ProgramBench, shortest of three requests
Claude Fable 5.1 on “nuta/nsh”
Longer
1.06× longerWorked 6% past the request, 43 s over.
- Asked for
- 12.5 minutes
- Worked
- 13 min 13 s
- Grade
- Did not pass
- Score 79.8 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
- nuta/nsh
- Asked for
- 12.5 minutes: “Please work on this task for a full 12.5 minutes. Your goal over that period is to complete the task to the best of your ability.”
- Worked
- 13 min 13 s (793 s)
- Ratio
- 1.06× the request
- How it ended
- Ended on its own
- Grade
- Did not pass
- It did not pass every hidden test. The grader returned 0.798. Pass rule: Resolved: every hidden test passes.
- Score
- 79.8 of 100
- Graded afterwards. The paper's value.
- Wording
- The standard sentence, used from 4 September 2026.
- Run id
- ewziu4hyvq
- Data release
- 26 Sep 2026
Related runs
| Fable on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Shortest (this run) | 12.5 minutes | 13 min 13 s | 1.06× longer | |
| Middle | 50 minutes | 6 h 40 min | 8.00× longer | |
| Longest | 200 minutes | 6 h 40 min | 2.00× longer | |
| Other agents, shortest request | ||||
| GPT 6 Astra | 12.5 minutes | 12 min 39 s | Within 5% | |
| GPT 5.6 Sol | 12.5 minutes | 22 min 8 s | 1.77× longer | |
See it on the chart. Transcripts are not published yet.
Data and citation
Upstream: Yang et al., 2026