Intfloat · Embedding
E5 Large V2
IntfloatEmbeddingOpen weights. One of its sources says the weights are publicly available.
The e5-large-v2 embedding model maps English sentences, paragraphs, and documents into a 1024-dimensional dense vector space, delivering high-accuracy semantic embeddings optimized for retrieval, semantic search, reranking, and similarity-scoring tasks.
Evidence and sources
🤗 intfloat/e5-large-v2llminfo IQ 85.1, ranked among embedding models. From 153 benchmarks. Plenty of data behind it.How llminfo IQ is computedReleased 7 Dec 2022
All rankings:
#371 on OpenRouter today
#451 on OpenRouter this week
#539 on OpenRouter this monthSources: DeepInfra data, Models.dev data, Nous Portal Inference Gateway data, llminfo researchPrimary data from DeepInfra
from Models.dev: weights availability
from Nous Portal Inference Gateway: description
from llminfo research: release date
Advantages and trade-offs
Compared with 10 embedding models, picked mainly by popularity and IQ
Trade-offs
Input & output
as stated by the model's providersText
Text
Embeddings
Also known as: intfloat/e5-large-v2
Like this one. Tap or hover any dotted value, label or icon to see where it comes from and how it is measured. open details when tapped or hovered. How this data works