That last benchmark seemed like an impressive leg up against Opus until I saw the sneaky footnote that it was actually a Sonnet result. Why even include it then, other than hoping people don't notice?

Definitely don’t want to click in at x either.

It seems that all frontier models are basically roughly even at this point. One may be slightly better for certain things but in general I think we are approaching a real level playing field field in terms of ability.

Why do so many people in the comments want 4o so bad?

how does 5.4-thinking have a lower FrontierMath score than 5.4-pro?

It is a bigger model, confirmed

Why do none of the benchmarks test for hallucinations?