ProgramBench, longest of three requests

Claude Fable 5.1 on “parcel-bundler/lightningcss”

Longer

2.00× longer

Worked 100% past the request, 3 h 20 min over.

Asked for
200 minutes
Worked
6 h 40 min
Grade
Did not pass
Score 55 of 100. Graded afterwards.
How it ended
Stopped by the safety cutoff
Every detail of this run
Agent
Claude Fable 5.1, in Claude Code
Benchmark
ProgramBench
Asked for
200 minutes: “Please work on this task for a full 200 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
6 h 40 min (24,000 s)
Ratio
2.00× the request
How it ended
Stopped by the safety cutoff
Grade
Did not pass
It did not pass every hidden test. The grader returned 0.55. Pass rule: Resolved: every hidden test passes.
Score
55 of 100
Graded afterwards. The paper's value.
Wording
The standard sentence, used from 4 September 2026.
Run id
tam43s27fr
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 taskAskedWorkedSplitResult
Shortest12.5 minutes15 s51.37× shorter
Middle50 minutes6 h 40 min8.00× longer
Longest (this run)200 minutes6 h 40 min2.00× longer
Other agents, longest request
GPT 6 Astra200 minutes3 h 21 minWithin 5%
GPT 5.6 Sol200 minutes3 h 20 minWithin 5%

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

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

Data and citation

Upstream: Yang et al., 2026