HN Explorer

6 comments

[ 3.3 ms ] story [ 23.3 ms ] thread
ssabev
Spoiler: it's fast, cheap, overly protective, and has Kafkaesque DX
jafitc
This "vibe" check that it's even better than GPT-4 Turbo is not what its Elo rating shows on the Chatbot Arena based on not 1 but thousands of user votes. GPT-4 (Turbo) is in a league of its own still.
Racing0461
The vibe check is for pro tho. I want to see how ultra is benchmarked.
npinsker
By its nature, that site isn't very representative of how the models perform in real-world use.
ssabev
The ELO leaderboard you mean?
Reubend
That depends on what real world use you're targeting, but unfortunately I'm not aware of anything better than that leaderboard in terms of sample size and model coverage.