Will AIs stay below 1453 elo in 2024 on chat.lmsys.org/?leaderboard as predicted by Gary Marcus?
➕
Plus
54
Ṁ48k
Dec 31
88%
chance
Get
Ṁ1,000
and
S3.00
Sort by:
opened a Ṁ500 YES at 60% order

@ZinqTable some limit orders for you ✨️

Elo jumps are 100ish from GPT-3.5 (first version) to GPT-4 (first version). GPT-4o's improvement over 3 months was 80 points. We have two months til the end of 2025. So that gives us a couple of rough upper bounds on previous performance jumps (upper bounds since we have current 4o not release 4o to compare to for the former, and we have 2 months for the latter).

Sam has said GPT-5 release this year is fake news, and the market is at 30% or so. Let's say ~10% to this happening without 5 releasing, and 20% if 5 releases. That's 13%. This is an absurdly priced market IMO. Would be curious to hear if anyone wants to explain an alternative view.

I'm not too concerned about o1-mini or o1-preview performing 100+ ELO better than GPT-4o because OpenAI has already released human preference data. These models only achieve a 70% win rate on math, leading to about a 75 ELO improvement—still roughly 50 ELO short of reaching 1453. Even if the full o1 model performs 50 ELO better than o1-preview, the data in the graph suggests it's unlikely to surpass 1453. I believe Orion or GPT-5 could achieve 1453+ ELO, but the market only gives that a 30% chance this year. Overall, I think the market is fairly well-calibrated at 75%, though perhaps a bit pessimistic.

bought Ṁ40 YES

@ZinqTable The initial results for o1-preview are in, and it's only 20 elo points higher than 4o.

😅 nervous about o1's lmsys ELO. This seems like the "real deal" from what I hear.

Will Opus 3.5 or GPT-5 be over 150 ELO better than current publicly available models? The difference between Claude Opus and Claude Haiku is only 70 ELO! I think this market should be 99% unless you expect AGI level output very soon. I hope I'm wrong, this "AI IQ" leaderboard is exciting!

That is not the same statement at all.

ELO is a way to measure how much better an agent is compared to the rest of competitors, based on the results of head-to-head matches. Gary is saying that we won’t have something 200 points higher than GPT-4. Gary’s statement could be correct if a few great chatbots emerge, and GPT-4’s ELO rating drops as a result.

bought Ṁ30 YES

Not a particularly bold prediction by Gary lol, he's trying to say that models are plateauing but if we get a 1400 Elo model before the end of the year that would not be a plateau at all, and would still be 50 away from this line.

I'd bet no on a version of this that excluded ties and a few other things. However, I think that ties and the low quality of many questions (and the low quality of the evaluation of many answers) might mean that even enormous improvements might not be enough to get a model to 1453. We are, I think, bumping on the ceiling of this particular method of evaluation, and while a fantastic enough model probably could reach 1453, it would not be the smallish-moderate sized improvement it may appear to be at first glance.

Related:

© Manifold Markets, Inc.Terms + Mana-only TermsPrivacyRules