← Model benchmark
Google DeepMind · Gemini Flash Cyber

Gemini 3.5 Flash Cyber

READER SUMMARY

A cyber-specialized Gemini model deployed through CodeMender for scalable vulnerability discovery, validation, exploitation testing, and patch generation.

DOOM SCORE72.2out of 100model risk profile, not the overall index
CURRENT ASSESSMENT · REVISION 1

Why this model scores 72.2

The model independently works through large codebases, found real remote-code-execution and memory-corruption flaws, and can generate reliable exploits. Its exclusivity to governments and trusted partners in a limited CodeMender pilot sharply reduces deployment, but the dual-use capability and lowered defensive barriers keep misuse potential and control difficulty high.

Capability78
Autonomy84
Deployment25
Misuse potential92
Control difficulty72
MODEL-ATTRIBUTED EVIDENCE

News tied to Gemini 3.5 Flash Cyber

The model score of 72.2 rates this model's risk profile. The overall Doom Index of 67.7 measures the accumulated evidence trajectory. These values answer different questions.

NET MODEL-ATTRIBUTED INDEX CONTRIBUTION+1.13

Each article's signed Doom Index movement is divided equally among the exact models named on that article. This prevents multi-model evidence from being counted in full on several model pages. The model's risk score itself never changes the overall index.

DeploymentTOWARD

Google releases Gemini Flash models for scaled agentic work

Google released Gemini 3.6 Flash and 3.5 Flash-Lite broadly across developer, enterprise, consumer, and search surfaces, while limiting the specialized 3.5 Flash Cyber model to governments and trusted partners through CodeMender.

Full item movement
+3.38
Gemini 3.5 Flash Cyber equal share
+1.13
Read assessment →
AUDIT TRAIL

Model score history

  1. R1
    Doom Score 72.2

    Initial source-backed profile for the exact cyber-specialized tier.

    11 Aug 2026