PPTArena, longest of three requests
Claude Fable 5.1 on “LaTeX to editable Office Math”
Within 5%
Within 5%Worked 96% of the time asked, within 5% of it.
- Asked for
- 25 minutes
- Worked
- 24 min 5 s
- Grade
- Score 50 of 100
- Instructions 5 of 5, visuals 0 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
- 24 min 5 s (1,445 s)
- Ratio
- 0.96× the request
- How it ended
- Ended on its own
- Grade
- Instructions 5.00 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
- 50 of 100
- Judged afterwards. The paper's value.
- Wording
- The standard sentence, used from 4 September 2026.
- Run id
- tn4y4tqekk
- Data release
- 26 Sep 2026
Related runs
| Fable on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Shortest | 1.5 minutes | 17 min 47 s | 11.86× longer | |
| Middle | 6 minutes | 11 min 45 s | 1.96× longer | |
| Longest (this run) | 25 minutes | 24 min 5 s | Within 5% | |
| Other agents, longest request | ||||
| GPT 6 Astra | 25 minutes | 25 min 44 s | Within 5% | |
| GPT 5.6 Sol | 25 minutes | 25 min 45 s | Within 5% | |
See it on the chart. Transcripts are not published yet.