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

Muse Wonder 1.0 on “ariga/atlas”

Shorter

19.05× shorter

Stopped at 5% of the time asked, 4 h 16 min short.

Asked for
4.5 hours
A quarter of its own forecast of 18 h.
Worked
14 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
4.5 hours, a quarter of its own forecast of 18 h: “Please work on this task for a full 4.5 hours. Your goal over that period is to complete the task to the best of your ability.”
Worked
14 min 10 s (850 s)
Ratio
0.05× 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
tunqunhcrl
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)4.5 hours14 min 10 s19.05× shorter
Four times72 hours2 min 10 s1990.78× shorter
Other agents, a quarter of their own forecast
Claude Opus 5.552.5 minutes41 min 47 s1.26× shorter
Gemini 4 Argon18.75 minutes16 min 59 s1.10× shorter
GPT 6.1 Sol25 minutes25 min 25 sWithin 5%
MiMo V2.6 Pro7.5 hours1 h 11 min6.31× shorter
MiMo V2.6 Pro UltraSpeed5 hours44 min 7 s6.80× shorter

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

Data and citation

Upstream: Yang et al., 2026