Compare 75 AI Models on 200 Prompts Side by Side

by pajopon 7/28/24, 9:20 PMwith 3 comments
by frabjousedon 7/29/24, 1:42 AM

Very nice. If these are pre-computed, is it possible to make a table view that lists every prompt and the answer?

by OutOfHereon 7/29/24, 3:53 AM

As per this site, only GPT-4-Turbo seems to get "What is poisonous for humans but not for dogs?". All other models look to fail at it.