BrowseComp, AgentTime v1.1, asked for four times its own forecast

Muse Wonder 1.0 on “BrowseComp question 6”

Shorter

18.90× shorter

Stopped at 5% of the time asked, 1 h 8 min short.

Asked for
72 minutes
Four times its own forecast of 18 min.
Worked
3 min 49 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
72 minutes, four times its own forecast of 18 min: “Please work on this task for a full 72 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
3 min 49 s (229 s)
Ratio
0.05× 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
2qizqdimcx
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
Quarter4.5 minutes5 min 19 s1.18× longer
Four times (this run)72 minutes3 min 49 s18.90× shorter
Other agents, four times their own forecast
Claude Opus 5.5720 seconds12 min 27 sWithin 5%
Gemini 4 Argon20 minutes21 min 47 s1.09× longer
GPT 6.1 Sol32 minutes32 min 42 sWithin 5%
MiMo V2.6 Pro128 minutes28 min 10 s4.54× shorter
MiMo V2.6 Pro UltraSpeed132 minutes3 min 1 s43.78× shorter

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

Data and citation

Upstream: Wei et al., 2025