Yes but there’s a reason we don’t evaluate these models this way and instead do it as carefully and thoughtfully as we can at scale. Human evaluations are important but they are an absolute minefield of footguns. 4.8 is not a downgrade from 4.6 there is an insane amount of hard data that contradicts this.

"Fable 5" is Opus 4.7, and the Opus 4.7 we got is a Sonnet sized model on a stronger base.

That's where all the regressions and inconsistency in experiences stem from: RL can still only go so far vs having more parameters