# LLM Jailbreaking on AdvBench (ASR-M & ASR-J) Source: [LLM Jailbreaking on AdvBench (ASR-M & ASR-J)]() Collection index: [llms.txt]() Data updated: 2026-04-29T07:21:43.894Z Evaluation of model susceptibility to jailbreaking prompts using the AdvBench dataset, specifically reporting Attack Success Rates measured by ASR-M and ASR-J metrics. 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 | LLM Jailbreaking | | Dataset (including any stated split) | AdvBench | | Metric | ASR-M | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 16 of 16 | | 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 - [ASR-M](): Higher is better; unit: PERCENT. - [ASR-J](): Higher is better; unit: PERCENT. ## Recorded results | Method | ASR-M | Result date | Report paper | | --- | --- | --- | --- | | PEO | 88.27 | Not recorded | 69f1907555a3c32af89fb9a8 | | SPT | 82.69 | Not recorded | 69f1907555a3c32af89fb9a8 | | nanoGCG | 81.35 | Not recorded | 69f1907555a3c32af89fb9a8 | | PEO | 70.58 | Not recorded | 69f1907555a3c32af89fb9a8 | | SPT | 69.81 | Not recorded | 69f1907555a3c32af89fb9a8 | | PEO | 59.62 | Not recorded | 69f1907555a3c32af89fb9a8 | | BEAST | 58.08 | Not recorded | 69f1907555a3c32af89fb9a8 | | nanoGCG | 55.38 | Not recorded | 69f1907555a3c32af89fb9a8 | | nanoGCG | 48.46 | Not recorded | 69f1907555a3c32af89fb9a8 | | SPT | 40.58 | Not recorded | 69f1907555a3c32af89fb9a8 | | PEO | 38.65 | Not recorded | 69f1907555a3c32af89fb9a8 | | BEAST | 28.08 | Not recorded | 69f1907555a3c32af89fb9a8 | | BEAST | 24.42 | Not recorded | 69f1907555a3c32af89fb9a8 | | SPT | 18.85 | Not recorded | 69f1907555a3c32af89fb9a8 | | nanoGCG | 15.38 | Not recorded | 69f1907555a3c32af89fb9a8 | | BEAST | 10.38 | Not recorded | 69f1907555a3c32af89fb9a8 | ### PEO ASR-M: 88.27. Result ID: 69f1b0d047f34ce924d7bf74. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Llama-3.2-3B-Instruct"}. This record does not assert independent reproduction. ### SPT ASR-M: 82.69. Result ID: 69f1b0d047f34ce924d7bf76. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model":"Llama-3.2-3B-Instruct"}. This record does not assert independent reproduction. ### nanoGCG ASR-M: 81.35. Result ID: 69f1b0d047f34ce924d7bf69. [Reporting paper]() Recorded evaluation configuration: {"Model":"Vicuna-7B v1.3"}. This record does not assert independent reproduction. ### PEO ASR-M: 70.58. Result ID: 69f1b0d047f34ce924d7bf68. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Vicuna-7B v1.3"}. This record does not assert independent reproduction. ### SPT ASR-M: 69.81. Result ID: 69f1b0d047f34ce924d7bf6a. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model":"Vicuna-7B v1.3"}. This record does not assert independent reproduction. ### PEO ASR-M: 59.62. Result ID: 69f1b0d047f34ce924d7bf6c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Llama-2-7B-Chat"}. This record does not assert independent reproduction. ### BEAST ASR-M: 58.08. Result ID: 69f1b0d047f34ce924d7bf77. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Llama-3.2-3B-Instruct"}. This record does not assert independent reproduction. ### nanoGCG ASR-M: 55.38. Result ID: 69f1b0d047f34ce924d7bf6d. [Reporting paper]() Recorded evaluation configuration: {"Model":"Llama-2-7B-Chat"}. This record does not assert independent reproduction. ### nanoGCG ASR-M: 48.46. Result ID: 69f1b0d047f34ce924d7bf75. [Reporting paper]() Recorded evaluation configuration: {"Model":"Llama-3.2-3B-Instruct"}. This record does not assert independent reproduction. ### SPT ASR-M: 40.58. Result ID: 69f1b0d047f34ce924d7bf6e. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model":"Llama-2-7B-Chat"}. This record does not assert independent reproduction. ### PEO ASR-M: 38.65. Result ID: 69f1b0d047f34ce924d7bf70. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Qwen3-4B-Instruct"}. This record does not assert independent reproduction. ### BEAST ASR-M: 28.08. Result ID: 69f1b0d047f34ce924d7bf73. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Qwen3-4B-Instruct"}. This record does not assert independent reproduction. ### BEAST ASR-M: 24.42. Result ID: 69f1b0d047f34ce924d7bf6b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Vicuna-7B v1.3"}. This record does not assert independent reproduction. ### SPT ASR-M: 18.85. Result ID: 69f1b0d047f34ce924d7bf72. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model":"Qwen3-4B-Instruct"}. This record does not assert independent reproduction. ### nanoGCG ASR-M: 15.38. Result ID: 69f1b0d047f34ce924d7bf71. [Reporting paper]() Recorded evaluation configuration: {"Model":"Qwen3-4B-Instruct"}. This record does not assert independent reproduction. ### BEAST ASR-M: 10.38. Result ID: 69f1b0d047f34ce924d7bf6f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Llama-2-7B-Chat"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.