logoalt Hacker News

andxoryesterday at 8:06 PM2 repliesview on HN

Artificial Analysis just published their aggregate score (61).

Still below Fable 5, let alone Fable 5.1.

EDIT: This is suspiciously low. Calls the relevance of existing benchmarks into question.


Replies

timperayesterday at 8:47 PM

I agree, Opus 5 scoring higher than Fable 5 on Artificial Analysis really makes me question the relevance of these scores.

show 1 reply
natsucksyesterday at 9:50 PM

I saw this too and I'm really confused.