The point here is to test for "genuine reasoning" or something approaching it. If a model is truly reasoning it should be competent even in a new language you just made up (provided the language itself is competently designed)
It's not as if the models here were asked to write a kernel in Brainfuck; the medium tier of problems here contains such apparently insurmountable tasks as "calculate the nth prime".
The thing about LLMs is there doesn't seem to be a way to teach them genuine reasoning. You can spend a month teaching an LLM brainfuck and it would likely still fail at a novel problem. Whereas if a human studied brainfuck for a month they would probably be quite competent at a novel problem