Agents' Last Exam, shortest of three requests

GPT 5.6 Sol on “Repair a Moodle backup and rebuild registrar exports”

Longer

1.92× longer

Worked 92% past the request, 4 min 36 s over.

Asked

Worked

Safety cutoff 2 h 40 min, off the scale

Every detail of this run

Agent: GPT 5.6 Sol, in Codex
Benchmark: Agents' Last Exam
Task: Repair a Moodle backup and rebuild registrar exports
Asked for: 5 minutes: “Please work on this task for a full 5 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked: 9 min 36 s (576 s)
Ratio: 1.92× 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 0.95. Pass rule: Full pass: a checker score of 1.
Score: 95 of 100; Graded afterwards. The paper's value.
Wording: The standard sentence, used from 4 September 2026.
Run id: zcanswp5fr
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)	5 minutes	9 min 36 s	1.92× longer
Middle	20 minutes	21 min 23 s	1.07× longer
Longest	80 minutes	7 min 52 s	10.17× shorter
Other agents, shortest request
GPT 6 Astra	5 minutes	8 min 11 s	1.64× longer
Claude Fable 5.1	5 minutes	2 h 35 min	31.04× longer

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

Data and citation