Wharton's Ethan Mollick says GPT-5 Pro has outperformed all rivals on difficult problems since last summer
Alex Imas notes the series requires longer processing times.
GPT-5.5 Pro is the model producing many of the novel math proofs, and also the model you should have reviewing any technical or academic paper for flaws.
Ethan Mollick@emollickInteresting that the GPT-5 Pro series models have consistently been the best models for single-shot attempts at the hardest problems since last summer. There has been no real competition in all that time.
@emollick It also thinks for *a lot* longer than the other models on basically anything, which is a real cost when the problems are not particularly hard. That's why you only give it the really hard problems that need correct answers.
Ethan Mollick@emollickInteresting that the GPT-5 Pro series models have consistently been the best models for single-shot attempts at the hardest problems since last summer. There has been no real competition in all that time.