OSWorld 2.0, shortest of three requests

Claude Fable 5.1 on “Defense schedule”

Longer

2.01× longer

Worked 101% past the request, 15 min 13 s over.

Asked

Worked

Safety cutoff 8 h 20 min, off the scale

Every detail of this run

Agent: Claude Fable 5.1, in Claude Code
Benchmark: OSWorld 2.0
Task: Defense schedule
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: 30 min 13 s (1,813 s)
Ratio: 2.01× the request
How it ended: Ended on its own
Grade: Passed; It met every checkpoint. The grader returned 1.0. Pass rule: Binary completion: a score of 1.00, with every checkpoint met.
Score: 100 of 100; Graded during the run. The paper's value.
Wording: The standard sentence, used from 4 September 2026.
Run id: hq5o43j3fu
Data release: 26 Sep 2026

The other requests for Claude Fable 5.1 on this task, and the other agents at this request
Fable on this task	Asked	Worked	Result
Shortest (this run)	15 minutes	30 min 13 s	2.01× longer
Middle	60 minutes	29 min 22 s	2.04× shorter
Longest	250 minutes	54 min 46 s	4.57× shorter
Other agents, shortest request
GPT 6 Astra	15 minutes	16 min 34 s	1.10× longer
GPT 5.6 Sol	15 minutes	1 h 2 min	4.14× longer

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

Data and citation