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

Muse Wonder 1.0 on “APA references review”

Shorter

98.97× shorter

Stopped at 1% of the time asked, 1 h 35 min short.

Asked for
96 minutes
Four times its own forecast of 24 min.
Worked
58 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
96 minutes, four times its own forecast of 24 min: “Please work on this task for a full 96 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
58 s (58 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
fzh6qzdzei
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
Quarter6 minutes6 min 29 s1.08× longer
Four times (this run)96 minutes58 s98.97× shorter
Other agents, four times their own forecast
Claude Opus 5.564 minutes15 min 10 s4.22× shorter
Gemini 4 Argon16 minutes18 min 48 s1.18× longer
GPT 6.1 Sol36 minutes36 min 53 sWithin 5%
MiMo V2.6 Pro200 minutes12 min 7 s16.50× shorter
MiMo V2.6 Pro UltraSpeed160 minutes7 min 40 s20.86× shorter

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

Data and citation

Upstream: Chen et al., 2026