#Extract the idea and question - 000026

1 messages · Page 1 of 1 (latest)

flint pike
#

For the following text, summarize the idea,
extract meaningful questions and give possible answers.

Is there a performance difference between text-embedding-3-small @ 1536 length and text-embedding-3-large @ 1536 length?
loud dragonBOT
#

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.

In terms of specific performance metrics, the text-embedding-3-large model has an example performance of 64.6% on the MTEB (https://github.com/embeddings-benchmark/mteb) evaluation, while the text-embedding-3-small model has a performance of 62.3%. Therefore, the text-embedding-3-large model performs slightly better than the text-embedding-3-small model.

Note: you can ask me a follow up question by @ mentioning me again :speech_balloon: