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

Gemini 4 Argon on “Train a lake-temperature profile model from sparse observations”

Longer

1.33× longer

Worked 33% past the request, 26 min 20 s over.

Asked for
80 minutes
Four times its own forecast of 20 min.
Worked
1 h 46 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
80 minutes, four times its own forecast of 20 min: “Please work on this task for a full 80 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
1 h 46 min (6,380 s)
Ratio
1.33× 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
ioweznyiaz
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
Quarter5 minutes18 min 8 s3.63× longer
Four times (this run)80 minutes1 h 46 min1.33× longer
Other agents, four times their own forecast
Claude Opus 5.5200 minutes2 h 37 min1.27× shorter
GPT 6.1 Sol180 minutes3 h 1 minWithin 5%
MiMo V2.6 Pro720 minutes2 h 18 min5.22× shorter
MiMo V2.6 Pro UltraSpeed280 minutes2 h 36 min1.80× shorter
Muse Wonder 1.0380 minutes41 min 52 s9.08× shorter

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

Data and citation

Upstream: Merrill et al., 2026 (ICLR)