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

Muse Wonder 1.0 on “jesseduffield/lazygit”

Shorter

6.53× shorter

Stopped at 15% of the time asked, 2 h 32 min short.

Asked for
3 hours
A quarter of its own forecast of 12 h.
Worked
27 min 35 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 hours, a quarter of its own forecast of 12 h: “Please work on this task for a full 3 hours. Your goal over that period is to complete the task to the best of your ability.”
Worked
27 min 35 s (1,655 s)
Ratio
0.15× 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
vsrrv52g23
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 hours27 min 35 s6.53× shorter
Four times48 hours13 min 56 s206.60× shorter
Other agents, a quarter of their own forecast
Claude Opus 5.550 minutes9 min 56 s5.03× shorter
Gemini 4 Argon21.25 minutes21 min 53 sWithin 5%
GPT 6.1 Sol30 minutes30 min 21 sWithin 5%
MiMo V2.6 Pro10 hours1 h 19 min7.58× shorter
MiMo V2.6 Pro UltraSpeed3.75 hours1 h 13 min3.09× shorter

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

Data and citation

Upstream: Yang et al., 2026