Big Sleep Evaluation (Google)

Agents search large real codebases such as Chrome and Safari for critical, hard to find vulnerabilities. Scored by pass@1 success rate, run without safety guardrails.

Google's Big Sleep team built it independently of the model team. Reported for Gemini 3.5 Flash Cyber at 72, against 36 for Gemini 3.5 Flash.

Made by Google (Big Sleep team) Released Jul 2026 Finding and exploiting real bugs Tasks kept private Last in a launch post Jul 2026 Last model added Jul 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.

deepmind.google

Model scored in lab cards

Launch post lists it, from 1 lab

Gemini 3.5 Flash Cyber 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 3.5 Flash Cyber

1 Gemini 3.5 Flash Cyber 72%

#	Model	Score	Setting	Date	Source
1	Gemini 3.5 Flash Cyber	72%		Jul 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

One lab put it in a launch post in the last six months

Launch posts from every lab that has listed it, one tick per post. Tall colored ticks include it, and short gray ones leave it out.

Google DeepMind

Date	Launch post	Score	As the post writes it
21 Jul 2026	Gemini 3.5 Flash Cyber	72	Success Rate on Big Sleep Evaluation (pass@1)

Gemini 3.5 Flash Cyber leads with 72%

Scores over time

One lab put it in a launch post in the last six months

More in Cybersecurity