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

Muse Wonder 1.0 on “Humanity's Last Exam item 43”

Shorter

2.45× shorter

Stopped at 41% of the time asked, 2 min 22 s short.

Asked for
240 seconds
Four times its own forecast of 1 min.
Worked
1 min 38 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
240 seconds, four times its own forecast of 1 min: “Please work on this task for a full 240 seconds. Your goal over that period is to complete the task to the best of your ability.”
Worked
1 min 38 s (98 s)
Ratio
0.41× 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
crn2nevhwk
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
Quarter15 seconds28 s1.89× longer
Four times (this run)240 seconds1 min 38 s2.45× shorter
Other agents, four times their own forecast
Claude Opus 5.5240 seconds8 min 36 s2.15× longer
Gemini 4 Argon192 seconds3 min 26 s1.07× longer
GPT 6.1 Sol288 seconds4 min 58 sWithin 5%
MiMo V2.6 Pro240 seconds2 min 16 s1.76× shorter
MiMo V2.6 Pro UltraSpeed720 seconds1 min 6 s10.89× shorter

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

Data and citation

Upstream: Phan et al., 2025