This market will resolve to the highest 50% time horizon, as reported by METR, for any Gemini 3 model released within a month of the first Gemini 3 announcement.
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.

Left bounds inclusive, right bounds exclusive.
See also:
/jim/claude-45-opuss-metr50-horizon (jim's version)
/Bayesian/claude-opus-45s-metr50-time-horizon (my version)
/Bayesian/gemini-3s-50-time-horizon-per-metr (this market)
People are also trading
@jim I think the “within a month” thing means any model of Gemini’s released within a month of the first announcement, not METR’s analysis
@bens yes, but it's not guaranteed that any Gemini models which meet this condition will be evaluated by METR.
but if they don't then obviously it would resolve to <1.5h jk it would resolve N/A
@MaxLennartson The currently available model is gemini 3 pro preview. General access is when they remove all modifiers and sctually call the model gemini 3 pro in the api and such
@MaxLennartson They’re calling it thst to customers to keep it simple but the devs they re calling it gemini 3 pro preview
@Bayesian Do you think that METR will evaluate the ai models that have been released recently including Gemini 3?
