Show HN: AA-Briefcase: a frontier knowledge work evaluation (artificialanalysis.ai)

13 points by declanjackson 4mo ago ↗ HN

2 comments

[ 1.8 ms ] story [ 16.3 ms ] thread

the example submissions are really good comparisons, comparing Fable 5's submission to Opus 4 is fairly stark

GLM hanging with the frontier big dogs