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 27”

Longer

6.06× longer

Worked 506% past the request, 5 min 4 s over.

Asked for
1 minute
A quarter of its own forecast of 4 min.
Worked
6 min 4 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
1 minute, a quarter of its own forecast of 4 min: “Please work on this task for a full 1 minute. Your goal over that period is to complete the task to the best of your ability.”
Worked
6 min 4 s (364 s)
Ratio
6.06× 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
gbmtgekwio
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)1 minute6 min 4 s6.06× longer
Four times16 minutes14 min 27 s1.11× shorter
Other agents, a quarter of their own forecast
Claude Opus 5.51.5 minutes32 min 31 s21.67× longer
Gemini 4 Argon18 seconds38 min 34 s128.54× longer
GPT 6.1 Sol45 seconds6 min 15 s8.33× longer
MiMo V2.6 Pro3 minutes1 h 9 min22.98× longer
MiMo V2.6 Pro UltraSpeed2.75 minutes6 min 43 s2.44× longer

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

Data and citation

Upstream: Phan et al., 2025