OSWorld 2.0, AgentTime v1.1, asked for four times its own forecast

Gemini 4 Argon on “GeoGebra vase and volume”

Shorter

1.42× shorter

Stopped at 70% of the time asked, 17 min 50 s short.

Asked for
60 minutes
Four times its own forecast of 15 min.
Worked
42 min 10 s
Grade
Not graded
How it ended
Ended on its own
Every detail of this run
Agent
Gemini 4 Argon, in Antigravity CLI
Benchmark
OSWorld 2.0
Asked for
60 minutes, four times its own forecast of 15 min: “Please work on this task for a full 60 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
42 min 10 s (2,530 s)
Ratio
0.70× 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
3kgnisclfs
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
Quarter3.75 minutes24 min 1 s6.41× longer
Four times (this run)60 minutes42 min 10 s1.42× shorter
Other agents, four times their own forecast
Claude Opus 5.5100 minutes1 h 54 min1.14× longer
GPT 6.1 Sol100 minutes1 h 2 min1.62× shorter
MiMo V2.6 Pro200 minutes1 h 16 min2.62× shorter
MiMo V2.6 Pro UltraSpeed192 minutes4 h 52 min1.52× longer
Muse Wonder 1.0240 minutes16 min 31 s14.53× shorter

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

Data and citation

Upstream: Yuan et al., 2026