ProgramBench, AgentTime v1.1, asked for a quarter of its own forecast

Gemini 4 Argon on “ariga/atlas”

Shorter

1.10× shorter

Stopped at 91% of the time asked, 1 min 46 s short.

Asked for
18.75 minutes
A quarter of its own forecast of 1 h 15 min.
Worked
16 min 59 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
18.75 minutes, a quarter of its own forecast of 1 h 15 min: “Please work on this task for a full 18.75 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
16 min 59 s (1,019 s)
Ratio
0.91× 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
wfkgyxv6xt
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
Quarter (this run)18.75 minutes16 min 59 s1.10× shorter
Four times300 minutes1 h 18 min3.86× shorter
Other agents, a quarter of their own forecast
Claude Opus 5.552.5 minutes41 min 47 s1.26× shorter
GPT 6.1 Sol25 minutes25 min 25 sWithin 5%
MiMo V2.6 Pro7.5 hours1 h 11 min6.31× shorter
MiMo V2.6 Pro UltraSpeed5 hours44 min 7 s6.80× shorter
Muse Wonder 1.04.5 hours14 min 10 s19.05× shorter

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

Data and citation

Upstream: Yang et al., 2026