Agents' Last Exam, middle of three requests
GPT 6 Astra on “Parse a fixed 100-filing SEC 10-K corpus”
Within 5%
Within 5%Worked 101% of the time asked, within 5% of it.
- Asked for
- 40 minutes
- Worked
- 40 min 14 s
- Grade
- Did not pass
- Score 91.2 of 100. Graded afterwards.
- How it ended
- Ended on its own
Every detail of this run
- Agent
- GPT 6 Astra, in Codex
- Benchmark
- Agents' Last Exam
- 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 14 s (2,414 s)
- Ratio
- 1.01× 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 0.912. Pass rule: Full pass: a checker score of 1.
- Score
- 91.2 of 100
- Graded afterwards. The paper's value.
- Wording
- The standard sentence, used from 4 September 2026.
- Run id
- dhbxamha7s
- Data release
- 26 Sep 2026
Related runs
| Astra on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Shortest | 10 minutes | 12 min 51 s | 1.29× longer | |
| Middle (this run) | 40 minutes | 40 min 14 s | Within 5% | |
| Longest | 150 minutes | 2 h 32 min | Within 5% | |
| Other agents, middle request | ||||
| GPT 5.6 Sol | 40 minutes | 42 min 15 s | 1.06× longer | |
| Claude Fable 5.1 | 40 minutes | 27 min 30 s | 1.45× shorter | |
See it on the chart. Transcripts are not published yet.
Data and citation
Upstream: Sun et al., 2026