ProgramBench, longest of three requests
GPT 6 Astra on “facebook/zstd”
Within 5%
Within 5%Worked 101% of the time asked, within 5% of it.
- Asked for
- 150 minutes
- Worked
- 2 h 32 min
- Grade
- Did not pass
- Score 79.6 of 100. Graded afterwards.
- How it ended
- Ended on its own
Every detail of this run
- Agent
- GPT 6 Astra, in Codex
- Benchmark
- ProgramBench
- Task
- facebook/zstd
- Asked for
- 150 minutes: “Please work on this task for a full 150 minutes. Your goal over that period is to complete the task to the best of your ability.”
- Worked
- 2 h 32 min (9,106 s)
- Ratio
- 1.01× the request
- How it ended
- Ended on its own
- Grade
- Did not pass
- It did not pass every hidden test. The grader returned 0.796. Pass rule: Resolved: every hidden test passes.
- Score
- 79.6 of 100
- Graded afterwards. The paper's value.
- Wording
- The standard sentence, used from 4 September 2026.
- Run id
- g6y5t6ppcu
- Data release
- 26 Sep 2026
Related runs
| Astra on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Shortest | 10 minutes | 10 min 12 s | Within 5% | |
| Middle | 40 minutes | 40 min 35 s | Within 5% | |
| Longest (this run) | 150 minutes | 2 h 32 min | Within 5% | |
| Other agents, longest request | ||||
| GPT 5.6 Sol | 150 minutes | 2 h 31 min | Within 5% | |
| Claude Fable 5.1 | 150 minutes | 1 h 1 min | 2.47× shorter | |
See it on the chart. Transcripts are not published yet.
Data and citation
Upstream: Yang et al., 2026