TUA-Bench, shortest of three requests

GPT 5.6 Sol on “EPW parquet check”

Longer

2.88× longer

Worked 188% past the request, 2 min 49 s over.

Asked

Worked

Safety cutoff 50 min, off the scale

Every detail of this run

Agent: GPT 5.6 Sol, in Codex
Benchmark: TUA-Bench
Task: EPW parquet check
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: 4 min 19 s (259 s)
Ratio: 2.88× the request
How it ended: Ended on its own
Grade: Did not pass; It did not complete the task in full. The grader returned 0.66. Pass rule: Full completion: a reward of 1 on the final state.
Score: 66 of 100; Graded during the run. The paper's value.
Wording: The standard sentence, used from 4 September 2026.
Run id: t2jnbk7gr5
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)	1.5 minutes	4 min 19 s	2.88× longer
Middle	6 minutes	6 min 52 s	1.15× longer
Longest	25 minutes	27 min 6 s	1.08× longer
Other agents, shortest request
GPT 6 Astra	1.5 minutes	3 min 42 s	2.47× longer
Claude Fable 5.1	1.5 minutes	7 min 17 s	4.86× longer
Muse Spark 1.3	1.5 minutes	4 min 13 s	2.81× longer

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

Data and citation