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

Muse Wonder 1.0 on “AtCoder Heuristic Contest 11”

Shorter

153.96× shorter

Stopped at 1% of the time asked, 25 h 8 min short.

Asked for
25.3 hours
Four times its own forecast of 6 h 20 min.
Worked
9 min 52 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
25.3 hours, four times its own forecast of 6 h 20 min: “Please work on this task for a full 25.3 hours. Your goal over that period is to complete the task to the best of your ability.”
Worked
9 min 52 s (592 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
fgcw4k4jwf
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
Quarter1.58 hours7 min 2 s13.49× shorter
Four times (this run)25.3 hours9 min 52 s153.96× shorter
Other agents, four times their own forecast
Claude Opus 5.5400 minutes5 h 18 min1.26× shorter
Gemini 4 Argon180 minutes1 h 13 min2.47× shorter
GPT 6.1 Sol180 minutes3 h 1 minWithin 5%
MiMo V2.6 Pro24 hours2 h 28 min9.73× shorter
MiMo V2.6 Pro UltraSpeed22 hours3 h 35 min6.13× shorter

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

Data and citation

Upstream: Imajuku et al., 2025