Question

What will be the best accuracy score on the MATH dataset by 2025?

16 comments16

Total Forecasters73

Community Prediction9.42e-1

Make a Prediction

My Prediction

community

lower 25%

median

upper 75%

...

9.04e-1

9.421e-1

9.73e-1

Authors:

Matthew_Barnett

Opened:

Closes:

Scheduled resolution:

AI Technical Benchmarks

Computing and Math

Artificial Intelligence

Mathematics

Machine learning

Artificial intelligence

Computer science

Data analysis

What will be state-of-the-art performance on the MATH dataset on the following dates?

What will be state-of-the-art accuracy on the Massive Multitask dataset on the following dates?

94.9

What will be the best non-human SAT-style score on the hard subset of the QuALITY dataset by January 1, 2025?

80.3

Comments

? comments

Authors:

Matthew_Barnett

Opened:

Closes:

Scheduled resolution:

AI Technical Benchmarks

Computing and Math

Artificial Intelligence

Mathematics

Machine learning

Artificial intelligence

Computer science

Data analysis

A Century-Old Question Is Still Revealing Answers in Fundamental Math

Scientific American•Oct 9, 2024

Between Chaos and Control: Where LLMs Find Their Brilliance

Psychology Today•Oct 11, 2024

Researchers question AI’s ‘reasoning’ ability as models stumble on math problems with trivial changes

TechCrunch•Oct 12, 2024

Learn more about Metaculus NewsMatch

What will be state-of-the-art performance on the MATH dataset on the following dates?

What will be state-of-the-art accuracy on the Massive Multitask dataset on the following dates?

94.9

What will be the best non-human SAT-style score on the hard subset of the QuALITY dataset by January 1, 2025?

80.3