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 44”

Within 5%

Within 5%

Worked 98% of the time asked, within 5% of it.

Asked for
30 seconds
A quarter of its own forecast of 2 min.
Worked
30 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
30 seconds, a quarter of its own forecast of 2 min: “Please work on this task for a full 30 seconds. Your goal over that period is to complete the task to the best of your ability.”
Worked
30 s (30 s)
Ratio
0.98× 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
urz5xifc22
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)30 seconds30 sWithin 5%
Four times480 seconds2 min 13 s3.61× shorter
Other agents, a quarter of their own forecast
Claude Opus 5.522.5 seconds2 min 52 s7.64× longer
Gemini 4 Argon7.5 seconds2 min 1 s16.11× longer
GPT 6.1 Sol22.5 seconds1 min 3 s2.81× longer
MiMo V2.6 Pro1.75 minutes4 min 38 s2.65× longer
MiMo V2.6 Pro UltraSpeed45 seconds46 sWithin 5%

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

Data and citation

Upstream: Phan et al., 2025