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

Muse Wonder 1.0 on “johnkerl/miller”

Shorter

221.12× shorter

Stopped at 0% of the time asked, 72 h 58 min short.

Asked for
73.3 hours
Four times its own forecast of 18 h 20 min.
Worked
19 min 53 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
73.3 hours, four times its own forecast of 18 h 20 min: “Please work on this task for a full 73.3 hours. Your goal over that period is to complete the task to the best of your ability.”
Worked
19 min 53 s (1,193 s)
Ratio
0.00× 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
vj7pmatky3
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
Quarter4.58 hours1 h 46 min2.59× shorter
Four times (this run)73.3 hours19 min 53 s221.12× shorter
Other agents, four times their own forecast
Claude Opus 5.520 hours9 h 42 min2.06× shorter
Gemini 4 Argon480 minutes1 h 47 min4.48× shorter
GPT 6.1 Sol480 minutes8 h 1 minWithin 5%
MiMo V2.6 Pro40 hours54 min 12 s44.28× shorter
MiMo V2.6 Pro UltraSpeed160 hours4 h 35 min34.90× shorter

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

Data and citation

Upstream: Yang et al., 2026