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 25”

Shorter

103.15× shorter

Stopped at 1% of the time asked, 59 min 25 s short.

Asked for
60 minutes
Four times its own forecast of 15 min.
Worked
35 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
60 minutes, four times its own forecast of 15 min: “Please work on this task for a full 60 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
35 s (35 s)
Ratio
0.01× 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
42ysalizsr
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
Quarter3.75 minutes10 s23.68× shorter
Four times (this run)60 minutes35 s103.15× 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
Muse Wonder 1.0480 seconds1 min 29 s5.41× shorter

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

Data and citation

Upstream: Phan et al., 2025