YC-Bench, middle of three requests

Claude Fable 5.1 on “Run the current one-year startup simulation, official seed 2”

Shorter

1.32× shorter

Stopped 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
The other requests for Claude Fable 5.1 on this task, and the other agents at this request
Fable on this taskAskedWorkedSplitResult
Shortest8 minutes1 h 8 min8.45× longer
Middle (this run)30 minutes22 min 41 s1.32× shorter
Longest125 minutes1 h 34 min1.33× shorter
Other agents, middle request
GPT 6 Astra30 minutes2 min 8 s14.04× shorter
GPT 5.6 Sol30 minutes35 min 34 s1.19× longer

See it on the chart. Transcripts are not published yet.

Data and citation

Upstream: He et al., 2026