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 26”

Shorter

6.96× shorter

Stopped at 14% of the time asked, 1 h 9 min short.

Asked for
80 minutes
Four times its own forecast of 20 min.
Worked
11 min 30 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
80 minutes, four times its own forecast of 20 min: “Please work on this task for a full 80 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
11 min 30 s (690 s)
Ratio
0.14× 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
oqbsmeomjq
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
Quarter5 minutes5 min 13 sWithin 5%
Four times (this run)80 minutes11 min 30 s6.96× shorter
Other agents, four times their own forecast
Claude Opus 5.552 minutes10 min 52 s4.79× shorter
Gemini 4 Argon480 seconds8 min 35 s1.07× longer
GPT 6.1 Sol24 minutes24 min 20 sWithin 5%
MiMo V2.6 Pro100 minutes1 h 23 min1.20× shorter
Muse Wonder 1.024 minutes9 min 33 s2.51× shorter

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

Data and citation

Upstream: Phan et al., 2025