YC-Bench, longest of three requests
Claude Fable 5.1 on “Run the current one-year startup simulation, official seed 3”
Shorter
1.99× shorterStopped at 50% of the time asked, 1 h 2 min short.
- Asked for
- 125 minutes
- Worked
- 1 h 3 min
- Grade
- Final funds $1,006,889.97
- 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
- 1 h 3 min (3,777 s)
- Ratio
- 0.50× the request
- How it ended
- Ended on its own
- Grade
- 1006889.97
- Final company funds in US dollars, starting from $200,000 (negative if the company goes bankrupt). No official pass rule.
- Score
- Final funds $1,006,889.97
- Graded afterwards. The paper's value.
- Wording
- The standard sentence, used from 4 September 2026.
- Run id
- ux3rphausv
- Data release
- 26 Sep 2026
Related runs
| Fable on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Shortest | 8 minutes | 44 min 16 s | 5.53× longer | |
| Middle | 30 minutes | 39 min 10 s | 1.31× longer | |
| Longest (this run) | 125 minutes | 1 h 3 min | 1.99× shorter | |
| Other agents, longest request | ||||
| GPT 6 Astra | 125 minutes | 2 h 13 min | 1.06× longer | |
| GPT 5.6 Sol | 125 minutes | 1 h 1 min | 2.06× shorter | |
See it on the chart. Transcripts are not published yet.
Data and citation
Upstream: He et al., 2026