ProgramBench, AgentTime v1.1, asked for a quarter of its own forecast

Gemini 4 Argon on “ninja-build/ninja”

Longer

2.37× longer

Worked 137% past the request, 25 min 37 s over.

Asked for
18.75 minutes
A quarter of its own forecast of 1 h 15 min.
Worked
44 min 22 s
Grade
Not graded
How it ended
Ended on its own
Every detail of this run
Agent
Gemini 4 Argon, in Antigravity CLI
Benchmark
ProgramBench
Asked for
18.75 minutes, a quarter of its own forecast of 1 h 15 min: “Please work on this task for a full 18.75 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
44 min 22 s (2,662 s)
Ratio
2.37× 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
v73g4nmjv2
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)18.75 minutes44 min 22 s2.37× longer
Four times300 minutes1 h 19 min3.81× shorter
Other agents, a quarter of their own forecast
Claude Opus 5.545 minutes1 h 34 min2.08× longer
GPT 6.1 Sol17.5 minutes17 min 58 sWithin 5%
MiMo V2.6 Pro3 hours1 h 15 min2.40× shorter
MiMo V2.6 Pro UltraSpeed10 hours1 h 10 min8.53× shorter
Muse Wonder 1.03.25 hours18 min 10 s10.73× shorter

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

Data and citation

Upstream: Yang et al., 2026