In that vein, perhaps the delta between o3 @ 87.5% and Human @ 85% represents a deficit in the ability of text to communicate human reasoning.
In other words, it's possible humans can reason better than o3, but cannot articulate that reasoning as well through text - only in our heads, or through some alternative medium.
It's possible humans reason better through text than not through text, so these models, having been trained on text, should be able to out-reason any person who's not currently sitting down to write.
Yeah, this is sort of meaningless without some idea of cost or consequences of a wrong answer. One of the nice things about working with a competent human is being able to tell them "all of our jobs are on the line" and knowing with certainty that they'll come to a good answer.
