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

Muse Wonder 1.0 on “stranger6667/jsonschema”

Shorter

9.83× shorter

Stopped at 10% of the time asked, 2 h 28 min short.

Asked for
2.75 hours
A quarter of its own forecast of 11 h.
Worked
16 min 47 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
2.75 hours, a quarter of its own forecast of 11 h: “Please work on this task for a full 2.75 hours. Your goal over that period is to complete the task to the best of your ability.”
Worked
16 min 47 s (1,007 s)
Ratio
0.10× 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
iz3mildsqr
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)2.75 hours16 min 47 s9.83× shorter
Four times44 hours16 min 31 s159.90× shorter
Other agents, a quarter of their own forecast
Claude Opus 5.542.5 minutes33 min 31 s1.27× shorter
Gemini 4 Argon22.5 minutes30 min 51 s1.37× longer
GPT 6.1 Sol15 minutes15 min 26 sWithin 5%
MiMo V2.6 Pro3.25 hours1 h 4 min3.05× shorter
MiMo V2.6 Pro UltraSpeed1.75 hours50 min 4 s2.10× shorter

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

Data and citation

Upstream: Yang et al., 2026