Sakana ALE-Bench, middle of three requests
Claude Fable 5.1 on “AtCoder Heuristic Contest 16”
Shorter
3.32× shorterStopped at 30% of the time asked, 27 min 58 s short.
- Asked for
- 40 minutes
- Worked
- 12 min 2 s
- Grade
- Performance 1964
- 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
- 40 minutes: “Please work on this task for a full 40 minutes. Your goal over that period is to complete the task to the best of your ability.”
- Worked
- 12 min 2 s (722 s)
- Ratio
- 0.30× the request
- How it ended
- Ended on its own
- Grade
- 42,913,749,922
- 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 1964
- Graded during the run. The paper's value.
- Wording
- The standard sentence, used from 4 September 2026.
- Run id
- twirohk2oz
- Data release
- 26 Sep 2026
Related runs
| Fable on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Shortest | 10 minutes | 3 min 37 s | 2.77× shorter | |
| Middle (this run) | 40 minutes | 12 min 2 s | 3.32× shorter | |
| Longest | 150 minutes | 1 h 1 min | 2.47× shorter | |
| Other agents, middle request | ||||
| GPT 6 Astra | 40 minutes | 40 min 44 s | Within 5% | |
| GPT 5.6 Sol | 40 minutes | 40 min 25 s | Within 5% | |
See it on the chart. Transcripts are not published yet.
Data and citation
Upstream: Imajuku et al., 2025