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

MiMo V2.6 Pro UltraSpeed on “Humanity's Last Exam item 32”

Shorter

29.44× shorter

Stopped at 3% of the time asked, 4 h 50 min short.

Asked for
300 minutes
Four times its own forecast of 1 h 15 min.
Worked
10 min 12 s
Grade
Not graded
How it ended
Ended on its own
Every detail of this run
Agent
MiMo V2.6 Pro UltraSpeed, in MiMo Code
Asked for
300 minutes, four times its own forecast of 1 h 15 min: “Please work on this task for a full 300 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
10 min 12 s (612 s)
Ratio
0.03× 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
qeye2evw3n
Data release
2 Nov 2026
The other ask for MiMo V2.6 Pro UltraSpeed on this task, and the other agents at the same share of their own time
MiMo UltraSpeed on this taskAskedWorkedSplitResult
Quarter18.75 minutes3 min 52 s4.84× shorter
Four times (this run)300 minutes10 min 12 s29.44× shorter
Other agents, four times their own forecast
Claude Opus 5.540 minutes49 min 55 s1.25× longer
Gemini 4 Argon600 seconds10 min 54 s1.09× longer
GPT 6.1 Sol40 minutes40 min 42 sWithin 5%
MiMo V2.6 Pro480 minutes45 min 21 s10.58× shorter
Muse Wonder 1.072 minutes9 min 10 s7.86× shorter

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

Data and citation

Upstream: Phan et al., 2025