Sakana ALE-Bench, AgentTime v1.1, asked for four times its own forecast

Muse Wonder 1.0 on “AtCoder Heuristic Contest 39”

Shorter

77.28× shorter

Stopped at 1% of the time asked, 10 h 51 min short.

Asked for
660 minutes
Four times its own forecast of 2 h 45 min.
Worked
8 min 32 s
Grade
Not graded
How it ended
Ended on its own
Every detail of this run
Agent
Muse Wonder 1.0, in Muse Code
Asked for
660 minutes, four times its own forecast of 2 h 45 min: “Please work on this task for a full 660 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
8 min 32 s (512 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
vc4gsykqq5
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
Quarter41.25 minutes2 min 35 s15.99× shorter
Four times (this run)660 minutes8 min 32 s77.28× shorter
Other agents, four times their own forecast
Claude Opus 5.5240 minutes3 h 19 min1.21× shorter
Gemini 4 Argon180 minutes3 min 13 s55.90× shorter
GPT 6.1 Sol140 minutes2 h 21 minWithin 5%
MiMo V2.6 Pro16 hours1 h 1 min15.81× shorter
MiMo V2.6 Pro UltraSpeed20 hours3 h 53 min5.15× shorter

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

Data and citation

Upstream: Imajuku et al., 2025