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

Gemini 4 Argon on “cweill/gotests”

Shorter

2.15× shorter

Stopped at 47% of the time asked, 2 h 19 min short.

Asked for
260 minutes
Four times its own forecast of 1 h 5 min.
Worked
2 h 1 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
260 minutes, four times its own forecast of 1 h 5 min: “Please work on this task for a full 260 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
2 h 1 min (7,260 s)
Ratio
0.47× 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
zijizqlx4q
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
Quarter16.25 minutes35 min 31 s2.19× longer
Four times (this run)260 minutes2 h 1 min2.15× shorter
Other agents, four times their own forecast
Claude Opus 5.5560 minutes8 h 14 min1.13× shorter
GPT 6.1 Sol240 minutes4 h 1 minWithin 5%
MiMo V2.6 Pro28 hours1 h 35 min17.71× shorter
MiMo V2.6 Pro UltraSpeed40 hours1 h39.91× shorter

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

Data and citation

Upstream: Yang et al., 2026