this post was submitted on 08 Aug 2025
5 points (69.2% liked)

Large Language Models

245 readers
1 users here now

A place to discuss large language models.

Rules

  1. Please tag [not libre software] and [never on-device] services as such (those not green in the License column here).
  2. Be useful to others

Resources

github.com/ollama/ollama
https://github.com/danny-avila/LibreChat
github.com/Aider-AI/aider
wikipedia.org/wiki/List_of_large_language_models

founded 2 years ago
MODERATORS
 

Since openai removed access to 4.5, I am looking for something comparable from any other company.

Personally, I used it when 4o was not good enough. 4.5 was way better at research and doing more complex programming tasks.

What is comparably good in your experience?

you are viewing a single comment's thread
view the rest of the comments
[–] Electricd@lemmybefree.net 2 points 1 month ago

I have a suite of tests that I run to compare AI quality for “problems” that I use it for that actually came up in real life. Not synthetic benchmarks that might mean nothing for my usecase.

Yea, the best way to know is to input things you would really try

Recently discovered https://lmarena.ai/ and sometimes I try a prompt that isn't personal or sensitive, and check how the different models do. Allows me to find the best (or less bad) one