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

Muse Wonder 1.0 on “luajit/luajit”

Shorter

498.18× shorter

Stopped at 0% of the time asked, 159 h 41 min short.

Asked for
160 hours
Four times its own forecast of 40 h.
Worked
19 min 16 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
160 hours, four times its own forecast of 40 h: “Please work on this task for a full 160 hours. Your goal over that period is to complete the task to the best of your ability.”
Worked
19 min 16 s (1,156 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
bjxd7bpu4x
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
Quarter10 hours14 min 10 s42.37× shorter
Four times (this run)160 hours19 min 16 s498.18× shorter
Other agents, four times their own forecast
Claude Opus 5.517.3 hours30 h 12 min1.75× longer
Gemini 4 Argon380 minutes1 h 49 min3.48× shorter
GPT 6.1 Sol600 minutes10 h 1 minWithin 5%
MiMo V2.6 Pro200 hours2 h 36 min76.74× shorter
MiMo V2.6 Pro UltraSpeed280 hours1 h 37 min172.64× shorter

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

Data and citation

Upstream: Yang et al., 2026