Exact order of LMSYS leaderboard at the end of April 2024
Basic
24
7.0k
resolved May 1
100%96%
GPT-4-Turbo-2024-04-09, GPT-4-1106-preview, Claude 3 Opus
0.6%
Claude 3 Opus, GPT-4-1106, GPT-4-0125
0.1%
Claude 3 Opus, GPT-4-0125, GPT-4-1106
0.1%
GPT-4-1106, Claude 3 Opus, GPT-4-0125
0.0%
GPT-4-1106, GPT-4-0125, Claude 3 Opus
0.5%
GPT-4-Turbo-2024-04-09, Claude 3 Opus, GPT-4-1106-preview
0.3%
Claude 3 Opus, GPT-4-Turbo-2024-04-09, GPT-4-1106-preview
0.4%
Claude 3 Opus, GPT-4-Turbo-2024-04-09, GPT-4-1106-preview
0.3%
Claude 3 Opus, GPT-4-1106-preview, GPT-4-Turbo-2024-04-09
2%Other

Whatever the exact elo order of the LLMs on the LMSYS leaderboard https://huggingface.co/spaces/lmsys/chatbot-arena-leaderboard

If they have the same elo the order on the site will be used.

Please add answers with commas in between them.

Get Ṁ600 play money

🏅 Top traders

#NameTotal profit
1Ṁ446
2Ṁ239
3Ṁ233
4Ṁ193
5Ṁ73
Sort by:
DanboughtṀ10Other YES

What warrants the confidence that Gemini won't sneak ahead of Opus in the next few days? The margins of error overlap a decent amount, and Gemini actually beats Opus in h2h matchups (barely).

@DanMan314 I think the Elo rankings have been pretty stable, but we'll see!

@TimothyJohnson5c16 Agree it’s unlikely! It was at like 95% when I commented this though which seemed like a lot.

bought Ṁ50 GPT-4-Turbo-2024-04-... YES

I'm not sure if this is meant to be the order of the top 3 models or the order of the 3 models mentioned in the original answer choices or something else.

@Jacy top 3 models not just the three mentioned