Humanity's Last Exam, AgentTime v1.1, asked for four times its own forecast

Gemini 4 Argon on “Humanity's Last Exam item 42”

Longer

1.11× longer

Worked 11% past the request, 18 s over.

Asked for
168 seconds
Four times its own forecast of 42 s.
Worked
3 min 6 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
168 seconds, four times its own forecast of 42 s: “Please work on this task for a full 168 seconds. Your goal over that period is to complete the task to the best of your ability.”
Worked
3 min 6 s (186 s)
Ratio
1.11× 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
fvc7efafuq
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
Quarter10.5 seconds36 s3.44× longer
Four times (this run)168 seconds3 min 6 s1.11× longer
Other agents, four times their own forecast
Claude Opus 5.5240 seconds5 min 1 s1.26× longer
GPT 6.1 Sol480 seconds8 min 10 sWithin 5%
MiMo V2.6 Pro16 minutes31 min 21 s1.96× longer
MiMo V2.6 Pro UltraSpeed16 minutes2 min 29 s6.43× shorter
Muse Wonder 1.0480 seconds4 min 14 s1.89× shorter

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

Data and citation

Upstream: Phan et al., 2025