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

Muse Wonder 1.0 on “BrowseComp question 1”

Shorter

1.06× shorter

Stopped at 95% of the time asked, 8 min 38 s short.

Asked for
160 minutes
Four times its own forecast of 40 min.
Worked
2 h 31 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
160 minutes, four times its own forecast of 40 min: “Please work on this task for a full 160 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
2 h 31 min (9,082 s)
Ratio
0.95× 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
aveauttda3
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
Quarter10 minutes19 min 37 s1.96× longer
Four times (this run)160 minutes2 h 31 min1.06× shorter
Other agents, four times their own forecast
Claude Opus 5.5120 minutes1 h 9 min1.73× shorter
Gemini 4 Argon56 minutes56 min 14 sWithin 5%
GPT 6.1 Sol100 minutes1 h 41 minWithin 5%
MiMo V2.6 Pro300 minutes1 h 32 min3.26× shorter
MiMo V2.6 Pro UltraSpeed180 minutes10 min 27 s17.23× shorter

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

Data and citation

Upstream: Wei et al., 2025