Google AI ModeJul 28, 2026
Multilingual E5 Large (intfloat/multilingual-e5-large-instruct): A top-tier open-source model optimized for semantic search
Data as of Oct 14, 2026Based on 33,941 AI responses
Reviewed by Dimitry Apollonsky
intfloat/e5-base is a text-embedding model trained with weakly-supervised contrastive pre-training that produces 768-dimensional sentence embeddings for tasks like semantic similarity and passage retrieval. It is designed for use with the Hugging Face ecosystem and can be accessed via the sentence-transformers library or raw Transformers, with examples showing how to encode queries and passages and compute similarities. The documentation notes that users should switch to e5-base-v2 for better performance while preserving the same usage.
Hosted on Hugging Face
<1%
of 33,941 answers across Multilingual E5 Large’s markets · since Jul 5
The market map
Embedding Model APIs and ServicesMentioned in
Share of answers in Embedding Model APIs and Services each week · 345 answers since Jul 5
Each engine’s share of its own answers across Multilingual E5 Large’s markets · since Jul 5
Where Multilingual E5 Large ranks in AI
huggingface.co 11%Other sites 89%
Excerpts where Multilingual E5 Large appeared in the AI's answer
Multilingual E5 Large (intfloat/multilingual-e5-large-instruct): A top-tier open-source model optimized for semantic search