How long will Claude 3 Opus keep its March 2024 lead of LMSYS Chatbot Arena Leaderboard?
31
292
1.9k
resolved Apr 11
Resolved
YES
March 2024
Resolved
NO
October 2024
Resolved
NO
November 2024
Resolved
NO
May 2024
Resolved
NO
April 2024
Resolved
NO
June 2024
Resolved
NO
July 2024
Resolved
NO
August 2024
Resolved
NO
September 2024
Resolved
NO
December 2024

Months resolve to YES as soon as the full month has passed, and Claude 3 Opus is still on the top of the leaderboard. When Claude 3 Opus is no longer on top of the list, that month and all of the following alternatives, resolve to NO.

Resolves according to ELO Arena ELO, not the first "rank" column, on LMSys Chatbot Arena Leaderboard.

Any other model topping the list, including models from Anthropic, or new variations of Claude 3, leads to resolution and closing of this question.
Edit: For new versions of "Claude 3 Opus" that don't change name on the leaderboard, I will consider it a continuation and "keeping its lead", as opposed to examples like "Claude 3 Epic", "Claude 3 Opus Max" or "Claude 4 Opus".

I have and will trade in this market.

Get Ṁ600 play money

🏅 Top traders

#NameTotal profit
1Ṁ465
2Ṁ186
3Ṁ118
4Ṁ102
5Ṁ92
Sort by:

Have they cemented their lead for the rest of the year? 👀

@Jacy does it resolve NO now?

bought Ṁ150 December 2024 NO

oops sorry, I meant to ping @HenriThunberg

@Bayesian I only get an error message at the moment, but I bet it will be OK in a few minutes.

Edit: NVM I can get it from their Twitter.

Does being tied for Rank 1 count, or does it have to have the highest Elo point estimate?

(E.g. if GPT-4-1106 comes in at 1254 +- 3 at the next update, and Opus is still at 1253, I believe lmsys would list GPT-4-1106 first, but still give Opus a shared rank of 1.)

@rogs Sorry for late reply here. Your described case would mean the lead has been taken over by GPT-4-1106 as it would have a higher ELO and be listed higher.

The real edge case for me would be if they have the same ELO – in that case I would take the answer for no 1 to be whichever is listed higher, as that is most consistent with my market description. It also

More related questions