Big Sleep Evaluation (Google)

Gemini 3.5 Flash Cyber 72% leads since July 2026

In use

Labs’ own numbers All independent runs

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: July 2026
Kind: Finding and exploiting real bugs
Level: Expert
Scored: Checked automatically
Answers: Agent task
Tasks: Kept private

Strongest model tested: Gemini 3.5 Flash #43 on the capability index
Last in a launch post: July 2026
Last model added: July 2026
Scores refreshed: November 12th, 2026

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.

Gemini 3.5 Flash Cyber leads with 72% across all independent runs

Best score per model across the official leaderboard, Epoch AI’s own runs and any board Epoch AI copied. Each bar and row names its source.

Bars Table

72.0 Gemini 3.5 Flash Cyber

1 Gemini 3.5 Flash Cyber 72%

Source: Labs’ model cards

Source: Official Big Sleep Evaluation (Google) leaderboard

#	Model	Score	Setting	Date	Source
1	Gemini 3.5 Flash Cyber	72%		Jul 2026	Lab model card

#	Model	Score	Date	Source
1	Gemini 3.5 Flash Cyber	72%	Jul 2026	Official leaderboard
2	Gemini 3.6 Flash	42%	Jul 2026	Official leaderboard
3	Gemini 3.5 Flash	36%	May 2026	Official leaderboard

The benchmark's own leaderboard has 3 models. Switch the scores above to rank them together.

Number one over time 2 models have held number one across all independent runs since its release in July 2026

Lab claims count from the day the card came out, independent runs from the model’s release.

Google DeepMind

Own leaderboard Not tested since Jul 2026

Gemini 3.5 Flash Cyber 72%

Source: Official Big Sleep Evaluation (Google) leaderboard

Scores over time

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

On the benchmark’s own leaderboard Reported by the lab in its model card Best so far

Sources: Official Big Sleep Evaluation (Google) leaderboard and labs’ model cards

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
Jul 21, 2026	Gemini 3.5 Flash Cyber	72	Success Rate on Big Sleep Evaluation (pass@1)

One lab claim next to the leaderboard

Each score a lab reported for its own model, beside the same model's best score on the leaderboard. Gaps mostly come from different harnesses, effort levels and task subsets. 1 of them match, which usually means one side copied the other. Every benchmark.

Model	Lab says	Board says	Gap
Gemini 3.5 Flash Cyber	72% Success Rate on Big Sleep Evaluation (pass@1)	72% Leaderboard	Same