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

Muse Wonder 1.0 on “BrowseComp question 3”

Shorter

4.45× shorter

Stopped at 22% of the time asked, 1 h 14 min short.

Asked for
96 minutes
Four times its own forecast of 24 min.
Worked
21 min 36 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
21 min 36 s (1,296 s)
Ratio
0.22× 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
6tweuscif4
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 minutes16 min 13 s2.70× longer
Four times (this run)96 minutes21 min 36 s4.45× shorter
Other agents, four times their own forecast
Claude Opus 5.580 minutes1 h 9 min1.15× shorter
Gemini 4 Argon24 minutes24 min 18 sWithin 5%
GPT 6.1 Sol96 minutes1 h 37 minWithin 5%
MiMo V2.6 Pro280 minutes17 min 31 s15.98× shorter
MiMo V2.6 Pro UltraSpeed152 minutes13 min 14 s11.48× shorter

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

Data and citation

Upstream: Wei et al., 2025