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

Muse Wonder 1.0 on “ninja-build/ninja”

Shorter

10.73× shorter

Stopped at 9% of the time asked, 2 h 57 min short.

Asked for
3.25 hours
A quarter of its own forecast of 13 h.
Worked
18 min 10 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
3.25 hours, a quarter of its own forecast of 13 h: “Please work on this task for a full 3.25 hours. Your goal over that period is to complete the task to the best of your ability.”
Worked
18 min 10 s (1,090 s)
Ratio
0.09× 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
7hbhpn3bl7
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)3.25 hours18 min 10 s10.73× shorter
Four times52 hours12 min 4 s258.49× shorter
Other agents, a quarter of their own forecast
Claude Opus 5.545 minutes1 h 34 min2.08× longer
Gemini 4 Argon18.75 minutes44 min 22 s2.37× longer
GPT 6.1 Sol17.5 minutes17 min 58 sWithin 5%
MiMo V2.6 Pro3 hours1 h 15 min2.40× shorter
MiMo V2.6 Pro UltraSpeed10 hours1 h 10 min8.53× shorter

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

Data and citation

Upstream: Yang et al., 2026