TUA-Bench, longest of three requests

GPT 6 Astra on “Extract presenter photos”

Within 5%

Worked 102% of the time asked, within 5% of it.

Asked

Worked

Safety cutoff 1 h 20 min, off the scale

Every detail of this run

Agent: GPT 6 Astra, in Codex
Benchmark: TUA-Bench
Task: Extract presenter photos
Asked for: 40 minutes: “Please work on this task for a full 40 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked: 40 min 46 s (2,446 s)
Ratio: 1.02× 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 afterwards. The paper's value.
Wording: The standard sentence, used from 4 September 2026.
Run id: tahcyo64pt
Data release: 26 Sep 2026

The other requests for GPT 6 Astra on this task, and the other agents at this request
Astra on this task	Asked	Worked	Result
Shortest	2.5 minutes	2 min 51 s	1.14× longer
Middle	10 minutes	10 min 38 s	1.06× longer
Longest (this run)	40 minutes	40 min 46 s	Within 5%
Other agents, longest request
GPT 5.6 Sol	40 minutes	41 min 33 s	Within 5%
Claude Fable 5.1	40 minutes	5 min 7 s	7.81× shorter

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