OSWorld 2.0, AgentTime v1.1, asked for a quarter of its own forecast

GPT 6.1 Sol on “Radio bumper”

Longer

1.09× longer

Worked 9% past the request, 46 s over.

Asked for
8.75 minutes
A quarter of its own forecast of 35 min.
Worked
9 min 31 s
Grade
Not graded
How it ended
Ended on its own
Every detail of this run
Agent
GPT 6.1 Sol, in Codex
Benchmark
OSWorld 2.0
Asked for
8.75 minutes, a quarter of its own forecast of 35 min: “Please work on this task for a full 8.75 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
9 min 31 s (571 s)
Ratio
1.09× 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
2whaslaiec
Data release
2 Nov 2026
The other ask for GPT 6.1 Sol on this task, and the other agents at the same share of their own time
Sol 6.1 on this taskAskedWorkedSplitResult
Quarter (this run)8.75 minutes9 min 31 s1.09× longer
Four times140 minutes2 h 22 minWithin 5%
Other agents, a quarter of their own forecast
Claude Opus 5.58 minutes31 min 56 s3.99× longer
Gemini 4 Argon3.75 minutes1 h 11 min19.05× longer
MiMo V2.6 Pro8 minutes1 h 16 min9.51× longer
MiMo V2.6 Pro UltraSpeed13.75 minutes59 min 19 s4.31× longer

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

Data and citation

Upstream: Yuan et al., 2026