TUA-Bench, middle of three requests

GPT 5.6 Sol on “Daily email report”

Within 5%

Worked 101% of the time asked, within 5% of it.

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: Daily email report
Asked for: 6 minutes: “Please work on this task for a full 6 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked: 6 min 5 s (365 s)
Ratio: 1.01× the request
How it ended: Ending not labelled yet
Grade: Did not pass; It did not complete the task in full. The grader returned 0. Pass rule: Full completion: a reward of 1 on the final state.
Score: 0 of 100; Graded during the run. The paper's value.
Wording: The standard sentence, used from 4 September 2026.
Run id: zouwdenuxj
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	1.5 minutes	1 min 49 s	1.21× longer
Middle (this run)	6 minutes	6 min 5 s	Within 5%
Longest	25 minutes	25 min 40 s	Within 5%
Other agents, middle request
GPT 6 Astra	6 minutes	6 min 9 s	Within 5%
Claude Fable 5.1	6 minutes	2 min 22 s	2.53× shorter
Muse Spark 1.3	6 minutes	2 min 14 s	2.69× shorter

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