Model
OpenAI text-embedding-3-large
A text embedding model released by OpenAI that outputs 3072-dimensional vectors. It is the large version of the text-embedding-3 series, used for higher-precision semantic retrieval.
Timeline (last 90 days)
Oct 13
Different embedding models have different output dimensions: paraphrase-multilingual-MiniLM-L12-v2 is 384 dimensions, the BERT-base series is 768 dimensions, OpenAI text-embedding-3-small is 1536 dimensions, and text-embedding-3-large and Google gemini-embedding-001 are 3072 dimensions.
Unverified50%