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

Gemini 4 Argon on “Young’s modulus report and fitted graph”

Longer

1.61× longer

Worked 61% past the request, 36 min 29 s over.

Asked for
60 minutes
Four times its own forecast of 15 min.
Worked
1 h 36 min
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
1 h 36 min (5,789 s)
Ratio
1.61× 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
fr4kzeak3j
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 minutes40 min 3 s10.68× longer
Four times (this run)60 minutes1 h 36 min1.61× longer
Other agents, four times their own forecast
Claude Opus 5.5180 minutes1 h 16 min2.36× shorter
GPT 6.1 Sol160 minutes2 h 42 minWithin 5%
MiMo V2.6 Pro288 minutes3 h 37 min1.33× shorter
MiMo V2.6 Pro UltraSpeed340 minutes3 h 27 min1.64× shorter

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

Data and citation

Upstream: Yuan et al., 2026