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

Gemini 4 Argon on “rvben/rumdl”

Longer

1.62× longer

Worked 62% past the request, 17 min 48 s over.

Asked for
28.75 minutes
A quarter of its own forecast of 1 h 55 min.
Worked
46 min 33 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
28.75 minutes, a quarter of its own forecast of 1 h 55 min: “Please work on this task for a full 28.75 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
46 min 33 s (2,793 s)
Ratio
1.62× 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
dtmbsarohc
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)28.75 minutes46 min 33 s1.62× longer
Four times460 minutes50 min 13 s9.16× shorter
Other agents, a quarter of their own forecast
Claude Opus 5.51 hour54 min 56 s1.09× shorter
GPT 6.1 Sol30 minutes30 min 23 sWithin 5%
MiMo V2.6 Pro5 hours51 min 44 s5.80× shorter
MiMo V2.6 Pro UltraSpeed6.25 hours1 h 54 min3.30× shorter
Muse Wonder 1.04 hours12 min 18 s19.51× shorter

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

Data and citation

Upstream: Yang et al., 2026