Simon P. Couch @simonpcouch.com · Apr 15

New on my blog: OpenAI dropped a trio of models yesterday that they claim result from "focusing closely on real-world developer needs." I was curious whether this might mean stronger #rstats coding performance. www.simonpcouch.com/blog/2025-04...

71 likes 5 replies

?

Replies

Sharon Machlis · Apr 15

Alas Sonnet is more expensive than all the OpenAI GPT 4x LLMs.

Johannes Schwenke · Apr 15

Time to compare Gemini 2.5 Pro ?

Jase Gehring · May 11

do you have issues controlling Sonnet 3.7? i usually use the chat interface for convenience. it goes HAM and one-shots 3 pages of code when i'd rather work step-by-step. i am the user and i make the rules!

Dariia Mykhailyshyna · Apr 15

Thanks! Did you by any chance run it with o1, o3mini-high? From personal experience they are much better than 4o, 4.5 but I am curious how they compare to claude 3.7 sonnet and gemini 2.5