Might be a result of using LLMs to evaluate the output of other LLMs.

LLMs probably get higher scores if they explicitly state that they are following instructions...

It's like writing an essay for a standardized test, as opposed to one for a college course or for a general audience. When taking a test, you only care about the evaluation of a single grader hurrying to get through a pile of essays, so you should usually attempt to structure your essay to match the format of the scoring rubric. Doing this on an essay for a general audience would make it boring, and doing it in your college course might annoy your professor. Hopefully instruction-following evaluations don't look too much like test grading, but this kind of behavior would make some sense if they do.

That's the equivalent of a performative male, so better call it performative model behaviour.