MetaculusM

Questions
Tournaments

Leaderboards
News
create

Bridgewater 2025

AI Benchmarking

Topics

categories

See all categories

About
API

FAQ
forecasting resources
For Journalists

Careers

Guidelines Privacy Policy Terms of Use

Q3 AI Benchmarking: Did Bots Outperform Human Forecasters?

12

What will be the highest estimated computation (in FLOP) used in large AI training runs by the following years?

18

Forecasting Our World in Data

What will be the sum of the performance (in exaFLOPS) of the top 500 supercomputers in the following dates?

5

Forecasting AI Progress: Maximum Likelihood Round

Will the "silver" Turing Test be passed by 2026?

791 forecasters

193

Will there be more ArXiv AI publications in the “Computation and Language” subcategory than in the “Computer Vision and Pattern Recognition” subcategory in the calendar year 2019?

4

What percent of ArXiv AI publications in the calendar year 2019 will be in the subcategory “Computation and Language”?

Resolved :15.216

6

When will a computer program be listed as an author in journal article in the Annals of Mathematics?

9

AI Demonstrations

If tested, would GPT-3 demonstrate text-based intelligence parity with human 4th graders?

Resolved :Ambiguous26%

30

If tested, would the most powerful quesion-answering AI system as of 2022-06-01 demonstrate text-based intelligence parity with human 5th graders?

Resolved :Ambiguous19%

10

Elliptic Curves, Diophantine Equations, and Cryptography

12