Will a multi-agent system have its time horizon evaluated by METR before August 2026?
12
Ṁ1kṀ1.5kJul 31
28%
chance
9
1H
6H
1D
1W
1M
ALL
METR's time horizon evaluation: https://metr.org/time-horizons/
Some existing multi-agent systems: GPT-5.2 Pro, Grok 4 Heavy, Gemini 3 Deep Think.
This market doesn't count "regular" models being able to spawn subagents. For example, if the reported evaluated model is Claude Opus 4.6, but the evaluation was made within Claude Code where Claude Opus 4.6 could spawn some Claude Sonnet 4.6 subagents, this does not count for the purpose of this market.
This question is managed and resolved by Manifold.
Market context
Get
1,000 to start trading!
Sort by:
GPT-5.2-Pro is actually available via API right now which I think should simplify the evaluation process quite a lot
People are also trading
Related questions
Will a multi-agent AI system publicly outperform a solo frontier model on a live benchmark before July 2026?
89% chance
Best AI time horizon by August 2026, per METR?
Polymarket has some METR time horizon market before August 2026?
20% chance
Will the METR 50% Time Horizon be "ambiguous" at the end of 2026?
71% chance
Best METR 50% Time Horizon in 2026
Will METR retire the 50% Time Horizon by EOY 2026
61% chance
What will be the METR time horizon doubling time in 2026?
What will the frontier METR time horizon be on January 1, 2027?
What will the frontier METR time horizon be on January 1, 2028?
AI time horizon of 10 hours by September 1st 2026?
83% chance