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

Gemini 4 Argon on “Repair a React lead form and its auditable CRM submission pipeline”

Shorter

2.50× shorter

Stopped at 40% of the time asked, 43 min 10 s short.

Asked for
72 minutes
Four times its own forecast of 18 min.
Worked
28 min 50 s
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
28 min 50 s (1,730 s)
Ratio
0.40× 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
63n4qzzqdv
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 minutes14 min 56 s3.32× longer
Four times (this run)72 minutes28 min 50 s2.50× shorter
Other agents, four times their own forecast
Claude Opus 5.5180 minutes1 h 29 min2.02× shorter
GPT 6.1 Sol120 minutes2 h 1 minWithin 5%
MiMo V2.6 Pro840 minutes37 min 21 s22.49× shorter
MiMo V2.6 Pro UltraSpeed16 hours16 min 3 s59.81× shorter
Muse Wonder 1.0340 minutes9 min 59 s34.03× shorter

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

Data and citation

Upstream: Merrill et al., 2026 (ICLR)