Internal vulnerability research

Gemini 4 Argon 72% Only in system cards

Agents find a vulnerability from an entry point, with or without source, then write a working exploit. Based on Google red team exercises.

In-house Google DeepMind evaluation. The tasks are not public.

Made by Google DeepMind Finding and exploiting real bugs Tasks kept private Last in a system card Oct 2026 Last model added Oct 2026

Level: Expert Specialists with years of training, often over hours of work
Scored: Checked automatically A program checks the result against an answer key, unit tests or the expected final state.
Answers: Agent task Many steps in a terminal, browser, desktop, app, game or robot.

Model scored in lab cards

System card reports it, from 1 lab

Gemini 4 Argon leads with 72%

Best score per model as labs report them in their own cards. Labs pick their own settings, so these compare less cleanly than independent runs.

Bars Table

72.0 Gemini 4 Argon

1 Gemini 4 Argon 72%

#	Model	Score	Setting	Date	Source
1	Gemini 4 Argon	72%		Oct 2026	Model card

Scores over time

All the scores we have, one dot each, so a model tested at several settings appears more than once.

Reported by the lab in its model card

Labs report it only in system cards

We read the headline results of 479 launch posts from 51 labs, and none of them list this benchmark. Some system cards do, below.

One system card reports it

Besides launch posts, we read the system cards, model cards and technical reports labs publish with a release. They report far more, including safety and frontier-risk tests.

Date	Document	Score	As the document writes it	Section
13 Oct 2026	Gemini 4 Argon system card	72	Internal vulnerability research, find and exploit pass@1 72% (7.1.3)	Cyber risk

Gemini 4 Argon leads with 72%

Scores over time

Labs report it only in system cards

One system card reports it

More in Cybersecurity