Will an AI model outperform 95% of Manifold users on accuracy before 2026?

1.1kṀ4730

Dec 31

49%

chance

ALL

This is comparing accuracy of the AI model vs Manifold users on a 'benchmark' selection of objective markets'.

Inspired by the Autocast competition: https://forecasting.mlsafety.org/

Close date updated to 2026-01-01 12:59 am

Technical AI Timelines

Manifold

Get

1,000

to start trading!

People are also trading

Will an AI achieve >85% performance on the FrontierMath benchmark before 2028?

72% chance

Will any AI model achieve > 40% on Frontier Math before 2026?

84% chance

Will AI image generating models score >= 90% on Winoground by June 1, 2025?

76% chance

Will Manifold stop using AI to make my questions worse by the end of 2025?

20% chance

Will AI wipe out Manifold by 2030?

5% chance

At the beginning of 2026, what percentage of Manifold users will believe that an AI intelligence explosion is a significant concern before 2075?

68% chance

Will any AI model score above 95% on GRAB by the end of 2025?

41% chance

An AI is trustworthy-ish on Manifold by 2030?

47% chance

Will any AI model score >80% on Epoch's Frontier Math Benchmark in 2025?

17% chance

Will an AI system beat humans in the GAIA benchmark before the end of 2025?

Sort by:

Does this refer to a single AI model or to a system with scaffolding? What tools is the model allowed to use?

Are there any examples of currently profitable LLM bots?

By users you mean human users right? Anything in the silicon league excluded?

Hmm... I think that this might depend crucially on how many inaccurate users Manifold will have at that point (e.g., would you count people who haven't been active for years, or all the people who lost their starting Mana in a few bets and then stopped using the platform)?