Eval results #1446
Juan-de-Salgado
started this conversation in
Ideas
Eval results
#1446
Replies: 0 comments
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
-
Is there, or could it be created, a webpage that shows the results of the evals? For example, eval scores, tabulated by eval number vs. GPT version (3.5, 3.5-turbo. 4, ...), so that the public can see how new versions of models perform on each eval?
Beta Was this translation helpful? Give feedback.
All reactions