text-embedding-3-large
text-embedding-3-large is a high-dimensional text embedding model released by OpenAI. It outputs 3072-dimensional vectors and achieves the strongest embedding quality among the models compared.
Timeline (last 90 days)
After projecting three competitor copy samples into 1536-dimensional space using text-embedding-3-large, cosine similarity typically falls between 0.91 and 0.94.
OpenAI's text-embedding-3-large returns 3072-dimensional vectors by default, while pgvector's HNSW can index halfvec up to 4000 dimensions.
text-embedding-3-large嵌入模型为3072维，成本为$0.13/百万token
All Facts (3)
After projecting three competitor copy samples into 1536-dimensional space using text-embedding-3-large, cosine similarity typically falls between 0.91 and 0.94.
50%UnverifiedOpenAI's text-embedding-3-large returns 3072-dimensional vectors by default, while pgvector's HNSW can index halfvec up to 4000 dimensions.
50%Unverifiedtext-embedding-3-large嵌入模型为3072维，成本为$0.13/百万token
50%