OSWorld 2.0, middle of three requests

GPT 5.6 Sol on “GIMP composite”

Longer

1.74× longer

Worked 74% past the request, 44 min 19 s over.

Asked

Worked

Safety cutoff 8 h 20 min, off the scale

Every detail of this run

Agent: GPT 5.6 Sol, in Codex
Benchmark: OSWorld 2.0
Task: GIMP composite
Asked for: 60 minutes: “Please work on this task for a full 60 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked: 1 h 44 min (6,259 s)
Ratio: 1.74× the request
How it ended: Ended on its own
Grade: Did not pass; It did not meet every checkpoint. The grader returned 0.4. Pass rule: Binary completion: a score of 1.00, with every checkpoint met.
Score: 40 of 100; Graded during the run. The paper's value.
Wording: The standard sentence, used from 4 September 2026.
Run id: cdvlsynr3s
Data release: 26 Sep 2026

The other requests for GPT 5.6 Sol on this task, and the other agents at this request
Sol on this task	Asked	Worked	Result
Shortest	15 minutes	1 h 20 min	5.33× longer
Middle (this run)	60 minutes	1 h 44 min	1.74× longer
Longest	250 minutes	23 min 35 s	10.60× shorter
Other agents, middle request
GPT 6 Astra	60 minutes	1 h 4 min	1.06× longer
Claude Fable 5.1	60 minutes	3 h 9 min	3.16× longer

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

Data and citation