YC-Bench, longest of three requests
Claude Fable 5.1 on “Run the current one-year startup simulation, official seed 1”
Shorter
3.64× shorterStopped at 27% of the time asked, 1 h 31 min short.
- Asked for
- 125 minutes
- Worked
- 34 min 22 s
- Grade
- Final funds $540,800.54
- Graded afterwards.
- How it ended
- Ended on its own
Every detail of this run
- Agent
- Claude Fable 5.1, in Claude Code
- Benchmark
- YC-Bench
- Asked for
- 125 minutes: “Please work on this task for a full 125 minutes. Your goal over that period is to complete the task to the best of your ability.”
- Worked
- 34 min 22 s (2,062 s)
- Ratio
- 0.27× the request
- How it ended
- Ended on its own
- Grade
- 540800.54
- Final company funds in US dollars, starting from $200,000 (negative if the company goes bankrupt). No official pass rule.
- Score
- Final funds $540,800.54
- Graded afterwards. The paper's value.
- Wording
- The standard sentence, used from 4 September 2026.
- Run id
- bfk2vyubre
- Data release
- 26 Sep 2026
Related runs
| Fable on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Shortest | 8 minutes | 28 min 58 s | 3.62× longer | |
| Middle | 30 minutes | 28 min 20 s | 1.06× shorter | |
| Longest (this run) | 125 minutes | 34 min 22 s | 3.64× shorter | |
| Other agents, longest request | ||||
| GPT 6 Astra | 125 minutes | 15 min 51 s | 7.89× shorter | |
| GPT 5.6 Sol | 125 minutes | 35 min 7 s | 3.56× shorter | |
See it on the chart. Transcripts are not published yet.
Data and citation
Upstream: He et al., 2026