Agents' Last Exam, AgentTime v1.1, asked for a quarter of its own forecast

Gemini 4 Argon on “Build a clean retail SQLite warehouse from messy inputs”

Longer

1.90× longer

Worked 90% past the request, 3 min 8 s over.

Asked for
3.5 minutes
A quarter of its own forecast of 14 min.
Worked
6 min 38 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
3.5 minutes, a quarter of its own forecast of 14 min: “Please work on this task for a full 3.5 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
6 min 38 s (398 s)
Ratio
1.90× 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
ljh2xcgkdi
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
Quarter (this run)3.5 minutes6 min 38 s1.90× longer
Four times56 minutes14 min 58 s3.74× shorter
Other agents, a quarter of their own forecast
Claude Opus 5.58 minutes8 min 48 s1.10× longer
GPT 6.1 Sol4 minutes4 min 19 s1.08× longer
MiMo V2.6 Pro15 minutes6 min 41 s2.24× shorter
MiMo V2.6 Pro UltraSpeed15.5 minutes3 min 7 s4.98× shorter
Muse Wonder 1.012.5 minutes1 min 43 s7.27× shorter

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

Data and citation

Upstream: Sun et al., 2026