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

Muse Wonder 1.0 on “BrowseComp question 5”

Within 5%

Within 5%

Worked 102% of the time asked, within 5% of it.

Asked for
96 minutes
Four times its own forecast of 24 min.
Worked
1 h 38 min
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 h 38 min (5,863 s)
Ratio
1.02× 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
5cceoimwbq
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 23 s1.06× longer
Four times (this run)96 minutes1 h 38 minWithin 5%
Other agents, four times their own forecast
Claude Opus 5.588 minutes49 min 18 s1.79× shorter
Gemini 4 Argon20 minutes20 min 15 sWithin 5%
GPT 6.1 Sol80 minutes1 h 21 minWithin 5%
MiMo V2.6 Pro72 minutes29 min 6 s2.47× shorter
MiMo V2.6 Pro UltraSpeed140 minutes17 min 51 s7.84× shorter

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

Data and citation

Upstream: Wei et al., 2025