Humanity's Last Exam, AgentTime v1.1, asked for a quarter of its own forecast

Muse Wonder 1.0 on “Humanity's Last Exam item 32”

Longer

3.17× longer

Worked 217% past the request, 9 min 45 s over.

Asked for
4.5 minutes
A quarter of its own forecast of 18 min.
Worked
14 min 15 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
4.5 minutes, a quarter of its own forecast of 18 min: “Please work on this task for a full 4.5 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
14 min 15 s (855 s)
Ratio
3.17× 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
vapikp4uv7
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
Quarter (this run)4.5 minutes14 min 15 s3.17× longer
Four times72 minutes9 min 10 s7.86× shorter
Other agents, a quarter of their own forecast
Claude Opus 5.52.5 minutes9 min 24 s3.76× longer
Gemini 4 Argon37.5 seconds2 min 23 s3.82× longer
GPT 6.1 Sol2.5 minutes3 min 55 s1.57× longer
MiMo V2.6 Pro30 minutes36 min 30 s1.22× longer
MiMo V2.6 Pro UltraSpeed18.75 minutes3 min 52 s4.84× shorter

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

Data and citation

Upstream: Phan et al., 2025