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

Muse Wonder 1.0 on “doxygen/doxygen”

Shorter

32.63× shorter

Stopped at 3% of the time asked, 69 h 48 min short.

Asked for
72 hours
Four times its own forecast of 18 h.
Worked
2 h 12 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
ProgramBench
Asked for
72 hours, four times its own forecast of 18 h: “Please work on this task for a full 72 hours. Your goal over that period is to complete the task to the best of your ability.”
Worked
2 h 12 min (7,945 s)
Ratio
0.03× 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
64iihgkfye
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
Quarter4.5 hoursno run
Four times (this run)72 hours2 h 12 min32.63× shorter
Other agents, four times their own forecast
Claude Opus 5.516 hours14 h 54 min1.07× shorter
Gemini 4 Argon420 minutes2 h 21 min2.98× shorter
GPT 6.1 Sol420 minutes7 hWithin 5%
MiMo V2.6 Pro200 hours1 h 10 min172.34× shorter
MiMo V2.6 Pro UltraSpeed60 hours1 h 14 min48.89× shorter

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

Data and citation

Upstream: Yang et al., 2026