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

Gemini 4 Argon on “Recalculate SA-CCR exposure, RWA, capital, and workbook evidence”

Shorter

3.04× shorter

Stopped at 33% of the time asked, 48 min 17 s short.

Asked for
72 minutes
Four times its own forecast of 18 min.
Worked
23 min 43 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
23 min 43 s (1,423 s)
Ratio
0.33× 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
mb2nn44bze
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 8 s3.14× longer
Four times (this run)72 minutes23 min 43 s3.04× shorter
Other agents, four times their own forecast
Claude Opus 5.5120 minutes34 min 43 s3.46× shorter
GPT 6.1 Sol88 minutes1 h 29 minWithin 5%
MiMo V2.6 Pro720 minutes22 min 58 s31.36× shorter
MiMo V2.6 Pro UltraSpeed380 minutes8 min 1 s47.38× shorter
Muse Wonder 1.0640 minutes5 min128.00× shorter

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

Data and citation

Upstream: Merrill et al., 2026 (ICLR)