TUA-Bench, shortest of three requests

GPT 5.6 Sol on “Extract gym auditorium”

Longer

5.68× longer

Worked 468% past the request, 5 min 51 s over.

Asked

Worked

Safety cutoff 40 min, off the scale

Every detail of this run

Agent: GPT 5.6 Sol, in Codex
Benchmark: TUA-Bench
Task: Extract gym auditorium
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: 7 min 6 s (426 s)
Ratio: 5.68× the request
How it ended: Ended on its own
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: zbk4xnfnrl
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	7 min 6 s	5.68× longer
Middle	5 minutes	6 min 20 s	1.27× longer
Longest	20 minutes	21 min 32 s	1.08× longer
Other agents, shortest request
GPT 6 Astra	1.25 minutes	1 min 37 s	1.29× longer
Claude Fable 5.1	1.25 minutes	21 min 32 s	17.23× longer
Muse Spark 1.3	1.25 minutes	3 min 20 s	2.66× longer

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

Data and citation