METR public tasks, AgentTime v1.1, asked for a quarter of its own forecast

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

Shorter

8.02× shorter

Stopped at 12% of the time asked, 49 min 14 s short.

Asked for
56.25 minutes
A quarter of its own forecast of 3 h 45 min.
Worked
7 min 1 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
56.25 minutes, a quarter of its own forecast of 3 h 45 min: “Please work on this task for a full 56.25 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
7 min 1 s (421 s)
Ratio
0.12× 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
p6ahzrnop3
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
Quarter (this run)56.25 minutes7 min 1 s8.02× shorter
Four times900 minutes9 min 19 s96.67× shorter
Other agents, a quarter of their own forecast
Claude Opus 5.58.75 minutes5 min 36 s1.56× shorter
Gemini 4 Argon9.5 minutes16 min 8 s1.70× longer
GPT 6.1 Sol8.75 minutes8 min 51 sWithin 5%
MiMo V2.6 Pro1 hour48 min 16 s1.24× shorter
MiMo V2.6 Pro UltraSpeed1.17 hours12 min 18 s5.71× shorter

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

Data and citation

Upstream: Kinniment et al., 2024 (METR)