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

Gemini 4 Argon on “Run the canonical one-year startup simulation with seed 4”

Longer

1.25× longer

Worked 25% past the request, 25 min 1 s over.

Asked for
100 minutes
Four times its own forecast of 25 min.
Worked
2 h 5 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
100 minutes, four times its own forecast of 25 min: “Please work on this task for a full 100 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
2 h 5 min (7,501 s)
Ratio
1.25× 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
n2fhrcnx7h
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
Quarter6.25 minutes25 min 2 s4.01× longer
Four times (this run)100 minutes2 h 5 min1.25× longer
Other agents, four times their own forecast
Claude Opus 5.5440 minutes2 h 36 min2.82× shorter
GPT 6.1 Sol200 minutes3 h 28 minWithin 5%
MiMo V2.6 Pro320 minutes1 h 25 min3.76× shorter
MiMo V2.6 Pro UltraSpeed288 minutes38 min 58 s7.39× shorter
Muse Wonder 1.0380 minutes9 min 12 s41.30× shorter

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

Data and citation

Upstream: He et al., 2026