Terminal-Bench 4.0, longest of three requests

Claude Fable 5.1 on “Recalculate SA-CCR exposure, RWA, capital, and workbook evidence”

Shorter

3.29× shorter

Stopped at 30% of the time asked, 41 min 47 s short.

Asked

Worked

Safety cutoff 2 h, off the scale

Every detail of this run

Agent: Claude Fable 5.1, in Claude Code
Benchmark: Terminal-Bench 4.0
Task: Recalculate SA-CCR exposure, RWA, capital, and workbook evidence
Asked for: 60 minutes: “Please work on this task for a full 60 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked: 18 min 13 s (1,093 s)
Ratio: 0.30× the request
How it ended: Ended on its own
Grade: Passed; It passed the task's tests. The grader returned 1. Pass rule: The task's tests pass.
Score: 100 of 100; Graded during the run. The paper's value.
Wording: The standard sentence, used from 4 September 2026.
Run id: 5ci5h7rdvl
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	4 minutes	12 min 6 s	3.02× longer
Middle	15 minutes	15 min 40 s	Within 5%
Longest (this run)	60 minutes	18 min 13 s	3.29× shorter
Other agents, longest request
GPT 6 Astra	60 minutes	1 h 1 min	Within 5%
GPT 5.6 Sol	60 minutes	1 h 1 min	Within 5%

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

Data and citation