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

Muse Wonder 1.0 on “nuta/nsh”

Shorter

3.84× shorter

Stopped at 26% of the time asked, 1 h 18 min short.

Asked for
1.75 hours
A quarter of its own forecast of 7 h.
Worked
27 min 22 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
1.75 hours, a quarter of its own forecast of 7 h: “Please work on this task for a full 1.75 hours. Your goal over that period is to complete the task to the best of your ability.”
Worked
27 min 22 s (1,642 s)
Ratio
0.26× 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
jzp5uvqbyz
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)1.75 hours27 min 22 s3.84× shorter
Four times28 hours10 min 5 s166.50× shorter
Other agents, a quarter of their own forecast
Claude Opus 5.527.5 minutes21 min 23 s1.29× shorter
Gemini 4 Argon21.25 minutes32 min 25 s1.53× longer
GPT 6.1 Sol22.5 minutes22 min 50 sWithin 5%
MiMo V2.6 Pro1.25 hours1 h 10 min1.07× shorter
MiMo V2.6 Pro UltraSpeed3 hours1 h 58 min1.53× shorter

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

Data and citation

Upstream: Yang et al., 2026