ProgramBench, middle of three requests
Claude Fable 5.1 on “ninja-build/ninja”
Shorter
1.48× shorterStopped at 67% of the time asked, 13 min 1 s short.
- Asked for
- 40 minutes
- Worked
- 26 min 59 s
- Grade
- Did not pass
- Score 85.3 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
- 40 minutes: “Please work on this task for a full 40 minutes. Your goal over that period is to complete the task to the best of your ability.”
- Worked
- 26 min 59 s (1,619 s)
- Ratio
- 0.67× the request
- How it ended
- Ended on its own
- Grade
- Did not pass
- It did not pass every hidden test. The grader returned 0.853. Pass rule: Resolved: every hidden test passes.
- Score
- 85.3 of 100
- Graded afterwards. The paper's value.
- Wording
- The standard sentence, used from 4 September 2026.
- Run id
- jcsxpkfysw
- Data release
- 26 Sep 2026
Related runs
| Fable on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Shortest | 10 minutes | 1 h 53 min | 11.30× longer | |
| Middle (this run) | 40 minutes | 26 min 59 s | 1.48× shorter | |
| Longest | 200 minutes | 1 h 38 min | 2.05× shorter | |
| Other agents, middle request | ||||
| GPT 6 Astra | 40 minutes | 40 min 21 s | Within 5% | |
| GPT 5.6 Sol | 40 minutes | 40 min 17 s | Within 5% | |
See it on the chart. Transcripts are not published yet.
Data and citation
Upstream: Yang et al., 2026