HN
login
gev beats jev and takes images as input tooanyeval.com

Two models on the same JevBench problems: paired accuracy and model answer speed.

1 points•ljlolel•7 days ago•1 comment•
#jev#beats#images#input#gev#gev beats#beats jev#takes images

1 comment

ljlolel7 days ago
I've made a new model `gev` that outperforms `jev` in accuracy on JevBench and it takes image input too (unlike jev), and gev can be faster too!

also this AnyEval we made is great. can set up any model vs model comparisons for any benchmark

full traces. cryptographically signed

Read the full thread on Hacker News →

Related stories