ProgramBench, AgentTime v1.1, asked for four times its own forecast

Gemini 4 Argon on “lfos/calcurse”

Shorter

3.82× shorter

Stopped at 26% of the time asked, 4 h 26 min short.

Asked for
360 minutes
Four times its own forecast of 1 h 30 min.
Worked
1 h 34 min
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
360 minutes, four times its own forecast of 1 h 30 min: “Please work on this task for a full 360 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
1 h 34 min (5,647 s)
Ratio
0.26× 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
waanqawouo
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
Quarter22.5 minutes43 min 13 s1.92× longer
Four times (this run)360 minutes1 h 34 min3.82× shorter
Other agents, four times their own forecast
Claude Opus 5.5660 minutes10 h 35 minWithin 5%
GPT 6.1 Sol360 minutes6 hWithin 5%
MiMo V2.6 Pro60 hours1 h 31 min39.58× shorter
MiMo V2.6 Pro UltraSpeed36 hours1 h 43 min21.06× shorter

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

Data and citation

Upstream: Yang et al., 2026