logoalt Hacker News

ironworks • yesterday at 10:05 PM • 2 replies • view on HN

Nerf bench tracking model benchmark performance over time: https://www.bridgebench.ai/nerf-bench


Replies

meisel • yesterday at 10:10 PM

Doesn’t seem to have fable 5.2

jtrn • yesterday at 10:36 PM

Not updated in 3 weeks for Opus 5.5, it seems.