# Jailbreak Attack on AdvBench Llama3.1-405B 1.0 (test) Source: [Jailbreak Attack on AdvBench Llama3.1-405B 1.0 (test)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:23:54.692Z Evaluation of model robustness against Jailbreak Attacks using the AdvBench configuration specifically targeting the Llama 3.1 405B model (test set), measured by Attack Success Rate (ASR). 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 Attack | | Dataset (including any stated split) | AdvBench Llama3.1-405B 1.0 (test) | | Metric | ASR | | Unit | PERCENT | | Direction | Lower is better | | Results loaded | 17 of 17 | | 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](): Lower is better; unit: PERCENT. ## Recorded results | Method | ASR | Result date | Report paper | | --- | --- | --- | --- | | GCG | 0 | Not recorded | 69535c9253fdd5c36173da26 | | MAC | 0 | Not recorded | 69535c9253fdd5c36173da26 | | Base64 | 0 | Not recorded | 69535c9253fdd5c36173da26 | | GPTFuzzer | 0 | Not recorded | 69535c9253fdd5c36173da26 | | DRA | 0 | Not recorded | 69535c9253fdd5c36173da26 | | PromptAttack | 0 | Not recorded | 69535c9253fdd5c36173da26 | | SelfCipher | 0 | Not recorded | 69535c9253fdd5c36173da26 | | ArtPromopt | 38 | Not recorded | 69535c9253fdd5c36173da26 | | CodeChameleon | 58 | Not recorded | 69535c9253fdd5c36173da26 | | COLD-Attack | 77 | Not recorded | 69535c9253fdd5c36173da26 | | TAP | 77 | Not recorded | 69535c9253fdd5c36173da26 | | ReNeLLM | 154 | Not recorded | 69535c9253fdd5c36173da26 | | DeepInception | 192 | Not recorded | 69535c9253fdd5c36173da26 | | PAIR | 212 | Not recorded | 69535c9253fdd5c36173da26 | | AutoDAN | 327 | Not recorded | 69535c9253fdd5c36173da26 | | EquaCode | 1788 | Not recorded | 69535c9253fdd5c36173da26 | | Flipattack | 2750 | Not recorded | 69535c9253fdd5c36173da26 | ### GCG ASR: 0. Result ID: 6996f9dd5698665ec446aaa6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Attack Type":"Automated","Evaluator":"GPT-4"}. This record does not assert independent reproduction. ### MAC ASR: 0. Result ID: 6996f9dd5698665ec446aaa8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Attack Type":"Automated","Evaluator":"GPT-4"}. This record does not assert independent reproduction. ### Base64 ASR: 0. Result ID: 6996f9dd5698665ec446aaac. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Attack Type":"Automated","Evaluator":"GPT-4"}. This record does not assert independent reproduction. ### GPTFuzzer ASR: 0. Result ID: 6996f9dd5698665ec446aaad. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Attack Type":"Automated","Evaluator":"GPT-4"}. This record does not assert independent reproduction. ### DRA ASR: 0. Result ID: 6996f9dd5698665ec446aaaf. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Attack Type":"Manual","Evaluator":"GPT-4"}. This record does not assert independent reproduction. ### PromptAttack ASR: 0. Result ID: 6996f9dd5698665ec446aab1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Attack Type":"Manual","Evaluator":"GPT-4"}. This record does not assert independent reproduction. ### SelfCipher ASR: 0. Result ID: 6996f9dd5698665ec446aab2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Attack Type":"Manual","Evaluator":"GPT-4"}. This record does not assert independent reproduction. ### ArtPromopt ASR: 38. Result ID: 6996f9dd5698665ec446aab0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Attack Type":"Manual","Evaluator":"GPT-4"}. This record does not assert independent reproduction. ### CodeChameleon ASR: 58. Result ID: 6996f9dd5698665ec446aab3. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Attack Type":"Manual","Evaluator":"GPT-4"}. This record does not assert independent reproduction. ### COLD-Attack ASR: 77. Result ID: 6996f9dd5698665ec446aaa9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Attack Type":"Automated","Evaluator":"GPT-4"}. This record does not assert independent reproduction. ### TAP ASR: 77. Result ID: 6996f9dd5698665ec446aaab. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Attack Type":"Automated","Evaluator":"GPT-4"}. This record does not assert independent reproduction. ### ReNeLLM ASR: 154. Result ID: 6996f9dd5698665ec446aab4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Attack Type":"Manual","Evaluator":"GPT-4"}. This record does not assert independent reproduction. ### DeepInception ASR: 192. Result ID: 6996f9dd5698665ec446aaae. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Attack Type":"Manual","Evaluator":"GPT-4"}. This record does not assert independent reproduction. ### PAIR ASR: 212. Result ID: 6996f9dd5698665ec446aaaa. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Attack Type":"Automated","Evaluator":"GPT-4"}. This record does not assert independent reproduction. ### AutoDAN ASR: 327. Result ID: 6996f9dd5698665ec446aaa7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Attack Type":"Automated","Evaluator":"GPT-4"}. This record does not assert independent reproduction. ### EquaCode ASR: 1788. Result ID: 6996f9dd5698665ec446aab6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluator":"GPT-4"}. This record does not assert independent reproduction. ### Flipattack ASR: 2750. Result ID: 6996f9dd5698665ec446aab5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Attack Type":"Manual","Evaluator":"GPT-4"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.