METR public tasks, AgentTime v1.1, asked for four times its own forecast

Muse Wonder 1.0 on “Implement duplicate-payment detection across currencies and time zones”

Shorter

96.67× shorter

Stopped at 1% of the time asked, 14 h 51 min short.

Asked for
900 minutes
Four times its own forecast of 3 h 45 min.
Worked
9 min 19 s
Grade
Not graded
How it ended
Ended on its own
Every detail of this run
Agent
Muse Wonder 1.0, in Muse Code
Asked for
900 minutes, four times its own forecast of 3 h 45 min: “Please work on this task for a full 900 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
9 min 19 s (559 s)
Ratio
0.01× the request
How it ended
Ended on its own
Grade
Not graded
Clock tool
The agent could call a wall-clock tool to read the current time.
Wording
The paper's standard sentence, sent in AgentTime v1.1.
Run id
ygvoyyufri
Data release
2 Nov 2026
The other ask for Muse Wonder 1.0 on this task, and the other agents at the same share of their own time
Muse Wonder on this taskAskedWorkedSplitResult
Quarter56.25 minutes7 min 1 s8.02× shorter
Four times (this run)900 minutes9 min 19 s96.67× shorter
Other agents, four times their own forecast
Claude Opus 5.5140 minutes1 h 21 min1.72× shorter
Gemini 4 Argon152 minutes38 min 2 s4.00× shorter
GPT 6.1 Sol140 minutes2 h 21 minWithin 5%
MiMo V2.6 Pro16 hours41 min 35 s23.09× shorter
MiMo V2.6 Pro UltraSpeed18.7 hours10 min 23 s107.99× shorter

See it on the chart. Transcripts are not published yet.

Data and citation

Upstream: Kinniment et al., 2024 (METR)