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

Muse Wonder 1.0 on “Humanity's Last Exam item 39”

Shorter

1.75× shorter

Stopped at 57% of the time asked, 1 min 43 s short.

Asked for
240 seconds
Four times its own forecast of 1 min.
Worked
2 min 17 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
240 seconds, four times its own forecast of 1 min: “Please work on this task for a full 240 seconds. Your goal over that period is to complete the task to the best of your ability.”
Worked
2 min 17 s (137 s)
Ratio
0.57× 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
upnb2eqjdw
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
Quarter15 seconds35 s2.36× longer
Four times (this run)240 seconds2 min 17 s1.75× shorter
Other agents, four times their own forecast
Claude Opus 5.5360 seconds8 min 55 s1.49× longer
Gemini 4 Argon96 seconds2 min 36 s1.62× longer
GPT 6.1 Sol360 seconds6 min 12 sWithin 5%
MiMo V2.6 Pro480 seconds31 min 33 s3.94× longer
MiMo V2.6 Pro UltraSpeed720 seconds14 min 8 s1.18× longer

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

Data and citation

Upstream: Phan et al., 2025