TUA-Bench, shortest of three requests

Claude Fable 5.1 on “Daily email report”

Shorter

1.26× shorter

Stopped at 79% of the time asked, 19 s short.

Asked

Worked

Safety cutoff 50 min, off the scale

Every detail of this run

Agent: Claude Fable 5.1, in Claude Code
Benchmark: TUA-Bench
Task: Daily email report
Asked for: 1.5 minutes: “Please work on this task for a full 1.5 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked: 1 min 11 s (71 s)
Ratio: 0.79× the request
How it ended: Stopped by an error
Grade: Passed; It completed the task in full. The grader returned 1. Pass rule: Full completion: a reward of 1 on the final state.
Score: 100 of 100; Graded during the run. The paper's value.
Wording: The standard sentence, used from 4 September 2026.
Run id: zdjcdu65gi
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 (this run)	1.5 minutes	1 min 11 s	1.26× shorter
Middle	6 minutes	2 min 22 s	2.53× shorter
Longest	25 minutes	2 min 9 s	11.67× shorter
Other agents, shortest request
GPT 6 Astra	1.5 minutes	1 min 43 s	1.15× longer
GPT 5.6 Sol	1.5 minutes	1 min 49 s	1.21× longer
Muse Spark 1.3	1.5 minutes	1 min 47 s	1.19× longer

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