ProgramBench, longest of three requests

Claude Fable 5.1 on “o2sh/onefetch”

Shorter

557.62× shorter

Stopped at 0% of the time asked, 4 h 10 min short.

Asked

Worked

Safety cutoff 8 h 20 min, off the scale

Asked for: 250 minutes
Worked: 27 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: o2sh/onefetch
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: 27 s (27 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: ykn65tefrp
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	15 minutes	6 min 50 s	2.20× shorter
Middle	60 minutes	25 min 3 s	2.40× shorter
Longest (this run)	250 minutes	27 s	557.62× shorter
Other agents, longest request
GPT 6 Astra	250 minutes	4 h 11 min	Within 5%
GPT 5.6 Sol	250 minutes	1 h 7 min	3.75× shorter

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