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

Gemini 4 Argon on “Local event booking QA”

Within 5%

Within 5%

Worked 105% of the time asked, within 5% of it.

Asked for
36 minutes
Four times its own forecast of 9 min.
Worked
37 min 37 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
36 minutes, four times its own forecast of 9 min: “Please work on this task for a full 36 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
37 min 37 s (2,257 s)
Ratio
1.04× 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
7sejojszvn
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
Quarter2.25 minutes2 min 51 s1.27× longer
Four times (this run)36 minutes37 min 37 sWithin 5%
Other agents, four times their own forecast
Claude Opus 5.5140 minutes1 h 58 min1.19× shorter
GPT 6.1 Sol140 minutes2 h 25 minWithin 5%
MiMo V2.6 Pro180 minutes9 min 34 s18.81× shorter
MiMo V2.6 Pro UltraSpeed160 minutes5 h 20 min2.00× longer

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

Data and citation

Upstream: Yuan et al., 2026