ProgramBench, middle of three requests
Claude Fable 5.1 on “o2sh/onefetch”
Shorter
2.40× shorterStopped at 42% of the time asked, 34 min 57 s short.
- Asked for
- 60 minutes
- Worked
- 25 min 3 s
- Grade
- Did not pass
- Score 60.2 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
- Task
- o2sh/onefetch
- Asked for
- 60 minutes: “Please work on this task for a full 60 minutes. Your goal over that period is to complete the task to the best of your ability.”
- Worked
- 25 min 3 s (1,503 s)
- Ratio
- 0.42× the request
- How it ended
- Ended on its own
- Grade
- Did not pass
- It did not pass every hidden test. The grader returned 0.602. Pass rule: Resolved: every hidden test passes.
- Score
- 60.2 of 100
- Graded afterwards. The paper's value.
- Wording
- The standard sentence, used from 4 September 2026.
- Run id
- aud7kcabi3
- Data release
- 26 Sep 2026
Related runs
| Fable on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Shortest | 15 minutes | 6 min 50 s | 2.20× shorter | |
| Middle (this run) | 60 minutes | 25 min 3 s | 2.40× shorter | |
| Longest | 250 minutes | 27 s | 557.62× shorter | |
| Other agents, middle request | ||||
| GPT 6 Astra | 60 minutes | 1 h 1 min | Within 5% | |
| GPT 5.6 Sol | 60 minutes | 1 h | Within 5% | |
See it on the chart. Transcripts are not published yet.
Data and citation
Upstream: Yang et al., 2026