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

MiMo V2.6 Pro UltraSpeed on “Make a Kafka payments worker recover quickly without losing notifications”

Shorter

19.15× shorter

Stopped at 5% of the time asked, 11 h 3 min short.

Asked for
700 minutes
Four times its own forecast of 2 h 55 min.
Worked
36 min 33 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
700 minutes, four times its own forecast of 2 h 55 min: “Please work on this task for a full 700 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
36 min 33 s (2,193 s)
Ratio
0.05× 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
aooznxqsre
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
Quarter43.75 minutes17 min 47 s2.46× shorter
Four times (this run)700 minutes36 min 33 s19.15× shorter
Other agents, four times their own forecast
Claude Opus 5.5160 minutes1 h 50 min1.45× shorter
Gemini 4 Argon80 minutes55 min 22 s1.45× shorter
GPT 6.1 Sol120 minutes2 h 1 minWithin 5%
MiMo V2.6 Pro340 minutes52 min 7 s6.52× shorter
Muse Wonder 1.0340 minutes44 min 29 s7.64× shorter

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

Data and citation

Upstream: Merrill et al., 2026 (ICLR)