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

Gemini 4 Argon on “canop/broot”

Longer

1.06× longer

Worked 6% past the request, 1 min 5 s over.

Asked for
18.75 minutes
A quarter of its own forecast of 1 h 15 min.
Worked
19 min 50 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
19 min 50 s (1,190 s)
Ratio
1.06× 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
am7dfurww3
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 minutes19 min 50 s1.06× longer
Four times300 minutes1 h4.97× shorter
Other agents, a quarter of their own forecast
Claude Opus 5.552.5 minutes15 min 22 s3.42× shorter
GPT 6.1 Sol37.5 minutes37 min 59 sWithin 5%
MiMo V2.6 Pro10.5 hours1 h 54 min5.52× shorter
MiMo V2.6 Pro UltraSpeed9 hours3 h 55 min2.30× shorter
Muse Wonder 1.03.75 hours21 min 1 s10.71× shorter

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

Data and citation

Upstream: Yang et al., 2026