CORE-Bench v1.1, longest of three requests

Claude Fable 5.1 on “Train and evaluate end-to-end neural-network feature selection on MNIST”

Shorter

1.08× shorter

Stopped at 92% of the time asked, 15 min 24 s short.

Asked

Worked

Safety cutoff 6 h 40 min, off the scale

Every detail of this run

Agent: Claude Fable 5.1, in Claude Code
Benchmark: CORE-Bench v1.1
Task: Train and evaluate end-to-end neural-network feature selection on MNIST
Asked for: 200 minutes: “Please work on this task for a full 200 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked: 3 h 5 min (11,076 s)
Ratio: 0.92× the request
How it ended: Ended on its own
Grade: Did not pass; It did not get every answer right. The grader returned 0. Pass rule: Every answer correct, with numbers inside a 95% prediction interval.
Score: 0 of 100; Graded during the run. The paper's value.
Wording: The standard sentence, used from 4 September 2026.
Run id: hohjabjwg5
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 task	Asked	Worked	Result
Shortest	12.5 minutes	3 h 11 min	15.32× longer
Middle	50 minutes	6 h 40 min	8.00× longer
Longest (this run)	200 minutes	3 h 5 min	1.08× shorter
Other agents, longest request
GPT 6 Astra	200 minutes	3 h 21 min	Within 5%
GPT 5.6 Sol	200 minutes	3 h 21 min	Within 5%

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

Data and citation