TUA-Bench, shortest of three requests

GPT 5.6 Sol on “Fix MP3 metadata”

Longer

1.55× longer

Worked 55% past the request, 42 s over.

Asked

Worked

Safety cutoff 40 min, off the scale

Asked for: 1.25 minutes
Worked: 1 min 57 s
Grade: Files not found; The files this run saved have not been found, so it has no grade.
How it ended: Ended on its own

Every detail of this run

Agent: GPT 5.6 Sol, in Codex
Benchmark: TUA-Bench
Task: Fix MP3 metadata
Asked for: 1.25 minutes: “Please work on this task for a full 1.25 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked: 1 min 57 s (117 s)
Ratio: 1.55× the request
How it ended: Ended on its own
Grade: Files not found; The files this run saved have not been found, so it has no grade.
Wording: The standard sentence, used from 4 September 2026.
Run id: kqoe5ph2lb
Data release: 26 Sep 2026

The other requests for GPT 5.6 Sol on this task, and the other agents at this request
Sol on this task	Asked	Worked	Result
Shortest (this run)	1.25 minutes	1 min 57 s	1.55× longer
Middle	5 minutes	5 min 45 s	1.15× longer
Longest	20 minutes	21 min 6 s	1.05× longer
Other agents, shortest request
GPT 6 Astra	1.25 minutes	1 min 32 s	1.23× longer
Claude Fable 5.1	1.25 minutes	45 s	1.68× shorter

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

Data and citation