You should expect quite a bit of novelty from the IMO, given the constraint of high school level curriculum. The problem setters work very hard to avoid problems that are variations of other contests or solvable by routine methods. That's why this is a very exciting result--you can't just regurgitate homework problem solutions to get a high score at the IMO.
These models are trained on all old problem and their various solutions.For LLM models, solving thses problems are as impressive as writing code.
There is no high generalization.