It seems they just passed the questions in, which is totally fine but I'd just add that this gives you pretty much a lower bound of performance. I think it's worse if you try and make it output very small responses, and does a lot better if it can output a lot (chain of thought). I'm continually astonished at how well gpt4 can handle problems with literally no additional work, and how much you can improve it with some small help.
Edit I asked question 1m but said it was an expert in QM and was there to explain the answer to test questions followed by answering them and it gets it right with a page or so of proof (please don't attack my use of the word proof, I'm a lay man - this also explains my failure to fix the numbering, latex editing on a phone is not my forte). I've not checked it, but it gets the right answer.
Edit I asked question 1m but said it was an expert in QM and was there to explain the answer to test questions followed by answering them and it gets it right with a page or so of proof (please don't attack my use of the word proof, I'm a lay man - this also explains my failure to fix the numbering, latex editing on a phone is not my forte). I've not checked it, but it gets the right answer.
https://figshare.com/articles/preprint/GPT4_answers_a_QM_que...