PPTArena, longest of three requests
Claude Fable 5.1 on “Copernicus climate multi-edit cascade”
Shorter
2.24× shorterStopped at 45% of the time asked, 13 min 51 s short.
- Asked for
- 25 minutes
- Worked
- 11 min 9 s
- Grade
- Score 70 of 100
- Instructions 3 of 5, visuals 4 of 5. Judged afterwards.
- How it ended
- Ended on its own
Every detail of this run
- Agent
- Claude Fable 5.1, in Claude Code
- 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
- 11 min 9 s (669 s)
- Ratio
- 0.45× the request
- How it ended
- Ended on its own
- Grade
- Instructions 3.00 of 5, visuals 4.00 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
- 70 of 100
- Judged afterwards. The paper's value.
- Wording
- The standard sentence, used from 4 September 2026.
- Run id
- kenn3uholf
- Data release
- 26 Sep 2026
Related runs
| Fable on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Shortest | 1.5 minutes | 7 min 57 s | 5.29× longer | |
| Middle | 6 minutes | 9 min 39 s | 1.61× longer | |
| Longest (this run) | 25 minutes | 11 min 9 s | 2.24× shorter | |
| Other agents, longest request | ||||
| GPT 6 Astra | 25 minutes | 25 min 17 s | Within 5% | |
| GPT 5.6 Sol | 25 minutes | 25 min 55 s | Within 5% | |
See it on the chart. Transcripts are not published yet.