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

Gemini 4 Argon on “tomarrell/wrapcheck”

Longer

4.26× longer

Worked 326% past the request, 34 min 13 s over.

Asked for
10.5 minutes
A quarter of its own forecast of 42 min.
Worked
44 min 43 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
10.5 minutes, a quarter of its own forecast of 42 min: “Please work on this task for a full 10.5 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
44 min 43 s (2,683 s)
Ratio
4.26× 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
lfdo6visii
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)10.5 minutes44 min 43 s4.26× longer
Four times168 minutes3 min 24 s49.41× shorter
Other agents, a quarter of their own forecast
Claude Opus 5.518.75 minutes5 min 4 s3.71× shorter
GPT 6.1 Sol15 minutes15 min 18 sWithin 5%
MiMo V2.6 Pro1.5 hours1 h 19 min1.14× shorter
MiMo V2.6 Pro UltraSpeed1.75 hours1 h 19 min1.33× shorter
Muse Wonder 1.01.25 hours19 min 51 s3.78× shorter

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

Data and citation

Upstream: Yang et al., 2026