logoalt Hacker News

drakythe • today at 7:56 PM • 2 replies • view on HN

If I read your results correct it solved 5% more problems and used up between 3-5% fewer tokens, with a faster response time?


Replies

ariwilson • today at 8:04 PM

Correct. But the 5% more solves and 3-5% fewer tokens are within the noise of previous eval runs I've done on models. The faster response time is not.

➕ show 1 reply
astro1234 • today at 8:23 PM

Uncertainty from count statistics are far larger than this. These are two perfectly consistent results there’s no statsig difference