ProgramBench, longest of three requests

GPT 5.6 Sol on “mookid/diffr”

Within 5%

Worked 101% of the time asked, within 5% of it.

Asked

Worked

Safety cutoff 8 h 20 min, off the scale

Every detail of this run

Agent: GPT 5.6 Sol, in Codex
Benchmark: ProgramBench
Task: mookid/diffr
Asked for: 250 minutes: “Please work on this task for a full 250 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked: 4 h 12 min (15,094 s)
Ratio: 1.01× the request
How it ended: Stopped by an error
Grade: Did not pass; It did not pass every hidden test. The grader returned 0.934. Pass rule: Resolved: every hidden test passes.
Score: 93.4 of 100; Graded afterwards. The paper's value.
Wording: The standard sentence, used from 4 September 2026.
Run id: c4zad5jtxs
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	22 min 48 s	1.52× longer
Middle	60 minutes	1 h 1 min	Within 5%
Longest (this run)	250 minutes	4 h 12 min	Within 5%
Other agents, longest request
GPT 6 Astra	250 minutes	4 h 11 min	Within 5%
Claude Fable 5.1	250 minutes	2 h 16 min	1.84× shorter

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

Read before quoting. This run was stopped by an error, so its time is a lower bound: the agent might have kept going. Details

Data and citation