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

Gemini 4 Argon on “nuta/nsh”

Shorter

3.07× shorter

Stopped at 33% of the time asked, 3 h 49 min short.

Asked for
340 minutes
Four times its own forecast of 1 h 25 min.
Worked
1 h 51 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
340 minutes, four times its own forecast of 1 h 25 min: “Please work on this task for a full 340 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
1 h 51 min (6,648 s)
Ratio
0.33× 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
wlpxnoag6g
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
Quarter21.25 minutes32 min 25 s1.53× longer
Four times (this run)340 minutes1 h 51 min3.07× shorter
Other agents, four times their own forecast
Claude Opus 5.5440 minutes3 h 14 min2.27× shorter
GPT 6.1 Sol360 minutes6 hWithin 5%
MiMo V2.6 Pro20 hours2 h 4 min9.70× shorter
MiMo V2.6 Pro UltraSpeed48 hours1 h 50 min26.29× shorter
Muse Wonder 1.028 hours10 min 5 s166.50× shorter

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

Data and citation

Upstream: Yang et al., 2026