Question

What will the highest score be, on Atari 2600 Montezuma's Revenge, by any ML model that is un-augmented with domain knowledge on 2022-01-14?

Resolved :43.8k

7 comments7

Total Forecasters42

Community Prediction80.9k

Make a Prediction

My Prediction

community

lower 25%

median

upper 75%

>1.5M

...

46.77k

80.95k

379.5k

12.8%

What was the final result?43.8k

Community Baseline Score

168.0

Community Peer Score

81.5

Authors:

MetaculusOutlooks

Opened:

Closes:

Resolves:

Forecasting AI Progress

Forecasting AI Progress: Hill Climbing Round

Artificial Intelligence

Atari 2600

Machine learning

Reinforcement learning

When will AI be able to learn to play Montezuma's Revenge in less than 30 min?

2025-06-29

In the following years, what will be the highest LLM scores on the GPQA Diamond benchmark?

80.5

What will be the best non-human SAT-style score on the hard subset of the QuALITY dataset by January 1, 2040?

98.2

Comments

? comments