OSWorld 2.0, shortest of three requests

GPT 6 Astra on “Radio bumper”

Longer

1.50× longer

Worked 50% past the request, 7 min 29 s over.

Asked

Worked

Safety cutoff 8 h 20 min, off the scale

Every detail of this run

Agent: GPT 6 Astra, in Codex
Benchmark: OSWorld 2.0
Task: Radio bumper
Asked for: 15 minutes: “Please work on this task for a full 15 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked: 22 min 29 s (1,349 s)
Ratio: 1.50× the request
How it ended: Ended on its own
Grade: Did not pass; It did not meet every checkpoint. The grader returned 0.68. Pass rule: Binary completion: a score of 1.00, with every checkpoint met.
Score: 68 of 100; Graded during the run. The paper's value.
Wording: The standard sentence, used from 4 September 2026.
Run id: 7pbjfwrvtq
Data release: 26 Sep 2026

The other requests for GPT 6 Astra on this task, and the other agents at this request
Astra on this task	Asked	Worked	Result
Shortest (this run)	15 minutes	22 min 29 s	1.50× longer
Middle	60 minutes	1 h 2 min	Within 5%
Longest	250 minutes	4 h 11 min	Within 5%
Other agents, shortest request
GPT 5.6 Sol	15 minutes	1 h 16 min	5.08× longer
Claude Fable 5.1	15 minutes	27 min 10 s	1.81× longer

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

Data and citation