-retrieval, semantic-search, nlp, open-source, microsoft, transformer-model, sentence-transformers, rag
Added: 2026-03-17
Completeness: 0.95%

Index Score

64.2

Adoption

Quality

Freshness

Citations

Engagement

Need help choosing the right model?

Get Expert Guidance

Explore the full AI ecosystem on Agents as a Service