ProgramBench, longest of three requests

Claude Fable 5.1 on “stathissideris/ditaa”

Shorter

348.84× shorter

Stopped at 0% of the time asked, 2 h 5 min short.

Asked

Worked

Safety cutoff 4 h 10 min, off the scale

Asked for: 125 minutes
Worked: 22 s
Grade: No grade recorded; This run is outside the paper's scores, and the campaign recorded no grade for it. Not in the paper's scores.
How it ended: Refused within 30 seconds

Every detail of this run

Agent: Claude Fable 5.1, in Claude Code
Benchmark: ProgramBench
Task: stathissideris/ditaa
Asked for: 125 minutes: “Please work on this task for a full 125 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked: 22 s (22 s)
Ratio: 0.00× the request
How it ended: Refused within 30 seconds
Grade: No grade recorded; This run is outside the paper's scores, and the campaign recorded no grade for it.
Wording: The standard sentence, used from 4 September 2026.
Run id: yizavjrhb4
Data release: 26 Sep 2026

The other requests for Claude Fable 5.1 on this task, and the other agents at this request
Fable on this task	Asked	Worked	Result
Shortest	8 minutes	5 min 16 s	1.52× shorter
Middle	30 minutes	2 h 29 min	4.98× longer
Longest (this run)	125 minutes	22 s	348.84× shorter
Other agents, longest request
GPT 6 Astra	125 minutes	2 h 6 min	Within 5%
GPT 5.6 Sol	125 minutes	2 h 6 min	Within 5%

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

Read before quoting. This run is left out of the default set.

Data and citation