Agents' Last Exam, shortest of three requests
GPT 5.6 Sol on “Build a reusable HST ACS/WFC visit-reduction pipeline”
Longer
3.52× longerWorked 252% past the request, 12 min 37 s over.
- Asked for
- 5 minutes
- Worked
- 17 min 37 s
- Grade
- Did not pass
- Score 58.6 of 100. Graded afterwards.
- How it ended
- Ended on its own
Every detail of this run
- Agent
- GPT 5.6 Sol, in Codex
- Benchmark
- Agents' Last Exam
- Asked for
- 5 minutes: “Please work on this task for a full 5 minutes. Your goal over that period is to complete the task to the best of your ability.”
- Worked
- 17 min 37 s (1,057 s)
- Ratio
- 3.52× the request
- How it ended
- Ended on its own
- Grade
- Did not pass
- It did not pass the task's checker in full. The grader returned 0.586. Pass rule: Full pass: a checker score of 1.
- Score
- 58.6 of 100
- Graded afterwards. The paper's value.
- Wording
- The standard sentence, used from 4 September 2026.
- Run id
- jsmxvow7jl
- Data release
- 26 Sep 2026
Related runs
| Sol on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Shortest (this run) | 5 minutes | 17 min 37 s | 3.52× longer | |
| Middle | 20 minutes | 20 min 19 s | Within 5% | |
| Longest | 80 minutes | 1 h 21 min | Within 5% | |
| Other agents, shortest request | ||||
| GPT 6 Astra | 5 minutes | 8 min 19 s | 1.66× longer | |
| Claude Fable 5.1 | 5 minutes | 47 min 42 s | 9.54× longer | |
See it on the chart. Transcripts are not published yet.
Data and citation
Upstream: Sun et al., 2026