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 43”

Longer

1.89× longer

Worked 89% past the request, 13 s over.

Asked for
15 seconds
A quarter of its own forecast of 1 min.
Worked
28 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
15 seconds, a quarter of its own forecast of 1 min: “Please work on this task for a full 15 seconds. Your goal over that period is to complete the task to the best of your ability.”
Worked
28 s (28 s)
Ratio
1.89× 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
m3au3sb75j
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)15 seconds28 s1.89× longer
Four times240 seconds1 min 38 s2.45× shorter
Other agents, a quarter of their own forecast
Claude Opus 5.515 seconds2 min 33 s10.17× longer
Gemini 4 Argon12 seconds1 min 30 s7.50× longer
GPT 6.1 Sol18 seconds54 s3.02× longer
MiMo V2.6 Pro15 seconds8 min 47 s35.15× longer
MiMo V2.6 Pro UltraSpeed45 seconds44 sWithin 5%

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

Data and citation

Upstream: Phan et al., 2025