PPTArena, longest of three requests
GPT 5.6 Sol on “Grid and baseline rhythm”
Shorter
3.73× shorterStopped at 27% of the time asked, 18 min 18 s short.
- Asked for
- 25 minutes
- Worked
- 6 min 42 s
- Grade
- Score 50 of 100
- Instructions 2 of 5, visuals 3 of 5. Judged afterwards.
- How it ended
- Ended on its own
Every detail of this run
- Agent
- GPT 5.6 Sol, in Codex
- Benchmark
- PPTArena
- Asked for
- 25 minutes: “Please work on this task for a full 25 minutes. Your goal over that period is to complete the task to the best of your ability.”
- Worked
- 6 min 42 s (402 s)
- Ratio
- 0.27× the request
- How it ended
- Ended on its own
- Grade
- Instructions 2.00 of 5, visuals 3.00 of 5
- Two 0-to-5 judge scores, instruction following (IF) and visual quality (VQ), each the median of 3 judge samples. No official pass rule.
- Score
- 50 of 100
- Judged afterwards. The paper's value.
- Wording
- The standard sentence, used from 4 September 2026.
- Run id
- myyreqbasq
- Data release
- 26 Sep 2026
Related runs
| Sol on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Shortest | 1.5 minutes | 4 min 26 s | 2.96× longer | |
| Middle | 6 minutes | 6 min 41 s | 1.11× longer | |
| Longest (this run) | 25 minutes | 6 min 42 s | 3.73× shorter | |
| Other agents, longest request | ||||
| GPT 6 Astra | 25 minutes | 25 min 39 s | Within 5% | |
| Claude Fable 5.1 | 25 minutes | 14 min 22 s | 1.74× shorter | |
See it on the chart. Transcripts are not published yet.