ProgramBench, shortest of three requests
Claude Fable 5.1 on “ninja-build/ninja”
Longer
11.30× longerWorked 11.3 times as long as asked, 1 h 43 min over.
- Asked for
- 10 minutes
- Worked
- 1 h 53 min
- Grade
- Did not pass
- Score 93.1 of 100. Graded afterwards.
- How it ended
- Ended on its own
Every detail of this run
- Agent
- Claude Fable 5.1, in Claude Code
- Benchmark
- ProgramBench
- Asked for
- 10 minutes: “Please work on this task for a full 10 minutes. Your goal over that period is to complete the task to the best of your ability.”
- Worked
- 1 h 53 min (6,783 s)
- Ratio
- 11.30× the request
- How it ended
- Ended on its own
- Grade
- Did not pass
- It did not pass every hidden test. The grader returned 0.931. Pass rule: Resolved: every hidden test passes.
- Score
- 93.1 of 100
- Graded afterwards. The paper's value.
- Wording
- The standard sentence, used from 4 September 2026.
- Run id
- qe2j5ifr7q
- Data release
- 26 Sep 2026
Related runs
| Fable on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Shortest (this run) | 10 minutes | 1 h 53 min | 11.30× longer | |
| Middle | 40 minutes | 26 min 59 s | 1.48× shorter | |
| Longest | 200 minutes | 1 h 38 min | 2.05× shorter | |
| Other agents, shortest request | ||||
| GPT 6 Astra | 10 minutes | 10 min 18 s | Within 5% | |
| GPT 5.6 Sol | 10 minutes | 23 min 54 s | 2.39× longer | |
See it on the chart. Transcripts are not published yet.
Data and citation
Upstream: Yang et al., 2026