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

Muse Wonder 1.0 on “BrowseComp question 8”

Shorter

17.46× shorter

Stopped at 6% of the time asked, 1 h 15 min short.

Asked for
80 minutes
Four times its own forecast of 20 min.
Worked
4 min 35 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
80 minutes, four times its own forecast of 20 min: “Please work on this task for a full 80 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
4 min 35 s (275 s)
Ratio
0.06× 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
ubx6jgtz7a
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
Quarter5 minutes8 min 28 s1.69× longer
Four times (this run)80 minutes4 min 35 s17.46× shorter
Other agents, four times their own forecast
Claude Opus 5.528 minutes22 min 52 s1.22× shorter
Gemini 4 Argon840 seconds14 min 41 sWithin 5%
GPT 6.1 Sol60 minutes1 h 1 minWithin 5%
MiMo V2.6 Pro120 minutes26 min 37 s4.51× shorter
MiMo V2.6 Pro UltraSpeed168 minutes12 min 51 s13.07× shorter

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

Data and citation

Upstream: Wei et al., 2025