TUA-Bench, shortest of three requests

GPT 6 Astra on “Place heater for sensors”

Longer

1.08× longer

Worked 8% past the request, 20 s over.

Asked

Worked

Safety cutoff 2 h, off the scale

Every detail of this run

Agent: GPT 6 Astra, in Codex
Benchmark: TUA-Bench
Task: Place heater for sensors
Asked for: 4 minutes: “Please work on this task for a full 4 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked: 4 min 20 s (260 s)
Ratio: 1.08× the request
How it ended: Ending not labelled yet
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: ioiod4buqs
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)	4 minutes	4 min 20 s	1.08× longer
Middle	15 minutes	15 min 29 s	Within 5%
Longest	60 minutes	1 h	Within 5%
Other agents, shortest request
GPT 5.6 Sol	4 minutes	8 min 46 s	2.19× longer
Claude Fable 5.1	4 minutes	2 h	30.00× longer
Muse Spark 1.3	4 minutes	12 min 18 s	3.08× longer

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

Read before quoting. How this run ended has not been labelled yet. It is timed like every other run and counted in every number. Details

Data and citation