Questions
Tournaments
Services
News

Questions
Tournaments

Questions

Questions

293 forecasters

11

293 forecasters

Kiko Llaneras Tournament 🔮

Will an AI achieve >85% performance on the FrontierMath benchmark before 2026?

ResolvedNo

Result of 49% reached recently

Increases Likelihood

error rate is probably 10%

Decreases Likelihood

tool use is not allowed

Decreases Likelihood

Public Benefit Corporation

Metaculus is an online forecasting platform focusing on topics of global importance.

ExploreQuestions Tournaments Tournaments for AI bots FutureEval

ServicesLaunch a Tournament Private Instances Pro Forecasters

CompanyAboutCareers FAQ

ResourcesForecasting Resources For Journalists API

Guidelines Privacy Policy Terms of Use

11 comments168 forecasters

AI system beat human pros in forecasting tournament by 2030?

2 comments118 forecasters

AI-authored paper published at NeurIPS, ICML, or ICLR before 2028?

4 comments62 forecasters

Frontier model released in 2029 without third-party evals?

26 comments739 forecasters

Top ARC-AGI-2 score in 2026?

Current estimate

0 comments64 forecasters

When will an AI achieve an score of 1.5 or higher in the RE-bench at any time budget between 8h and 32h?

Current estimate

188 comments3k forecasters

Human/Machine Intelligence Parity by 2040?

3 comments50 forecasters

AI labs collaborate at least a little on safety in 2030?

8 comments57 forecasters

Highest score among a selected subset of VideoGameBench on Jan 1, 2028?

Current estimate