WildClawBench, middle of three requests
Claude Fable 5.1 on “Find a shortest coauthorship chain between two scholars”
Longer
3.31× longerWorked 231% past the request, 18 min 29 s over.
- Asked for
- 8 minutes
- Worked
- 26 min 29 s
- Grade
- Score 100 of 100
- Judged afterwards.
- How it ended
- Ended on its own
Every detail of this run
- Agent
- Claude Fable 5.1, in Claude Code
- Benchmark
- WildClawBench
- Asked for
- 8 minutes: “Please work on this task for a full 8 minutes. Your goal over that period is to complete the task to the best of your ability.”
- Worked
- 26 min 29 s (1,589 s)
- Ratio
- 3.31× the request
- How it ended
- Ended on its own
- Grade
- 1
- Task grader score, 0 to 1 (a model judge only where the task calls for one). No official pass rule.
- Score
- 100 of 100
- Judged afterwards. The paper's value.
- Wording
- The standard sentence, used from 4 September 2026.
- Run id
- rswv3aaogs
- Data release
- 26 Sep 2026
Related runs
| Fable on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Shortest | 2 minutes | 26 min 6 s | 13.05× longer | |
| Middle (this run) | 8 minutes | 26 min 29 s | 3.31× longer | |
| Longest | 40 minutes | 25 min 27 s | 1.57× shorter | |
| Other agents, middle request | ||||
| GPT 6 Astra | 8 minutes | 1 h 20 min | 10.00× longer | |
| GPT 5.6 Sol | 8 minutes | 1 h 20 min | 10.00× longer | |
See it on the chart. Transcripts are not published yet.
Data and citation
Upstream: Ding et al., 2026