Agents' Last Exam, shortest of three requests
GPT 5.6 Sol on “Parse a fixed 100-filing SEC 10-K corpus”
Longer
2.25× longerWorked 125% past the request, 12 min 30 s over.
- Asked for
- 10 minutes
- Worked
- 22 min 30 s
- Grade
- Did not pass
- Score 86 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
- 10 minutes: “Please work on this task for a full 10 minutes. Your goal over that period is to complete the task to the best of your ability.”
- Worked
- 22 min 30 s (1,350 s)
- Ratio
- 2.25× 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 0.86. Pass rule: Full pass: a checker score of 1.
- Score
- 86 of 100
- Graded afterwards. The paper's value.
- Wording
- The standard sentence, used from 4 September 2026.
- Run id
- ogpanl3ksw
- Data release
- 26 Sep 2026
Related runs
| Sol on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Shortest (this run) | 10 minutes | 22 min 30 s | 2.25× longer | |
| Middle | 40 minutes | 42 min 15 s | 1.06× longer | |
| Longest | 150 minutes | 2 h 31 min | Within 5% | |
| Other agents, shortest request | ||||
| GPT 6 Astra | 10 minutes | 12 min 51 s | 1.29× longer | |
| Claude Fable 5.1 | 10 minutes | 39 min 29 s | 3.95× longer | |
See it on the chart. Transcripts are not published yet.
Data and citation
Upstream: Sun et al., 2026