ProgramBench, middle of three requests
Claude Fable 5.1 on “cweill/gotests”
Longer
1.46× longerWorked 46% past the request, 22 min 57 s over.
- Asked for
- 50 minutes
- Worked
- 1 h 13 min
- Grade
- Did not pass
- Score 94.5 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
- cweill/gotests
- Asked for
- 50 minutes: “Please work on this task for a full 50 minutes. Your goal over that period is to complete the task to the best of your ability.”
- Worked
- 1 h 13 min (4,377 s)
- Ratio
- 1.46× the request
- How it ended
- Ended on its own
- Grade
- Did not pass
- It did not pass every hidden test. The grader returned 0.945. Pass rule: Resolved: every hidden test passes.
- Score
- 94.5 of 100
- Graded afterwards. The paper's value.
- Wording
- The standard sentence, used from 4 September 2026.
- Run id
- envfsutgjm
- Data release
- 26 Sep 2026
Related runs
| Fable on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Shortest | 12.5 minutes | 1 h 8 min | 5.43× longer | |
| Middle (this run) | 50 minutes | 1 h 13 min | 1.46× longer | |
| Longest | 200 minutes | 1 h 20 min | 2.50× shorter | |
| Other agents, middle request | ||||
| GPT 6 Astra | 50 minutes | 50 min 38 s | Within 5% | |
| GPT 5.6 Sol | 50 minutes | 50 min 59 s | Within 5% | |
See it on the chart. Transcripts are not published yet.
Data and citation
Upstream: Yang et al., 2026