logoalt Hacker News

mjburgess • today at 12:30 AM • 1 reply • view on HN

And tokens/task is very high. They don't seem to have figured out making the models usable in a typical interactive workflow, ie., they're in a Opus-4.7 era.

Very high hallucination rates too.


Replies

applicative • today at 1:47 AM

It may be a bad bench, but the three going Google models are measured as having the lowest hallucination rates of any llms in history]

https://artificialanalysis.ai/evaluations/omniscience?models...