A model can have high token / s and still be slow to complete a task. They tend to have vastly different verbosity characteristics.

E.g. something like Haiku is "obviously" faster than Opus. Yet if you test Opus 5.5 on medium vs Haiku on max (because Haiku needs to be cranked pretty high on effort to be reasonably intelligent), you'll observe that Opus is ~2x faster to complete.