Humanity's Last Exam, AgentTime v1.1, asked for four times its own forecast

Muse Wonder 1.0 on “Humanity's Last Exam item 30”

Shorter

5.73× shorter

Stopped at 17% of the time asked, 1 h 13 min short.

Asked for
88 minutes
Four times its own forecast of 22 min.
Worked
15 min 22 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
88 minutes, four times its own forecast of 22 min: “Please work on this task for a full 88 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
15 min 22 s (922 s)
Ratio
0.17× 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
qhiigqquny
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
Quarter5.5 minutes6 min 27 s1.17× longer
Four times (this run)88 minutes15 min 22 s5.73× shorter
Other agents, four times their own forecast
Claude Opus 5.568 minutes1 h 6 minWithin 5%
Gemini 4 Argon840 seconds14 min 36 sWithin 5%
GPT 6.1 Sol28 minutes28 min 21 sWithin 5%
MiMo V2.6 Pro120 minutes1 h 8 min1.76× shorter
MiMo V2.6 Pro UltraSpeed140 minutes12 min 18 s11.39× shorter

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

Data and citation

Upstream: Phan et al., 2025