ProgramBench, shortest of three requests
Claude Fable 5.1 on “mookid/diffr”
Longer
33.33× longerWorked 33.3 times as long as asked, 8 h 5 min over.
- Asked for
- 15 minutes
- Worked
- 8 h 20 min
- Grade
- Did not pass
- Score 92.1 of 100. Graded afterwards.
- How it ended
- Stopped by the safety cutoff
Every detail of this run
- Agent
- Claude Fable 5.1, in Claude Code
- Benchmark
- ProgramBench
- Task
- mookid/diffr
- 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
- 8 h 20 min (30,000 s)
- Ratio
- 33.33× the request
- How it ended
- Stopped by the safety cutoff
- Grade
- Did not pass
- It did not pass every hidden test. The grader returned 0.921. Pass rule: Resolved: every hidden test passes.
- Score
- 92.1 of 100
- Graded afterwards. The paper's value.
- Wording
- The standard sentence, used from 4 September 2026.
- Run id
- pnuxqxd674
- Data release
- 26 Sep 2026
Related runs
| Fable on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Shortest (this run) | 15 minutes | 8 h 20 min | 33.33× longer | |
| Middle | 60 minutes | 54 min 17 s | 1.11× shorter | |
| Longest | 250 minutes | 2 h 16 min | 1.84× shorter | |
| Other agents, shortest request | ||||
| GPT 6 Astra | 15 minutes | 15 min 11 s | Within 5% | |
| GPT 5.6 Sol | 15 minutes | 22 min 48 s | 1.52× longer | |
See it on the chart. Transcripts are not published yet.
Read before quoting. This run was stopped by the safety cutoff, so its time is a lower bound: the agent might have kept going. Details
Data and citation
Upstream: Yang et al., 2026