Why would OpenAI bother serving GPT4 if customers would be just as happy with a tiny 9B model?
Check out the lmsys leaderboard. It has an overall ranking as well as ranking for specific categories.
OpenAI are also serving gpt4o mini. That said afaiu it’s not known how large/small mini is.
Being more useful than GPT3.5 is not a high bar anymore.
GPT-4o is a much better experience than the smaller local models. You can see that in the lmarena benchmarks or from trying them out yourself.
Why would OpenAI bother serving GPT4 if customers would be just as happy with a tiny 9B model?