Re:30% Drop In o1-Preview Accuracy When Putnam Problems Are ...
by scratchyone on Wednesday January 01, 2025 @09:24PM
(#42571060)
fwiw i think reasoning models have at least solved this. even the smallest reasoning model, o1-mini, gets it right first try on my test:
[ Parent
| on HN ]
There are no comments on this comment yet.