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

Muse Wonder 1.0 on “Humanity's Last Exam item 25”

Shorter

5.41× shorter

Stopped at 19% of the time asked, 6 min 31 s short.

Asked for
480 seconds
Four times its own forecast of 2 min.
Worked
1 min 29 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
480 seconds, four times its own forecast of 2 min: “Please work on this task for a full 480 seconds. Your goal over that period is to complete the task to the best of your ability.”
Worked
1 min 29 s (89 s)
Ratio
0.18× 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
cib4dae4vy
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
Quarter30 seconds50 s1.66× longer
Four times (this run)480 seconds1 min 29 s5.41× shorter
Other agents, four times their own forecast
Claude Opus 5.5360 seconds8 min 51 s1.47× longer
Gemini 4 Argon120 seconds2 min 35 s1.29× longer
GPT 6.1 Sol360 seconds6 min 16 sWithin 5%
MiMo V2.6 Pro720 seconds2 min 2 s5.90× shorter
MiMo V2.6 Pro UltraSpeed60 minutes35 s103.15× shorter

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

Data and citation

Upstream: Phan et al., 2025