@scottalanmiller said in OpenAI ChatGPT 4.1 vs 4.5 Models:

Until you spend a lot of time in technical tasks, you might not be aware of just how significantly different the output from different models can be for coding and other technical tasks where we want discrete results and not wordy soliloquies. After weeks of deep diving into using several models for technical research GPT-4.1 is a clear winner by quite a stretch. Keywords has a great breakdown of the two latest ChatGPT models, 4.1 and 4.5 and how they stack up (and why) for different tasks.

https://www.keywordsai.co/blog/gpt-41-vs-gpt-45-a-comprehensive-comparison

This is a somewhat surprising because all the recent reviews I've read or heard claim o3 and o3-mini are the best models so far at least for programming purposes. Are 4.1 and 4.5 newer than o3?