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

Gemini 4 Argon on “Complete a German month-end Intrastat filing across services”

Longer

1.39× longer

Worked 39% past the request, 27 min 57 s over.

Asked for
72 minutes
Four times its own forecast of 18 min.
Worked
1 h 40 min
Grade
Not graded
How it ended
Ended on its own
Every detail of this run
Agent
Gemini 4 Argon, in Antigravity CLI
Asked for
72 minutes, four times its own forecast of 18 min: “Please work on this task for a full 72 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
1 h 40 min (5,997 s)
Ratio
1.39× 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
hlfxl4qzwb
Data release
2 Nov 2026
The other ask for Gemini 4 Argon on this task, and the other agents at the same share of their own time
Argon on this taskAskedWorkedSplitResult
Quarter4.5 minutes57 min 33 s12.79× longer
Four times (this run)72 minutes1 h 40 min1.39× longer
Other agents, four times their own forecast
Claude Opus 5.5220 minutes46 s285.71× shorter
GPT 6.1 Sol140 minutes2 h 21 minWithin 5%
MiMo V2.6 Pro440 minutes27 min 6 s16.24× shorter
MiMo V2.6 Pro UltraSpeed320 minutes23 min 27 s13.65× shorter
Muse Wonder 1.0360 minutes27 min 20 s13.17× shorter

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

Data and citation

Upstream: Merrill et al., 2026 (ICLR)