Hacker News new | ask | show | jobs
by pixel_popping 141 days ago
It's lacking the best model (Opus 4.5) on the benchmark tho.
1 comments
djohnston 140 days ago
Yeah but then their own product might not score the highest.
link
pixel_popping 139 days ago
Exactly why I'm pointing it out, which feels a bit corrupt, but understandable.
link
djohnston 139 days ago
tbh i was a bit cranky yesterday - even if they are #2 on a legit benchmark that would be impressive
link