Re:30% Drop In o1-Preview Accuracy When Putnam Problems Are ...
by dialup_sounds on Wednesday January 01, 2025 @11:45AM
(#42567155)
I believe this is just a case of OpenAI's naming scheme being weird and confusing.
The default model I see on chatgpt.com is GPT 4o-mini, which is not o1-mini.
OpenAI describes GPT 4o-mini as "Our fast, affordable small model for focused tasks" and o1/o1-mini as "Reasoning models that excel at complex, multi-step tasks".
The default model I see on chatgpt.com is GPT 4o-mini, which is not o1-mini.
OpenAI describes GPT 4o-mini as "Our fast, affordable small model for focused tasks" and o1/o1-mini as "Reasoning models that excel at complex, multi-step tasks".