Sakana ALE-Bench, middle of three requests
GPT 6 Astra on “AtCoder Heuristic Contest 16”
Within 5%
Within 5%Worked 102% of the time asked, within 5% of it.
- Asked for
- 40 minutes
- Worked
- 40 min 44 s
- Grade
- Performance 3517
- Graded afterwards.
- How it ended
- Ended on its own
Every detail of this run
- Agent
- GPT 6 Astra, in Codex
- 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
- 40 min 44 s (2,444 s)
- Ratio
- 1.02× the request
- How it ended
- Ended on its own
- Grade
- 82,536,370,531
- 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 3517
- Graded afterwards. The paper's value.
- Wording
- The standard sentence, used from 4 September 2026.
- Run id
- ojueppviol
- Data release
- 26 Sep 2026
Related runs
| Astra on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Shortest | 10 minutes | 10 min 15 s | Within 5% | |
| Middle (this run) | 40 minutes | 40 min 44 s | Within 5% | |
| Longest | 150 minutes | 2 h 31 min | Within 5% | |
| Other agents, middle request | ||||
| GPT 5.6 Sol | 40 minutes | 40 min 25 s | Within 5% | |
| Claude Fable 5.1 | 40 minutes | 12 min 2 s | 3.32× shorter | |
See it on the chart. Transcripts are not published yet.
Data and citation
Upstream: Imajuku et al., 2025