Data as of Aug 16, 2026 · Based on 3,131,739 AI responses across 10,525 prompts · See how Parse measures this
intfloat/e5-small-v2huggingface.coE5 base v2 is a text embedding model with 12 layers and a 768-dimensional embedding size, trained using weakly supervised contrastive pre-training. It requires input texts to be prefixed with "query: " or "passage: " for optimal performance in tasks like passage retrieval and semantic similarity.
Sources
dev.to shapes more of what AI says about intfloat/e5-small-v2 than any other source, at 33% of its citations.
research.aimultiple.com · supermemory.ai
The market map
Embedding Model APIs and Services →Where AI ranks intfloat/e5-small-v2
