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

Muse Wonder 1.0 on “facebook/zstd”

Shorter

46.53× shorter

Stopped at 2% of the time asked, 4 h 10 min short.

Asked for
4.25 hours
A quarter of its own forecast of 17 h.
Worked
5 min 29 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
4.25 hours, a quarter of its own forecast of 17 h: “Please work on this task for a full 4.25 hours. Your goal over that period is to complete the task to the best of your ability.”
Worked
5 min 29 s (329 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
ggiwnnh6uq
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)4.25 hours5 min 29 s46.53× shorter
Four times68 hours8 min 47 s464.16× shorter
Other agents, a quarter of their own forecast
Claude Opus 5.545 minutes43 min 40 sWithin 5%
Gemini 4 Argon18.75 minutes12 min 10 s1.54× shorter
GPT 6.1 Sol30 minutes31 min 11 sWithin 5%
MiMo V2.6 Pro10 hours1 h 32 min6.55× shorter
MiMo V2.6 Pro UltraSpeed8.75 hours52 min 41 s9.97× shorter

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

Data and citation

Upstream: Yang et al., 2026