Skip to content

Evaluation

Code vulnerability detection evaluation (multiple-choice datasets)

Multiple-choice vulnerability detection datasets (Chen et al. 2023a; Ding et al. 2024; Wang et al. 2019b; Zhou et al. 2021): classify whether snippets contain vulnerabilities or diffs are security-related

Cybersecurity Google DeepMind — Gemini

How it was run

Open a release to see the setup, scoring, and other details that the lab published. Only fields the lab actually disclosed are shown.

Gemini 1.5
Google DeepMind — Gemini

rich detail 9 method fields published

See how this test was run