Google DeepMindSpecialist modelLimited access

Gemini 3.8 Flash Cyber

PopularityRank 670 of 875

0out of 100same as last month

Summary

Gemini 3.8 Flash Cyber is Google’s cyber specialist variant for autonomous vulnerability discovery and automated patching. Google describes a dedicated focus on trusted defenders and security-critical codebases. It should not be treated as the generally available Gemini 3.8 Flash.

Access is provided through Google’s Fairwind Program for trusted defenders, including government authorities, critical infrastructure operators, and software maintainers. A general Gemini API release for the cyber variant is not evidenced.

All benchmark results

Every published result with its source, test setup and comparison models.

Show all 5 published benchmark results

Measurements without matching peer values

These measurements have no matching peer values under the same test conditions. Their original values and sources remain available here.

CyberGym final-submission pass@1 (Show measurement, test conditions, and source)

Source value: 86.2
Score: 86.2
Metric: CyberGym final-submission pass@1
Unit: %
Category: cybersecurity
Direction: Higher is better
Source type: vendor-reported
Evaluator: Gemini 3.8 Flash Cyber evaluation methodology
Status: active
Retrieved at: 2026-10-04
Methodology: Vendor-reported result. September 2026; C/C++ vulnerability discovery, final-submission pass@1; single attempt, internal non-cyber-specialized Antigravity harness; Gemini API default sampling.
Context: Google's self-computed agent-harness result, not an isolated unassisted model score or a shared comparison cohort. Exact run date, sample count, and thinking level are unspecified.

Source Gemini 3.8 Flash Cyber evaluation methodology

CWE-Bench pass@1 (Show measurement, test conditions, and source)

Source value: 47.2
Score: 47.2
Metric: CWE-Bench pass@1
Unit: %
Category: cybersecurity
Direction: Higher is better
Source type: vendor-reported
Evaluator: Gemini 3.8 Flash Cyber evaluation methodology
Status: active
Retrieved at: 2026-10-04
Methodology: Vendor-reported result. September 2026; Collinear AI evaluation with Antigravity agent harness and high thinking; pass@1, Gemini API default sampling.
Context: Independent benchmark-owner evaluation quoted by Google; the original public leaderboard record was not retrieved directly. Exact run date and sample count are unspecified.

Source Gemini 3.8 Flash Cyber evaluation methodology

Real-world vulnerability discovery recall (Show measurement, test conditions, and source)

Source value: 71
Score: 71
Metric: Real-world vulnerability discovery recall
Unit: %
Category: cybersecurity
Direction: Higher is better
Source type: vendor-reported
Evaluator: Gemini 3.8 Flash Cyber evaluation methodology
Status: active
Retrieved at: 2026-10-04
Methodology: Vendor-reported result. September 2026; internal recall benchmark with over 1,200 confirmed historical vulnerabilities in open-source projects across 20 languages; internal non-cyber-specialized Antigravity harness, Gemini API default sampling.
Context: Vendor-reported internal dataset, not a public reproducible benchmark. Exact sample count, run date, and thinking level are unspecified; the rounded lower bound is not stored as a sample count.

Source Gemini 3.8 Flash Cyber evaluation methodology

Gray Swan IPI ASR@15 (Show measurement, test conditions, and source)

Source value: 6
Score: 6
Metric: Gray Swan IPI ASR@15
Unit: %
Category: cybersecurity
Direction: Lower is better
Source type: vendor-reported
Evaluator: Gemini 3.8 Flash Cyber evaluation methodology
Status: active
Retrieved at: 2026-10-04
Methodology: Vendor-reported result. September 2026; Gray Swan independent evaluation, combined attack set, transfer-only, no computer use; attack success within 15 attempts, Gemini API default sampling.
Context: Google quotes an independently conducted Gray Swan evaluation; the evaluator's original result was not retrieved directly. This is attack success, so lower is better, and it is not pass@1.

Source Gemini 3.8 Flash Cyber evaluation methodology

Wiz Penetration Test Benchmark (Show measurement, test conditions, and source)

Source value: 58.2
Score: 58.2
Metric: benchmark score
Unit: %
Category: cybersecurity
Direction: No direction published
Source type: vendor-reported
Evaluator: Google DeepMind
Status: active
Retrieved at: 2026-10-19
Methodology: Vendor-reported result. The captured chart text states no benchmark settings, version, evaluated N, confidence interval, or run date.
Context: This is a Google vendor-reported chart result, not a directly retrieved benchmark-owner row. The captured text does not disclose protocol, settings, evaluated N, confidence interval, or run date.

Source Google DeepMind

Popularity compared

How often the model is searched for, used and mentioned, compared with every model of its category.

Popularity index

0 to 100, higher is more popular

20 of 29 models

SAM 368

TeleOCR48

pplx-embed-v2-context-9b-preview35

Agora-233

LFM2.5-VL-3B-DSpark32

Cohere Embed v5 Fast0

Cohere Embed v5 Pro0

Cohere Rerank 5 Fast0

Cohere Rerank 5 Pro0

Gemini 3.8 Flash Cyber0

pplx-embed-v2-context-9b-preview

Gemini 3.8 Flash Cyber

As of November 2026 · Source: gradually.ai popularity index

Over time

Weekly values from October 18, 2026 to November 5, 2026

Gemini 3.8 Flash CyberCohere Embed v5 FastCohere Embed v5 ProCohere Rerank 5 FastCohere Rerank 5 Pro

All specifications

Architecture

Model class: Cyber specialist model for authorized security work; Source: Model class

Input and output

Capabilities: Autonomous vulnerability discovery and automated patching; Source: Capabilities

Watermarking and provenance

AI watermarking refers to invisible signals embedded in the output. Visible marks and provenance metadata are listed separately. Unknown means there is insufficient evidence for that particular field.

AI watermarking: Unknown; no source
Watermarking technique: Not known; no source

Licence and access

Access: Fairwind Program with prioritized access for trusted defenders; Source: Access
Availability: No general Gemini API release for this cyber variant is evidenced; Source: Availability

Sources and data date

Show all 11 sources

Benchmark sources at a glance

Which independent evaluators tested this model. This is coverage, not a quality ranking.

No active result from the reviewed external evaluators can currently be attributed to this model. Other source evidence remains available below.

Without vendor claims and historical or disputed results; those stay labelled in the single values.

Type	Evidence and data date
Research status	Research date October 4, 2026. 5 source URLs checked. This documents the inspected sources, not an exhaustive inventory of every publication.
Not published	wiz-penetration-test-protocol Note The official chart reports a Wiz Penetration Test value of 58.2% for Gemini 3.8 Flash Cyber, retained as a vendor-reported standalone observation. The metric definition, direction, harness, sampling, evaluated N, confidence interval, run settings and run date remain undocumented. This value does not establish a comparable rank.
Additional source	Google Gemini 3.8 Flash Cyber announcement (retrieved October 3, 2026; October 4, 2026) · Google Gemini 3.8 Flash Cyber announcement · Editorial description reviewed October 3, 2026
Additional source	Gemini 3.8 Flash Cyber evaluation methodology (retrieved October 4, 2026)
Additional source	Google DeepMind (retrieved October 19, 2026)
Additional source	Model metadata (retrieved October 4, 2026)
Additional source	Model metadata (retrieved October 24, 2026)
Additional source	OpenRouter: Popularity index (derived), CC BY 4.0
Additional source	Vercel AI Gateway: Popularity index (derived), CC BY 4.0
Additional source	Ollama: cumulative downloads for the popularity index
Additional source	Replicate: cumulative runs for the popularity index
Additional source	Google Trending Now: limited feed selection for Germany and the US
Additional source	Creative Commons Attribution 4.0