Will there be a model that has a 75% win rate against the latest iteration of GPT-4 as of January 1st, 2025?

AI Technical AI Timelines Chatbot Arena Leaderboard GPT-4

Basic

Ṁ15k

2025

44%

chance

ALL

As per the LMSYS Chatbot Arena leaderboard, the latest iteration of GPT-4 currently has a 77% (0.77) win rate against Mistral Medium, approximately representing the advantage of GPT-4 over GPT 3.5. As of 2025-01-01, will there be a model that has a 75% or higher win rate against the latest iteration of GPT-4?

Clarifications:

I will look at the ranking of the models in the Fraction of Model A Wins for All Non-tied A vs. B Battles section of Chatbot Arena, or an equivalent section as of Jan 1st, 2025. If a new GPT-4 model is released on (say) Dec 31st, 2024 and is not yet ranked on Chatbot Arena, it will not count for the purposes of this question.
Any model that's named gpt-4-* will count. So gpt-4-turbo-2025-01-01 or gpt-4-hyper-advanced will count as "GPT-4". Something like gpt-4.1-turbo or gpt-5-turbo will not count as "GPT-4".
If ChatBot arena no longer provides a win % for any GPT-4 models or ceases to exist entirely, this question will resolve as N/A.
If the ChatBot Arena website happens to be down for maintenance or any technical issue on Jan 1st, 2025, I will keep trying again for 7 days. If after 7 days the ranking is still unavailable, I will resolve this to N/A.

Get Ṁ600 play money

Related questions

Will xAI release a model that matches or surpasses GPT4 performance in 2024?

73% chance

Will there be a OpenAI LLM known as GPT-4.5? by 2033

35% chance

Who will release a GPT-4o comparable model in 2024?

Will an open source model beat GPT-4 in 2024?

89% chance

Will a model as great as GPT-5 be available to the public in 2025?

79% chance

Will an open model with comparable results to GPT-4 on MMLU be released by the end of July 2024?

93% chance

Will we have an open-source model better than GPT-4-Turbo before 2025?

69% chance

Will there be an LLM (as good as GPT-4) that was trained with 1/100th the energy consumed to train GPT-4, by 2026?

52% chance

Will an open-source LLM beat or match GPT-4 by the end of 2024?

81% chance

Will any open-source model achieve GPT-4 level performance on MMLU through 2024?

Sort by:

Chat Arena is a flawed benchmark anyway, and based on the numbers it seems almost impossible this would happen. GPT-4o, the number 1 model on the leaderboard, only has a 71% win rate against its most lopsided matchup. That matchup is GLM-4, a model which is terrible in all my evaluations.

Even if the next gen of models are a huge step up over the current SOTA, I don't expect any of them to achieve that high of a win rate

GPT-4o has a 61% win rate against GPT-4-turbo. Pretty good but still needs a lot of work to get to 75%.

GPT-4o did not follow the gpt-4-x scheme, so it doesn't count as GPT-4 for the purposes of this question (it would've if it was called gpt-4*-*o). So if gpt-4o beats gpt-4-latest with a 75+% win rate in the leaderboard, this will resolve to Yes.

Danopened aṀ250 NO at 52% order

reposted

Limit up if anyone wants to take it

why is this market less than the gpt-5 comes out in 2024 market? The 'gpt-5 will be underwhelming' money?
https://manifold.markets/VictorLJZ/will-gpt5-be-released-before-2025

@JoeandSeth GPT-5 could come out and still fail to have a decisive advantage over GPT-4.