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

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

Shorter

3.72× shorter

Stopped at 27% of the time asked, 5 h 51 min short.

Asked for
480 minutes
Four times its own forecast of 2 h.
Worked
2 h 9 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
480 minutes, four times its own forecast of 2 h: “Please work on this task for a full 480 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
2 h 9 min (7,743 s)
Ratio
0.27× 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
fdxcszk4d3
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
Quarter30 minutes1 h 18 min2.59× longer
Four times (this run)480 minutes2 h 9 min3.72× 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 Pro UltraSpeed600 minutes34 min 58 s17.16× 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)