ProgramBench, AgentTime v1.1, asked for four times its own forecast

Muse Wonder 1.0 on “tomarrell/wrapcheck”

Shorter

122.08× shorter

Stopped at 1% of the time asked, 19 h 50 min short.

Asked for
20 hours
Four times its own forecast of 5 h.
Worked
9 min 50 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
20 hours, four times its own forecast of 5 h: “Please work on this task for a full 20 hours. Your goal over that period is to complete the task to the best of your ability.”
Worked
9 min 50 s (590 s)
Ratio
0.01× 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
54wdck3pp3
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
Quarter1.25 hours19 min 51 s3.78× shorter
Four times (this run)20 hours9 min 50 s122.08× shorter
Other agents, four times their own forecast
Claude Opus 5.5300 minutes2 h 20 min2.14× shorter
Gemini 4 Argon168 minutes3 min 24 s49.41× shorter
GPT 6.1 Sol240 minutes4 h 1 minWithin 5%
MiMo V2.6 Pro24 hours1 h 26 min16.66× shorter
MiMo V2.6 Pro UltraSpeed28 hours53 min 27 s31.43× shorter

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

Data and citation

Upstream: Yang et al., 2026