Agents' Last Exam, longest of three requests

Claude Fable 5.1 on “Route a KiCad PCB from the staged schematic”

Shorter

3.79× shorter

Stopped at 26% of the time asked, 1 h 50 min short.

Asked

Worked

Safety cutoff 5 h, off the scale

Asked for: 150 minutes
Worked: 39 min 36 s
Grade: Waiting for its machine; The run's output is on its virtual machine's disk, and grading it needs a restored copy of that machine.
How it ended: Stopped by an error

Every detail of this run

Agent: Claude Fable 5.1, in Claude Code
Benchmark: Agents' Last Exam
Task: Route a KiCad PCB from the staged schematic
Asked for: 150 minutes: “Please work on this task for a full 150 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked: 39 min 36 s (2,376 s)
Ratio: 0.26× the request
How it ended: Stopped by an error
Grade: Waiting for its machine; The run's output is on its virtual machine's disk, and grading it needs a restored copy of that machine.
Wording: The standard sentence, used from 4 September 2026.
Run id: xftynsmx75
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	10 minutes	25 min 55 s	2.59× longer
Middle	40 minutes	50 min 42 s	1.27× longer
Longest (this run)	150 minutes	39 min 36 s	3.79× shorter
Other agents, longest request
GPT 6 Astra	150 minutes	2 h 32 min	Within 5%
GPT 5.6 Sol	150 minutes	1 h 32 min	1.63× shorter

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

Read before quoting. This run was stopped by an error, so its time is a lower bound: the agent might have kept going. Details

Data and citation