ProgramBench, middle of three requests

GPT 5.6 Sol on “lfos/calcurse”

Within 5%

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

Asked

Worked

Safety cutoff 13 h 20 min, off the scale

Every detail of this run

Agent: GPT 5.6 Sol, in Codex
Benchmark: ProgramBench
Task: lfos/calcurse
Asked for: 100 minutes: “Please work on this task for a full 100 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked: 1 h 41 min (6,086 s)
Ratio: 1.01× the request
How it ended: Ending not labelled yet
Grade: Did not pass; It did not pass every hidden test. The grader returned 0.656. Pass rule: Resolved: every hidden test passes.
Score: 65.6 of 100; Graded afterwards. The paper's value.
Wording: The standard sentence, used from 4 September 2026.
Run id: k5nfplaifm
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	25 minutes	23 min 42 s	1.05× shorter
Middle (this run)	100 minutes	1 h 41 min	Within 5%
Longest	400 minutes	13 min 54 s	28.79× shorter
Other agents, middle request
GPT 6 Astra	100 minutes	1 h 40 min	Within 5%
Claude Fable 5.1	100 minutes	2 h 16 min	1.36× longer

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

Read before quoting. How this run ended has not been labelled yet. It is timed like every other run and counted in every number. Details

Data and citation