ProgramBench, AgentTime v1.1, asked for a quarter of its own forecast

Muse Wonder 1.0 on “typst/typst”

Shorter

42.33× shorter

Stopped at 2% of the time asked, 7 h 19 min short.

Asked for
7.5 hours
A quarter of its own forecast of 30 h.
Worked
10 min 38 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
ProgramBench
Asked for
7.5 hours, a quarter of its own forecast of 30 h: “Please work on this task for a full 7.5 hours. Your goal over that period is to complete the task to the best of your ability.”
Worked
10 min 38 s (638 s)
Ratio
0.02× 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
vxazuqxiqn
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
Quarter (this run)7.5 hours10 min 38 s42.33× shorter
Four times120 hours22 min 37 s318.30× shorter
Other agents, a quarter of their own forecast
Claude Opus 5.51 hour17 min 34 s3.42× shorter
Gemini 4 Argon27.5 minutes7 min 22 s3.73× shorter
GPT 6.1 Sol26.25 minutes26 min 37 sWithin 5%
MiMo V2.6 Pro5.25 hours2 h 25 min2.18× shorter
MiMo V2.6 Pro UltraSpeed5 hours1 h 13 min4.12× shorter

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

Data and citation

Upstream: Yang et al., 2026