Humanity's Last Exam, longest of three requests

Claude Fable 5.1 on “Humanity's Last Exam item 24”

Shorter

2.89× shorter

Stopped at 35% of the time asked, 13 min 5 s short.

Asked

Worked

Safety cutoff 40 min, off the scale

Every detail of this run

Agent: Claude Fable 5.1, in Claude Code
Benchmark: Humanity's Last Exam
Task: Humanity's Last Exam item 24
Asked for: 20 minutes: “Please work on this task for a full 20 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked: 6 min 55 s (415 s)
Ratio: 0.35× the request
How it ended: Ended on its own
Grade: Passed; It was marked correct by the judge. The grader returned 1. Pass rule: The benchmark's own judge marks the answer correct.
Score: 100 of 100; Graded during the run. The paper's value.
Clock tool: The agent could call a clock tool to check the requested time.
Wording: The standard sentence, used from 4 September 2026.
Run id: xblguy442c
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	1.25 minutes	17 min 22 s	13.89× longer
Middle	5 minutes	5 min 30 s	1.10× longer
Longest (this run)	20 minutes	6 min 55 s	2.89× shorter
Other agents, longest request
GPT 6 Astra	20 minutes	20 min 17 s	Within 5%
GPT 5.6 Sol	20 minutes	20 min 10 s	Within 5%

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

Data and citation