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

GPT 6.1 Sol on “Blender logo and Impress”

Longer

1.08× longer

Worked 8% past the request, 47 s over.

Asked for
9.5 minutes
A quarter of its own forecast of 38 min.
Worked
10 min 17 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
9.5 minutes, a quarter of its own forecast of 38 min: “Please work on this task for a full 9.5 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
10 min 17 s (617 s)
Ratio
1.08× 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
34ses6ccrc
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)9.5 minutes10 min 17 s1.08× longer
Four times152 minutes2 h 34 minWithin 5%
Other agents, a quarter of their own forecast
Claude Opus 5.512.5 minutes12 min 35 sWithin 5%
Gemini 4 Argon6.25 minutes8 min 12 s1.31× longer
MiMo V2.6 Pro11.25 minutes1 h 31 min8.13× longer
MiMo V2.6 Pro UltraSpeed10 minutes3 h 20 min19.98× longer
Muse Wonder 1.012 minutes46 min 12 s3.85× longer

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

Data and citation

Upstream: Yuan et al., 2026