PPTArena, longest of three requests
Claude Fable 5.1 on “Animation and bullet sequencing”
Shorter
2.10× shorterStopped at 48% of the time asked, 13 min 6 s short.
- Asked for
- 25 minutes
- Worked
- 11 min 54 s
- Grade
- Score 90 of 100
- Instructions 4 of 5, visuals 5 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 54 s (714 s)
- Ratio
- 0.48× the request
- How it ended
- Ended on its own
- Grade
- Instructions 4.00 of 5, visuals 5.00 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
- 90 of 100
- Judged afterwards. The paper's value.
- Wording
- The standard sentence, used from 4 September 2026.
- Run id
- yhwjjihuo5
- Data release
- 26 Sep 2026
Related runs
| Fable on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Shortest | 1.5 minutes | 6 min 59 s | 4.65× longer | |
| Middle | 6 minutes | 8 min 36 s | 1.43× longer | |
| Longest (this run) | 25 minutes | 11 min 54 s | 2.10× shorter | |
| Other agents, longest request | ||||
| GPT 6 Astra | 25 minutes | 25 min 44 s | Within 5% | |
| GPT 5.6 Sol | 25 minutes | 25 min 28 s | Within 5% | |
See it on the chart. Transcripts are not published yet.