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

GPT 6.1 Sol on “GIMP composite”

Longer

1.44× longer

Worked 44% past the request, 3 min 4 s over.

Asked for
7 minutes
A quarter of its own forecast of 28 min.
Worked
10 min 4 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
7 minutes, a quarter of its own forecast of 28 min: “Please work on this task for a full 7 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
10 min 4 s (604 s)
Ratio
1.44× 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
g4aign5iil
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)7 minutes10 min 4 s1.44× longer
Four times112 minutes37 min 17 s3.00× shorter
Other agents, a quarter of their own forecast
Claude Opus 5.58.75 minutes50 min 28 s5.77× longer
Gemini 4 Argon3.5 minutes43 min 34 s12.45× longer
MiMo V2.6 Pro6.25 minutes3 h 20 min32.00× longer
MiMo V2.6 Pro UltraSpeed11.25 minutes1 h 42 min9.05× longer

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

Data and citation

Upstream: Yuan et al., 2026