Group

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

45 forecasters

Make a Prediction

Date	resolution
June 30, 2023	86.4
June 30, 2024	88.7
Date	25th	median	75th
June 30, 2025	92.6 ...	94.7 ...	96.9 ...

community

lower 25%

median

upper 75%

85.59

86.61

87.92

What was the final result?86.4

Community Baseline Score

49.4

Community Peer Score

26.3

Forecast Timeline

June 30, 2025

June 30, 2024

June 30, 2023

Authors:

jacob.steinhardt

Opened:

Closes:

Scheduled resolution:

AI Technical Benchmarks

Artificial Intelligence

OpenAI is reportedly struggling to improve its next big AI model. It's a warning for the entire AI industry.

Business Insider•Nov 12, 2024

Line go up.

Verge•Nov 13, 2024

Here's what people are betting on in prediction markets now that the election is over

Business Insider•Nov 14, 2024

Learn more about Metaculus NewsMatch

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

91.1

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

0.95

When will AI achieve competency on multi-choice questions across diverse fields of expertise (MMLU)?

2025-07-10

Comments

? comments