Agents' Last Exam, shortest of three requests

GPT 5.6 Sol on “Compress a 3D Gaussian Splatting scene without losing quality”

Longer

2.73× longer

Worked 173% past the request, 6 min 55 s over.

Asked

Worked

Safety cutoff 2 h, off the scale

Every detail of this run

Agent: GPT 5.6 Sol, in Codex
Benchmark: Agents' Last Exam
Task: Compress a 3D Gaussian Splatting scene without losing quality
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: 10 min 55 s (655 s)
Ratio: 2.73× the request
How it ended: Ended on its own
Grade: Passed; It passed the task's checker in full. The grader returned 1. Pass rule: Full pass: a checker score of 1.
Score: 100 of 100; Graded afterwards. The paper's value.
Wording: The standard sentence, used from 4 September 2026.
Run id: mznflrhuvl
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 (this run)	4 minutes	10 min 55 s	2.73× longer
Middle	15 minutes	28 min 36 s	1.91× longer
Longest	60 minutes	1 h 1 min	Within 5%
Other agents, shortest request
GPT 6 Astra	4 minutes	6 min 39 s	1.66× longer
Claude Fable 5.1	4 minutes	43 min 45 s	10.94× longer

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

Data and citation