logoalt Hacker News

apical_dendritetoday at 1:53 PM1 replyview on HN

The best Anthropic models on VendingBench2 are Opus 4.7, Opus 4.6, Sonnet 4.6, and Sonnet 5. Opus 4.7 scored more than twice Fable 5 max. Fable 5 - Low outperforms Fable 5 - Max, with Opus 4.5 in the middle. This seems to break the narrative, which is maybe why Andon Labs doesn't seem to have updated the trend lines on their graphs.


Replies

mckinnon100today at 2:05 PM

However, as another point "On Blueprint-Bench on the other hand, Fable 5 achieves SOTA."

show 1 reply