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

MiMo V2.6 Pro on “Humanity's Last Exam item 30”

Shorter

1.76× shorter

Stopped at 57% of the time asked, 51 min 48 s short.

Asked for
120 minutes
Four times its own forecast of 30 min.
Worked
1 h 8 min
Grade
Not graded
How it ended
Ended on its own
Every detail of this run
Agent
MiMo V2.6 Pro, in MiMo Code
Asked for
120 minutes, four times its own forecast of 30 min: “Please work on this task for a full 120 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
1 h 8 min (4,092 s)
Ratio
0.57× 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
h6qjc7mwti
Data release
2 Nov 2026
The other ask for MiMo V2.6 Pro on this task, and the other agents at the same share of their own time
MiMo Pro on this taskAskedWorkedSplitResult
Quarter7.5 minutes58 min 19 s7.77× longer
Four times (this run)120 minutes1 h 8 min1.76× shorter
Other agents, four times their own forecast
Claude Opus 5.568 minutes1 h 6 minWithin 5%
Gemini 4 Argon840 seconds14 min 36 sWithin 5%
GPT 6.1 Sol28 minutes28 min 21 sWithin 5%
MiMo V2.6 Pro UltraSpeed140 minutes12 min 18 s11.39× shorter
Muse Wonder 1.088 minutes15 min 22 s5.73× shorter

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

Data and citation

Upstream: Phan et al., 2025