TUA-Bench, shortest of three requests

GPT 6 Astra on “First-author table”

Longer

1.15× longer

Worked 15% past the request, 22 s over.

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: First-author table
Asked for: 2.5 minutes: “Please work on this task for a full 2.5 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked: 2 min 52 s (172 s)
Ratio: 1.15× 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: dbmbqnnnst
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 (this run)	2.5 minutes	2 min 52 s	1.15× longer
Middle	10 minutes	10 min 22 s	Within 5%
Longest	40 minutes	40 min 39 s	Within 5%
Other agents, shortest request
GPT 5.6 Sol	2.5 minutes	3 min 38 s	1.45× longer
Claude Fable 5.1	2.5 minutes	2 min 6 s	1.19× shorter
Muse Spark 1.3	2.5 minutes	2 min 22 s	1.06× shorter

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

Data and citation