This market will resolve to the 50% time horizon, as reported by METR, for GPT-5.2.
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
/Bayesian/grok-5s-50-time-horizon-per-metr
/Bayesian/r2s-50-time-horizon-per-metr
Update 2025-12-12 (PST) (AI summary of creator comment): Only GPT-5.2 itself will count for resolution. Variants like GPT-5.2 Codex will not count, even if they are the only version evaluated by METR.
1,000