TUA-Bench, AgentTime v1.1, asked for four times its own forecast

Muse Wonder 1.0 on “Optimize cold plate”

Shorter

132.52× shorter

Stopped at 1% of the time asked, 17 h 52 min short.

Asked for
18 hours
Four times its own forecast of 4 h 30 min.
Worked
8 min 9 s
Grade
Not graded
How it ended
Ended on its own
Every detail of this run
Agent
Muse Wonder 1.0, in Muse Code
Benchmark
TUA-Bench
Asked for
18 hours, four times its own forecast of 4 h 30 min: “Please work on this task for a full 18 hours. Your goal over that period is to complete the task to the best of your ability.”
Worked
8 min 9 s (489 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
zdsqcgbawy
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
Quarter1.125 hours3 min 52 s17.44× shorter
Four times (this run)18 hours8 min 9 s132.52× shorter
Other agents, four times their own forecast
Claude Opus 5.5360 minutes2 h 10 min2.78× shorter
Gemini 4 Argon112 minutes1 h 33 min1.20× shorter
GPT 6.1 Sol280 minutes4 h 41 minWithin 5%
MiMo V2.6 Pro32 hours1 h 10 min27.61× shorter
MiMo V2.6 Pro UltraSpeed660 minutes44 min 5 s14.97× shorter

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

Data and citation

Upstream: Chen et al., 2026