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

Gemini 4 Argon on “Zotero, Obsidian, and BibTeX”

Shorter

149.25× shorter

Stopped at 1% of the time asked, 1 h 39 min short.

Asked for
100 minutes
Four times its own forecast of 25 min.
Worked
40 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
100 minutes, four times its own forecast of 25 min: “Please work on this task for a full 100 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
40 s (40 s)
Ratio
0.01× 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
tbw6onkgmj
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
Quarter6.25 minutes11 min 50 s1.89× longer
Four times (this run)100 minutes40 s149.25× shorter
Other agents, four times their own forecast
Claude Opus 5.5240 minutes1 h 17 min3.12× shorter
GPT 6.1 Sol260 minutes1 h 7 min3.88× shorter
MiMo V2.6 Pro380 minutes3 h 58 min1.60× shorter
MiMo V2.6 Pro UltraSpeed340 minutes4 h 2 min1.41× shorter

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

Data and citation

Upstream: Yuan et al., 2026