Terminal-Bench 4.0, middle of three requests

GPT 5.6 Sol on “Rebuild a retired production risk scorer from black-box behavior”

Within 5%

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

Asked

Worked

Safety cutoff 3 h 20 min, off the scale

Every detail of this run

Agent: GPT 5.6 Sol, in Codex
Benchmark: Terminal-Bench 4.0
Task: Rebuild a retired production risk scorer from black-box behavior
Asked for: 25 minutes: “Please work on this task for a full 25 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked: 25 min 35 s (1,535 s)
Ratio: 1.02× the request
How it ended: Ending not labelled yet
Grade: Did not pass; It did not pass the task's tests. The grader returned 0. Pass rule: The task's tests pass.
Score: 0 of 100; Graded during the run. The paper's value.
Wording: The standard sentence, used from 4 September 2026.
Run id: bgplc3s2p4
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	6 minutes	14 min 1 s	2.33× longer
Middle (this run)	25 minutes	25 min 35 s	Within 5%
Longest	100 minutes	1 h 41 min	Within 5%
Other agents, middle request
GPT 6 Astra	25 minutes	25 min 15 s	Within 5%
Claude Fable 5.1	25 minutes	27 min 2 s	1.08× 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