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

Gemini 4 Argon on “typst/typst”

Shorter

5.29× shorter

Stopped at 19% of the time asked, 5 h 57 min short.

Asked for
440 minutes
Four times its own forecast of 1 h 50 min.
Worked
1 h 23 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
440 minutes, four times its own forecast of 1 h 50 min: “Please work on this task for a full 440 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
1 h 23 min (4,994 s)
Ratio
0.19× 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
f7egm3d5qk
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
Quarter27.5 minutes7 min 22 s3.73× shorter
Four times (this run)440 minutes1 h 23 min5.29× shorter
Other agents, four times their own forecast
Claude Opus 5.516 hours15 h 41 minWithin 5%
GPT 6.1 Sol420 minutes7 hWithin 5%
MiMo V2.6 Pro84 hours36 h 22 min2.31× shorter
MiMo V2.6 Pro UltraSpeed80 hours1 h 22 min58.54× shorter
Muse Wonder 1.0120 hours22 min 37 s318.30× shorter

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

Data and citation

Upstream: Yang et al., 2026