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

Gemini 4 Argon on “MuseScore transcription”

Shorter

1.85× shorter

Stopped at 54% of the time asked, 36 min 49 s short.

Asked for
80 minutes
Four times its own forecast of 20 min.
Worked
43 min 11 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
80 minutes, four times its own forecast of 20 min: “Please work on this task for a full 80 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
43 min 11 s (2,591 s)
Ratio
0.54× 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
2mv53c6f6c
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
Quarter5 minutes39 min 1 s7.80× longer
Four times (this run)80 minutes43 min 11 s1.85× shorter
Other agents, four times their own forecast
Claude Opus 5.5320 minutes6 h 3 min1.13× longer
GPT 6.1 Sol360 minutes4 h 14 min1.42× shorter
MiMo V2.6 Pro600 minutes6 h 6 min1.64× shorter
MiMo V2.6 Pro UltraSpeed360 minutes4 h 16 min1.41× shorter

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

Data and citation

Upstream: Yuan et al., 2026