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

Gemini 4 Argon on “Run the current one-year startup simulation, official seed 2”

Longer

1.28× longer

Worked 28% past the request, 35 min 55 s over.

Asked for
128 minutes
Four times its own forecast of 32 min.
Worked
2 h 44 min
Grade
Not graded
How it ended
Ended on its own
Every detail of this run
Agent
Gemini 4 Argon, in Antigravity CLI
Benchmark
YC-Bench
Asked for
128 minutes, four times its own forecast of 32 min: “Please work on this task for a full 128 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
2 h 44 min (9,835 s)
Ratio
1.28× 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
xvtmepbwhb
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
Quarter8 minutes2 h 29 min18.61× longer
Four times (this run)128 minutes2 h 44 min1.28× longer
Other agents, four times their own forecast
Claude Opus 5.5480 minutes1 h 30 min5.36× shorter
GPT 6.1 Sol240 minutes4 hWithin 5%
MiMo V2.6 Pro800 minutes1 h 15 min10.67× shorter
MiMo V2.6 Pro UltraSpeed360 minutes1 h 11 min5.08× shorter
Muse Wonder 1.0440 minutes18 min 11 s24.19× shorter

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

Data and citation

Upstream: He et al., 2026