ProgramBench, shortest of three requests
Claude Fable 5.1 on “rcoh/angle-grinder”
Shorter
1.09× shorterStopped at 92% of the time asked, 1 min 16 s short.
- Asked for
- 15 minutes
- Worked
- 13 min 44 s
- Grade
- Did not pass
- Score 61.8 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
- Asked for
- 15 minutes: “Please work on this task for a full 15 minutes. Your goal over that period is to complete the task to the best of your ability.”
- Worked
- 13 min 44 s (824 s)
- Ratio
- 0.92× the request
- How it ended
- Ended on its own
- Grade
- Did not pass
- It did not pass every hidden test. The grader returned 0.618. Pass rule: Resolved: every hidden test passes.
- Score
- 61.8 of 100
- Graded afterwards. The paper's value.
- Wording
- The standard sentence, used from 4 September 2026.
- Run id
- hocwwtxqo6
- Data release
- 26 Sep 2026
Related runs
| Fable on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Shortest (this run) | 15 minutes | 13 min 44 s | 1.09× shorter | |
| Middle | 60 minutes | 33 min 49 s | 1.77× shorter | |
| Longest | 250 minutes | 15 s | 980.39× shorter | |
| Other agents, shortest request | ||||
| GPT 6 Astra | 15 minutes | 15 min 15 s | Within 5% | |
| GPT 5.6 Sol | 15 minutes | 14 min 58 s | Within 5% | |
See it on the chart. Transcripts are not published yet.
Data and citation
Upstream: Yang et al., 2026