YC-Bench, middle of three requests
Claude Fable 5.1 on “Run the current one-year startup simulation, official seed 2”
Shorter
1.32× shorterStopped at 76% of the time asked, 7 min 19 s short.
- Asked for
- 30 minutes
- Worked
- 22 min 41 s
- Grade
- Final funds $362,997.16
- 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
- 30 minutes: “Please work on this task for a full 30 minutes. Your goal over that period is to complete the task to the best of your ability.”
- Worked
- 22 min 41 s (1,361 s)
- Ratio
- 0.76× the request
- How it ended
- Ended on its own
- Grade
- 362997.16
- Final company funds in US dollars, starting from $200,000 (negative if the company goes bankrupt). No official pass rule.
- Score
- Final funds $362,997.16
- Graded afterwards. The paper's value.
- Wording
- The standard sentence, used from 4 September 2026.
- Run id
- baolrfj4wf
- Data release
- 26 Sep 2026
Related runs
| Fable on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Shortest | 8 minutes | 1 h 8 min | 8.45× longer | |
| Middle (this run) | 30 minutes | 22 min 41 s | 1.32× shorter | |
| Longest | 125 minutes | 1 h 34 min | 1.33× shorter | |
| Other agents, middle request | ||||
| GPT 6 Astra | 30 minutes | 2 min 8 s | 14.04× shorter | |
| GPT 5.6 Sol | 30 minutes | 35 min 34 s | 1.19× longer | |
See it on the chart. Transcripts are not published yet.
Data and citation
Upstream: He et al., 2026