BrowseComp, AgentTime v1.1, asked for a quarter of its own forecast

Muse Wonder 1.0 on “BrowseComp question 11”

Longer

1.20× longer

Worked 20% past the request, 1 min 44 s over.

Asked for
8.75 minutes
A quarter of its own forecast of 35 min.
Worked
10 min 29 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
BrowseComp
Asked for
8.75 minutes, a quarter of its own forecast of 35 min: “Please work on this task for a full 8.75 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
10 min 29 s (629 s)
Ratio
1.20× 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
33zcasl4ma
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)8.75 minutes10 min 29 s1.20× longer
Four times140 minutes28 min 22 s4.94× shorter
Other agents, a quarter of their own forecast
Claude Opus 5.52.25 minutes3 min 21 s1.49× longer
Gemini 4 Argon52.5 seconds1 min 10 s1.34× longer
GPT 6.1 Sol3 minutes3 min 33 s1.19× longer
MiMo V2.6 Pro13.75 minutes42 min 44 s3.11× longer
MiMo V2.6 Pro UltraSpeed16.25 minutes3 min 11 s5.12× shorter

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

Data and citation

Upstream: Wei et al., 2025