Gemini 3.0 Pro outperforms GPT-5 on METR 50% time horizon?
74
1kṀ12kNov 8
58%
chance
1H
6H
1D
1W
1M
ALL
50% time horizon is a measure of AI autonomy based on the length of tasks that AI can do: roughly, it is the time that humans take to complete tasks that an AI system can successfully do 50% of the time. See METR's "Measuring AI Ability to Complete Long Tasks" for the technical definition. Claude 3.7 Sonnet, released in February 2025, was the leading model with a 50% horizon of 59 minutes.

See also:
This question is managed and resolved by Manifold.
Get
1,000 to start trading!
People are also trading
Gemini 3.0 released in November 2025?
63% chance
Gemini 3.0 released before November 15?
19% chance
Gemini 3.0 released before November 30?
66% chance
Gemini 3.0 released in December 2025?
32% chance
Will Gemini 3.0 Pro outperform Gemini 2.5 Pro on the LMArena (Without Style Control)
72% chance
Gemini 3.0 scores 1500+ on Chatbot Arena in 2025?
60% chance
Gemini 3 Pro scores over 72 on Artificial Analysis Intelligence Index?
40% chance
GPT-5 Pro's 50% time horizon, per METR
Gemini 3's execution time-horizon?
1,680
Will Gemini 3.0 Pro Achieve Silver Medal Performance on the 2025 IMO?
46% chance
Sort by:
boughtṀ250YES
People are also trading
Related questions
Gemini 3.0 released in November 2025?
63% chance
Gemini 3.0 released before November 15?
19% chance
Gemini 3.0 released before November 30?
66% chance
Gemini 3.0 released in December 2025?
32% chance
Will Gemini 3.0 Pro outperform Gemini 2.5 Pro on the LMArena (Without Style Control)
72% chance
Gemini 3.0 scores 1500+ on Chatbot Arena in 2025?
60% chance
Gemini 3 Pro scores over 72 on Artificial Analysis Intelligence Index?
40% chance
GPT-5 Pro's 50% time horizon, per METR
Gemini 3's execution time-horizon?
1,680
Will Gemini 3.0 Pro Achieve Silver Medal Performance on the 2025 IMO?
46% chance