Oh this will be a little bit of a mess to resolve: https://twitter.com/lmsysorg/status/1790097588399779991

@ChrisPrichard In particular, they won't be called gpt2-chatbot when they go up on the official leaderboard.

@ChrisPrichard My read, given that it is the same model, that this should resolve yes if gpt-4o is on top at the end of May.