Humanity's Last Exam, longest of three requests

Claude Fable 5.1 on “Humanity's Last Exam item 7”

Shorter

2.51× shorter

Stopped at 40% of the time asked, 12 min 2 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 7
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: 7 min 58 s (478 s)
Ratio: 0.40× 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: ihj6po5fpd
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	5 min 40 s	4.53× longer
Middle	5 minutes	7 min 2 s	1.41× longer
Longest (this run)	20 minutes	7 min 58 s	2.51× shorter
Other agents, longest request
GPT 6 Astra	20 minutes	20 min 10 s	Within 5%
GPT 5.6 Sol	20 minutes	20 min 23 s	Within 5%

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

Data and citation