#Extract the idea and question - 000026
1 messages · Page 1 of 1 (latest)
Hi @flint pike. I'm kapa.ai, your friendly support bot. I will try to answer your question by searching through the knowledge base. :wave:
Idea Summary:
The user is inquiring about the performance difference between two of OpenAI's third-generation embedding models: text-embedding-3-small and text-embedding-3-large. Both models have an output dimension of 1536.
Extracted Question:
Is there a performance difference between text-embedding-3-small and text-embedding-3-large, both having an output dimension of 1536?
Possible Answer:
Yes, there is a performance difference between the two models. According to the documentation (https://platform.openai.com/docs/guides/embeddings), the text-embedding-3-large model is the most capable embedding model for both English and non-English tasks, while the text-embedding-3-small model offers increased performance over the second-generation ada embedding model.