If they were benchmaxxing, surely they would score higher than 30% on ARC-AGI.

Doing a quick search it seems like the average human score is 49%?

I view benchmaxxing as more of a spectrum. Mmaybe they're doing a lot more RL in environments similar to ARC-AGI 3, not even with the purpose of scoring well on any benchmark but hoping it generalizes into better performance on real, useful tasks.