My understanding is that gpt4 is better at this than 3.5 and it seems to get it pretty reliably. One thing that's interesting to do is to imply the answer is incorrect and see if you can get it to change its answer. If you let it stop answering when it's correct, you get the Clever Hans effect.
(For comparison, here's GPT-4 getting it on first try: https://chat.openai.com/share/9e17ed25-d9ea-4e72-a9d8-a139ca... )