Chatbot Arena: Benchmarking LLMs in the Wild with Elo Ratings(lmsys.org)
lmsys.org
Chatbot Arena: Benchmarking LLMs in the Wild with Elo Ratings
https://lmsys.org/blog/2023-05-03-arena/
5 comments
could you provide any reference? Is it a variant of ELO?
Elo != ELO.
One is a rating system named after the creator, Arpad Elo. See https://en.wikipedia.org/wiki/Elo_rating_system
The other is a rock band that was formed in 1970. See https://en.wikipedia.org/wiki/Electric_Light_Orchestra
One is a rating system named after the creator, Arpad Elo. See https://en.wikipedia.org/wiki/Elo_rating_system
The other is a rock band that was formed in 1970. See https://en.wikipedia.org/wiki/Electric_Light_Orchestra
check matchmaking section: https://www.dota2.com/newfrontiers
Valve listed some reason for making the change.
https://en.wikipedia.org/wiki/Glicko_rating_system
Valve listed some reason for making the change.
https://en.wikipedia.org/wiki/Glicko_rating_system
This is a very good idea.
You may also learn from 7.33 dota update which uses a new ranking algorithm called Glicko.