Terminal-Bench 4.0, AgentTime v1.1, asked for four times its own forecast

MiMo V2.6 Pro UltraSpeed on “Rebuild a retired production risk scorer from black-box behavior”

Shorter

17.16× shorter

Stopped at 6% of the time asked, 9 h 25 min short.

Asked for
600 minutes
Four times its own forecast of 2 h 30 min.
Worked
34 min 58 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
600 minutes, four times its own forecast of 2 h 30 min: “Please work on this task for a full 600 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
34 min 58 s (2,098 s)
Ratio
0.06× 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
6q35toejmq
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
Quarter37.5 minutes17 min 44 s2.12× shorter
Four times (this run)600 minutes34 min 58 s17.16× shorter
Other agents, four times their own forecast
Claude Opus 5.5220 minutes51 min 46 s4.25× shorter
Gemini 4 Argon80 minutes21 min 54 s3.65× shorter
GPT 6.1 Sol200 minutes3 h 21 minWithin 5%
MiMo V2.6 Pro480 minutes2 h 9 min3.72× shorter
Muse Wonder 1.0360 minutes13 min 14 s27.21× shorter

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

Data and citation

Upstream: Merrill et al., 2026 (ICLR)