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

GPT 6.1 Sol on “Reimbursement package”

Longer

1.11× longer

Worked 11% past the request, 41 s over.

Asked for
6.5 minutes
A quarter of its own forecast of 26 min.
Worked
7 min 11 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
6.5 minutes, a quarter of its own forecast of 26 min: “Please work on this task for a full 6.5 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
7 min 11 s (431 s)
Ratio
1.11× 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
mzx3z6o3uc
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)6.5 minutes7 min 11 s1.11× longer
Four times104 minutes1 h 45 minWithin 5%
Other agents, a quarter of their own forecast
Claude Opus 5.58.75 minutes10 min 11 s1.16× longer
Gemini 4 Argon3 minutes31 min 7 s10.37× longer
MiMo V2.6 Pro5 minutes44 min 32 s8.91× longer
MiMo V2.6 Pro UltraSpeed5.5 minutes1 h 9 min12.56× longer
Muse Wonder 1.08 minutes35 min 44 s4.47× longer

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

Data and citation

Upstream: Yuan et al., 2026