PPTArena, longest of three requests
Claude Fable 5.1 on “Accessibility and master cleanup”
Shorter
2.52× shorterStopped at 40% of the time asked, 15 min 6 s short.
- Asked for
- 25 minutes
- Worked
- 9 min 55 s
- Grade
- Score 0 of 100
- Instructions 0 of 5, visuals 0 of 5. Nothing to grade, counted as 0.
- 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
- 9 min 55 s (595 s)
- Ratio
- 0.40× the request
- How it ended
- Ended on its own
- Grade
- Instructions 0.00 of 5, visuals 0.00 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
- 0 of 100
- Nothing to grade, counted as 0. The paper's value.
- Wording
- The standard sentence, used from 4 September 2026.
- Run id
- v4aq6d4mhg
- Data release
- 26 Sep 2026
Related runs
| Fable on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Shortest | 1.5 minutes | 8 min 37 s | 5.75× longer | |
| Middle | 6 minutes | 12 min 31 s | 2.08× longer | |
| Longest (this run) | 25 minutes | 9 min 55 s | 2.52× shorter | |
| Other agents, longest request | ||||
| GPT 6 Astra | 25 minutes | 25 min 29 s | Within 5% | |
| GPT 5.6 Sol | 25 minutes | 24 min 39 s | Within 5% | |
See it on the chart. Transcripts are not published yet.