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

Muse Wonder 1.0 on “AtCoder Heuristic Contest 7”

Shorter

117.07× shorter

Stopped at 1% of the time asked, 7 h 56 min short.

Asked for
480 minutes
Four times its own forecast of 2 h.
Worked
4 min 6 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
480 minutes, four times its own forecast of 2 h: “Please work on this task for a full 480 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
4 min 6 s (246 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
rxdatcq62e
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
Quarter30 minutes8 min 42 s3.45× shorter
Four times (this run)480 minutes4 min 6 s117.07× shorter
Other agents, four times their own forecast
Claude Opus 5.5180 minutes2 h 25 min1.24× shorter
Gemini 4 Argon100 minutes1 h 36 minWithin 5%
GPT 6.1 Sol140 minutes2 h 22 minWithin 5%
MiMo V2.6 Pro900 minutes2 h 54 min5.18× shorter
MiMo V2.6 Pro UltraSpeed480 minutes1 h 56 min4.13× shorter

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

Data and citation

Upstream: Imajuku et al., 2025