Hacker News new | ask | show | jobs
by npinsker 918 days ago
By its nature, that site isn't very representative of how the models perform in real-world use.
2 comments
Reubend 916 days ago
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.
link
ssabev 918 days ago
The ELO leaderboard you mean?
link