Agents' Last Exam, shortest of three requests

GPT 5.6 Sol on “Redesign and validate a Flowable supply-disruption workflow”

Longer

7.44× longer

Worked 644% past the request, 51 min 33 s over.

Asked

Worked

Safety cutoff 4 h 10 min, off the scale

Every detail of this run

Agent: GPT 5.6 Sol, in Codex
Benchmark: Agents' Last Exam
Task: Redesign and validate a Flowable supply-disruption workflow
Asked for: 8 minutes: “Please work on this task for a full 8 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked: 59 min 33 s (3,573 s)
Ratio: 7.44× the request
How it ended: Ended on its own
Grade: Did not pass; It did not pass the task's checker in full. The grader returned 0.834. Pass rule: Full pass: a checker score of 1.
Score: 83.4 of 100; Graded afterwards. The paper's value.
Wording: The standard sentence, used from 4 September 2026.
Run id: 2d23bnes7m
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 (this run)	8 minutes	59 min 33 s	7.44× longer
Middle	30 minutes	30 min 47 s	Within 5%
Longest	125 minutes	2 h 6 min	Within 5%
Other agents, shortest request
GPT 6 Astra	8 minutes	8 min 47 s	1.10× longer
Claude Fable 5.1	8 minutes	34 min	4.25× longer

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

Data and citation