Terminal-Bench 4.0, middle of three requests

Claude Fable 5.1 on “Generate physically valid walking, jumping, and running trajectories”

Longer

1.40× longer

Worked 40% past the request, 32 min 5 s over.

Asked

Worked

Safety cutoff 10 h, off the scale

Every detail of this run

Agent: Claude Fable 5.1, in Claude Code
Benchmark: Terminal-Bench 4.0
Task: Generate physically valid walking, jumping, and running trajectories
Asked for: 80 minutes: “Please work on this task for a full 80 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked: 1 h 52 min (6,725 s)
Ratio: 1.40× the request
How it ended: Stopped by an error
Grade: Did not pass; It did not pass the task's tests. The grader returned 0. Pass rule: The task's tests pass.
Score: 0 of 100; Nothing to grade, counted as 0. The paper's value.
Wording: The standard sentence, used from 4 September 2026.
Run id: ua5e33hpd7
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	20 minutes	56 min 9 s	2.81× longer
Middle (this run)	80 minutes	1 h 52 min	1.40× longer
Longest	300 minutes	3 h 6 min	1.61× shorter
Other agents, middle request
GPT 6 Astra	80 minutes	1 h 20 min	Within 5%
GPT 5.6 Sol	80 minutes	1 h 21 min	Within 5%

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