Will Claude Opus be ranked in the top 20 on the Chatbot Arena Leaderboard two years from today (3/10/24)?
23
1kแน€10k
Mar 11
6%
chance

To resolve this, I will look at the huggingface Chatbot Arena Leaderboad and see if Claude Opus' ELO is within the top 20. If it is, this market resolves as yes. If not, then no.

https://huggingface.co/spaces/lmsys/chatbot-arena-leaderboard

Get
แน€1,000
to start trading!
Sort by:
bought แน€10 YES

Will future versions/revisions of Opus count? For example, GPT-4 has multiple versions released at different times that currently occupy the 1st, 2nd, 5th, and 7th positions.

@AndrewBrown My bad for missing this comment. I will consider any future revisions to count for this. So long as it is released as a Claude 3 model I will count it.

So "Claude 3.5 Opus" would count but "Claude 4 Opus" would not count?

bought แน€100 NO

@VerySeriousPoster due to this statement, it can't resolve to yes for 3.5 opus imo

ยฉ Manifold Markets, Inc.โ€ขTermsโ€ขPrivacy