BlogLLM Benchmark Scores as Published, Side by Side
Google Internal Vulnerability Research: Results as Published
Every result the catalog holds for Google Internal Vulnerability Research: 1 model from 1 developer, read from 1 page. Each number is as printed by the company named beside it; nothing is ranked or rescored. Models are listed by developer, newest first.
Area CybersecurityMaintainer Google DeepMind (internal evaluation)Data version 2026103001, as of 2026-10-30
Pass at 1 for finding a vulnerability and writing a full code-execution exploit, with and without source code (section 7.1.3, text only).
Not checked against a maintainer's page.
Internal vulnerability research: pass at 1
| Model | Value | Printed by | Setup as printed |
|---|---|---|---|
| Gemini 4 ArgonGoogle, released 2026-09-30 | 72% | Google, Gemini 4 Argon Safety and Security Reportchecked 2026-10-19 | - |
Every number here is read from the same catalog file as the benchmark table, data version 2026103001, and is the number the table shows for that model and test. Where one page printed a model under several setups, each value is listed. The catalog is public in armanobosyan/sugra-llm-benchmarks; a wrong number can be reported from the table, with Report an error under the value, or as an issue in that repository.