Will a model achieve a METR 50% time-horizon of 4+ hours by the end of 2025?
5
100Ṁ190Dec 31
41%
chance
1H
6H
1D
1W
1M
ALL
METR's 50%-time horizon doubling time trendline from more recent models indicates that a model released towards the end of 2025 will likely have a time horizon of over 4 hours. Will this come true?
See links for more details:
https://www.alignmentforum.org/posts/SuvWoLaGiNjPDcA7d/metr-s-evaluation-of-gpt-5
https://www.lesswrong.com/posts/deesrjitvXM4xYGZd/metr-measuring-ai-ability-to-complete-long-tasks
This question is managed and resolved by Manifold.
Get 
1,000 to start trading!
1,000People are also trading
Related questions
GPT-5's 50% time horizon, per METR
Best AI time horizon by August 2026, per METR?
Will any AI model achieve > 40% on Frontier Math before 2026?
58% chance
Grok 5's 50% time horizon, per METR
Will the METR long-horizons have a >6 month doubling time for at least a 4 month period before 2026?
77% chance
Will any model get above human level on the Simple Bench benchmark before September 1st, 2025.
4% chance
Best AI time horizon by February 2026, per METR?
Will a female runner run a mile in under 4 minutes by the end of 2030?
R2's 50% time horizon, per METR
Will an AI system capable of doing tasks that take humans eight hours as determined by METR.org, exist by 2027
82% chance