Sakana ALE-Bench, longest of three requests
Claude Fable 5.1 on “Future Contest 2022 Qual”
Shorter
3.60× shorterStopped at 28% of the time asked, 3 h 1 min short.
- Asked for
- 250 minutes
- Worked
- 1 h 9 min
- Grade
- Performance 2882
- Graded during the run.
- How it ended
- Ended on its own
Every detail of this run
- Agent
- Claude Fable 5.1, in Claude Code
- Benchmark
- Sakana ALE-Bench
- Asked for
- 250 minutes: “Please work on this task for a full 250 minutes. Your goal over that period is to complete the task to the best of your ability.”
- Worked
- 1 h 9 min (4,167 s)
- Ratio
- 0.28× the request
- How it ended
- Ended on its own
- Grade
- 6,303,453
- Raw score on the private test cases, in each problem's own units; also reports rank against human contest entrants. No official pass rule.
- Score
- Performance 2882
- Graded during the run. The paper's value.
- Wording
- The standard sentence, used from 4 September 2026.
- Run id
- ry6tcyynv4
- Data release
- 26 Sep 2026
Related runs
| Fable on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Shortest | 15 minutes | 8 min 57 s | 1.68× shorter | |
| Middle | 60 minutes | 28 min 4 s | 2.14× shorter | |
| Longest (this run) | 250 minutes | 1 h 9 min | 3.60× shorter | |
| Other agents, longest request | ||||
| GPT 6 Astra | 250 minutes | 4 h 11 min | Within 5% | |
| GPT 5.6 Sol | 250 minutes | 4 h 12 min | Within 5% | |
See it on the chart. Transcripts are not published yet.
Data and citation
Upstream: Imajuku et al., 2025