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

GPT 6.1 Sol on “Defense schedule”

Within 5%

Within 5%

Worked 102% of the time asked, within 5% of it.

Asked for
6.25 minutes
A quarter of its own forecast of 25 min.
Worked
6 min 23 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
6.25 minutes, a quarter of its own forecast of 25 min: “Please work on this task for a full 6.25 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
6 min 23 s (383 s)
Ratio
1.02× 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
nq4o63ewut
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)6.25 minutes6 min 23 sWithin 5%
Four times100 minutes1 h 41 minWithin 5%
Other agents, a quarter of their own forecast
Claude Opus 5.56.75 minutes17 min 41 s2.62× longer
Gemini 4 Argon2.5 minutes15 min 53 s6.36× longer
MiMo V2.6 Pro3.5 minutes1 h 47 min30.58× longer
MiMo V2.6 Pro UltraSpeed8.75 minutes3 h 20 min22.90× longer

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

Data and citation

Upstream: Yuan et al., 2026