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

Muse Wonder 1.0 on “AtCoder Heuristic Contest 16”

Shorter

17.90× shorter

Stopped at 6% of the time asked, 17 h short.

Asked for
18 hours
Four times its own forecast of 4 h 30 min.
Worked
1 h
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
18 hours, four times its own forecast of 4 h 30 min: “Please work on this task for a full 18 hours. Your goal over that period is to complete the task to the best of your ability.”
Worked
1 h (3,620 s)
Ratio
0.06× 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
gnqrkh3nyd
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
Quarter1.125 hours59 min 39 s1.13× shorter
Four times (this run)18 hours1 h17.90× shorter
Other agents, four times their own forecast
Claude Opus 5.5360 minutes1 h 58 min3.06× shorter
Gemini 4 Argon180 minutes2 h 30 min1.20× shorter
GPT 6.1 Sol160 minutes2 h 41 minWithin 5%
MiMo V2.6 Pro840 minutes1 h 57 min7.17× shorter
MiMo V2.6 Pro UltraSpeed720 minutes40 min 31 s17.77× shorter

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

Data and citation

Upstream: Imajuku et al., 2025