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

Muse Wonder 1.0 on “BrowseComp question 1”

Longer

1.96× longer

Worked 96% past the request, 9 min 37 s over.

Asked for
10 minutes
A quarter of its own forecast of 40 min.
Worked
19 min 37 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
10 minutes, a quarter of its own forecast of 40 min: “Please work on this task for a full 10 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
19 min 37 s (1,177 s)
Ratio
1.96× 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
cgyoucx3iz
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)10 minutes19 min 37 s1.96× longer
Four times160 minutes2 h 31 min1.06× shorter
Other agents, a quarter of their own forecast
Claude Opus 5.57.5 minutes49 min 47 s6.64× longer
Gemini 4 Argon3.5 minutes4 min 9 s1.18× longer
GPT 6.1 Sol6.25 minutes6 min 26 sWithin 5%
MiMo V2.6 Pro18.75 minutes1 h 2 min3.31× longer
MiMo V2.6 Pro UltraSpeed11.25 minutes5 min 53 s1.91× shorter

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

Data and citation

Upstream: Wei et al., 2025