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

Muse Wonder 1.0 on “AtCoder Heuristic Contest 46”

Shorter

107.53× shorter

Stopped at 1% of the time asked, 8 h 15 min short.

Asked for
500 minutes
Four times its own forecast of 2 h 5 min.
Worked
4 min 39 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
500 minutes, four times its own forecast of 2 h 5 min: “Please work on this task for a full 500 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
4 min 39 s (279 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
wkwqaooap7
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
Quarter31.25 minutes1 min 14 s25.41× shorter
Four times (this run)500 minutes4 min 39 s107.53× shorter
Other agents, four times their own forecast
Claude Opus 5.5300 minutes3 h 38 min1.38× shorter
Gemini 4 Argon120 minutes1 h 43 min1.16× shorter
GPT 6.1 Sol140 minutes2 h 21 minWithin 5%
MiMo V2.6 Pro660 minutes2 h 5 min5.29× shorter
MiMo V2.6 Pro UltraSpeed600 minutes44 min 59 s13.34× shorter

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

Data and citation

Upstream: Imajuku et al., 2025