# Jailbreak Prompt Classification on AdvBench 520 prompts Source: [Jailbreak Prompt Classification on AdvBench 520 prompts]() Collection index: [llms.txt]() Data updated: 2026-04-02T09:17:19.061Z Evaluation of model performance on classifying jailbreak prompts using the specific 520-prompt subset of the AdvBench dataset, measured by Accuracy. A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. | Scope | Recorded value | | --- | --- | | Task | Jailbreak Prompt Classification | | Dataset (including any stated split) | AdvBench 520 prompts | | Metric | Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 1 of 1 | | Coverage | All results currently returned for this benchmark | Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol. ## Metrics - [Accuracy](): Higher is better; unit: PERCENT. ## Recorded results | Method | Accuracy | Result date | Report paper | | --- | --- | --- | --- | | Kumar et al. | 93 | Not recorded | 68fa7a081e209131cea80a81 | ### Kumar et al. Accuracy: 93. Result ID: 69ce341b47f34ce924b79c66. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Attack Vectors":"Jailbreaking but not specific to phishing","Models":"Llama 2, DistilBERT","Best Model":"Llama 2"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.