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

Gemini 4 Argon on “dandavison/delta”

Shorter

8.62× shorter

Stopped at 12% of the time asked, 5 h 18 min short.

Asked for
360 minutes
Four times its own forecast of 1 h 30 min.
Worked
41 min 46 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
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
41 min 46 s (2,506 s)
Ratio
0.12× 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
q7w4fswsef
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 minutes1 h 9 min3.07× longer
Four times (this run)360 minutes41 min 46 s8.62× shorter
Other agents, four times their own forecast
Claude Opus 5.5680 minutes10 h 24 min1.09× shorter
GPT 6.1 Sol480 minutes8 h 1 minWithin 5%
MiMo V2.6 Pro32 hours1 h 8 min28.29× shorter
MiMo V2.6 Pro UltraSpeed180 hours1 h 43 min104.83× shorter
Muse Wonder 1.064 hours18 min 38 s206.12× shorter

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

Data and citation

Upstream: Yang et al., 2026