# Gpt-3.5-turbo-1106 performance

**URL:** <https://community.openai.com/t/gpt-3-5-turbo-1106-performance/616666>\
**Category:** API\
**Tags:** embeddings, gpt-4, llm, rag, assistants-api\
**Created:** [February 6, 2024, 3:40pm UTC](https://community.openai.com/t/gpt-3-5-turbo-1106-performance/616666 "2024-02-06T15:40:49Z")\
**Posts on this page:** 1\
**Showing post:** 3

<div class="post-metadata">

**Author:** ![SomebodySysop](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/somebodysysop/32/17613_2.png) [@SomebodySysop](https://community.openai.com/u/SomebodySysop)\
**Post date:** [February 6, 2024, 11:56pm UTC](https://community.openai.com/t/gpt-3-5-turbo-1106-performance/616666/3 "2024-02-06T23:56:13Z")

</div>

> [@nikitamobile](#):
>
> The LLM replies became quite less relevant.

I have made several posts about this issue. gpt-3.5-turbo-16k is far less capable than gpt-4 and sometimes seems incapable of accurately reading returned documents. I have documented cases where, given the exact same question and context documents, gpt-3.5-turbo-16k fails to even recognize the answer in the documents where gpt-4 responds perfectly.

I doubt that it is the vector search results as they won’t be affected by the LLM.

This was way back in June 2023: [Gpt-3.5-turbo-16k api not reading context documents](https://community.openai.com/t/gpt-3-5-turbo-16k-api-not-reading-context-documents/290663)

However, I was able to eventually get much better results from the gpt-3.5 model by using xml markup in my prompt: [API Prompt for gpt-3.5-turbo-16k - #12 by SomebodySysop](https://community.openai.com/t/api-prompt-for-gpt-3-5-turbo-16k/578556/12)

I know your question was about ‘gpt-3.5-turbo-1106, but my understanding is that gpt-3.5-turbo-16k is an alias for that model. Somebody let me know if that is incorrect.

---

_[View the full topic](https://community.openai.com/t/gpt-3-5-turbo-1106-performance/616666)._