Best AI time horizon by August 2026, per METR?

Question

This market will resolve to the highest METR 50% time horizon for any AI model released by August 31, 2026, closing after a two-month buffer period. Left bounds inclusive, right bounds exclusive.

50% time horizon is, roughly speaking, the time that skilled 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 more. As of August 2025, the longest 50% time horizon is GPT-5's 2h 17 min.

[image]For reference, the buckets in this market correspond to doubling times of roughly:

6 hours: 9 months

8 hours: 7 months

12 hours: 5.3 months

16 hours: 4.5 months

24 hours: 3.7 months

given that GPT-5 has a time horizon of 2.28 hours and was released in early August 2025.

Time horizon estimates will vary based on the set of tasks used, so this market will be based on the "headline" result reported by METR. METR currently uses a composite of the HCAST, RE-Bench, and SWAA benchmarks. There is a good chance that they extend this set with harder/longer tasks at some point.  If METR no longer publishes a headline result, and their future evals are based on substantially different benchmarks so that it is difficult to compare to their mid-2025 estimates, then this market may become ambiguous and resolve N/A.

Update 2026-05-10 (PST) (AI summary of creator comment): If METR releases a point estimate for a model's time horizon, this market will resolve to that point estimate. For example, a 17-hour point estimate for Mythos preview would be used directly.

Manifold Markets · Answer

Per Manifold Markets prediction market, >=24 hours, followed by 16 to 24 hours and 12 to 16 hours are most likely. See the market for live updates (60 traders, as of Jun 2, 2026).