METR public tasks, AgentTime v1.1, asked for four times its own forecast

MiMo V2.6 Pro UltraSpeed on “Implement duplicate-payment detection across currencies and time zones”

Shorter

107.99× shorter

Stopped at 1% of the time asked, 18 h 32 min short.

Asked for
18.7 hours
Four times its own forecast of 4 h 40 min.
Worked
10 min 23 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
18.7 hours, four times its own forecast of 4 h 40 min: “Please work on this task for a full 18.7 hours. Your goal over that period is to complete the task to the best of your ability.”
Worked
10 min 23 s (623 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
4umi5nicyl
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
Quarter1.17 hours12 min 18 s5.71× shorter
Four times (this run)18.7 hours10 min 23 s107.99× shorter
Other agents, four times their own forecast
Claude Opus 5.5140 minutes1 h 21 min1.72× shorter
Gemini 4 Argon152 minutes38 min 2 s4.00× shorter
GPT 6.1 Sol140 minutes2 h 21 minWithin 5%
MiMo V2.6 Pro16 hours41 min 35 s23.09× shorter
Muse Wonder 1.0900 minutes9 min 19 s96.67× shorter

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

Data and citation

Upstream: Kinniment et al., 2024 (METR)