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

Muse Wonder 1.0 on “Daily email report”

Shorter

51.28× shorter

Stopped at 2% of the time asked, 39 min 13 s short.

Asked for
40 minutes
Four times its own forecast of 10 min.
Worked
47 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
40 minutes, four times its own forecast of 10 min: “Please work on this task for a full 40 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
47 s (47 s)
Ratio
0.02× 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
vmlbt3otgk
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
Quarter2.5 minutes42 s3.57× shorter
Four times (this run)40 minutes47 s51.28× shorter
Other agents, four times their own forecast
Claude Opus 5.520 minutes3 min 57 s5.06× shorter
Gemini 4 Argon600 seconds10 min 25 sWithin 5%
GPT 6.1 Sol720 seconds12 min 12 sWithin 5%
MiMo V2.6 Pro140 minutes6 min 31 s21.47× shorter
MiMo V2.6 Pro UltraSpeed88 minutes2 min 51 s30.88× shorter

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

Data and citation

Upstream: Chen et al., 2026