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

Muse Wonder 1.0 on “BrowseComp question 7”

Shorter

50.04× shorter

Stopped at 2% of the time asked, 1 h 34 min short.

Asked for
96 minutes
Four times its own forecast of 24 min.
Worked
1 min 55 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
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
1 min 55 s (115 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
izshribfiu
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 minutes3 min 22 s1.78× shorter
Four times (this run)96 minutes1 min 55 s50.04× shorter
Other agents, four times their own forecast
Claude Opus 5.520 minutes21 min 1 s1.05× longer
Gemini 4 Argon480 seconds8 min 29 s1.06× longer
GPT 6.1 Sol24 minutes24 min 18 sWithin 5%
MiMo V2.6 Pro120 minutes40 min 10 s2.99× shorter
MiMo V2.6 Pro UltraSpeed140 minutes3 min 58 s35.26× shorter

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

Data and citation

Upstream: Wei et al., 2025