# Jailbreak Attack on AdvBench GPT-4 1.0 (test) Source: [Jailbreak Attack on AdvBench GPT-4 1.0 (test)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:23:54.607Z Evaluation of model susceptibility to jailbreak attacks using the specific AdvBench GPT-4 1.0 test set, reporting 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 GPT-4 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 | | --- | --- | --- | --- | | MAC | 0.77 | Not recorded | 69535c9253fdd5c36173da26 | | COLD-Attack | 0.77 | Not recorded | 69535c9253fdd5c36173da26 | | Base64 | 0.77 | Not recorded | 69535c9253fdd5c36173da26 | | PromptAttack | 0.96 | Not recorded | 69535c9253fdd5c36173da26 | | GCG | 1.73 | Not recorded | 69535c9253fdd5c36173da26 | | ArtPromopt | 1.75 | Not recorded | 69535c9253fdd5c36173da26 | | CodeChameleon | 22.27 | Not recorded | 69535c9253fdd5c36173da26 | | AutoDAN | 26.54 | Not recorded | 69535c9253fdd5c36173da26 | | PAIR | 27.18 | Not recorded | 69535c9253fdd5c36173da26 | | DeepInception | 27.27 | Not recorded | 69535c9253fdd5c36173da26 | | TAP | 40.97 | Not recorded | 69535c9253fdd5c36173da26 | | SelfCipher | 41.73 | Not recorded | 69535c9253fdd5c36173da26 | | GPTFuzzer | 42.5 | Not recorded | 69535c9253fdd5c36173da26 | | ReNeLLM | 68.08 | Not recorded | 69535c9253fdd5c36173da26 | | DRA | 82.88 | Not recorded | 69535c9253fdd5c36173da26 | | Flipattack | 86.73 | Not recorded | 69535c9253fdd5c36173da26 | | EquaCode | 91.92 | Not recorded | 69535c9253fdd5c36173da26 | ### MAC ASR: 0.77. Result ID: 6996f9dd5698665ec446aa53. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Attack Type":"Automated","Evaluator":"GPT-4"}. This record does not assert independent reproduction. ### COLD-Attack ASR: 0.77. Result ID: 6996f9dd5698665ec446aa54. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Attack Type":"Automated","Evaluator":"GPT-4"}. This record does not assert independent reproduction. ### Base64 ASR: 0.77. Result ID: 6996f9dd5698665ec446aa57. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Attack Type":"Automated","Evaluator":"GPT-4"}. This record does not assert independent reproduction. ### PromptAttack ASR: 0.96. Result ID: 6996f9dd5698665ec446aa5c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Attack Type":"Manual","Evaluator":"GPT-4"}. This record does not assert independent reproduction. ### GCG ASR: 1.73. Result ID: 6996f9dd5698665ec446aa51. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Attack Type":"Automated","Evaluator":"GPT-4"}. This record does not assert independent reproduction. ### ArtPromopt ASR: 1.75. Result ID: 6996f9dd5698665ec446aa5b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Attack Type":"Manual","Evaluator":"GPT-4"}. This record does not assert independent reproduction. ### CodeChameleon ASR: 22.27. Result ID: 6996f9dd5698665ec446aa5e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Attack Type":"Manual","Evaluator":"GPT-4"}. This record does not assert independent reproduction. ### AutoDAN ASR: 26.54. Result ID: 6996f9dd5698665ec446aa52. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Attack Type":"Automated","Evaluator":"GPT-4"}. This record does not assert independent reproduction. ### PAIR ASR: 27.18. Result ID: 6996f9dd5698665ec446aa55. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Attack Type":"Automated","Evaluator":"GPT-4"}. This record does not assert independent reproduction. ### DeepInception ASR: 27.27. Result ID: 6996f9dd5698665ec446aa59. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Attack Type":"Manual","Evaluator":"GPT-4"}. This record does not assert independent reproduction. ### TAP ASR: 40.97. Result ID: 6996f9dd5698665ec446aa56. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Attack Type":"Automated","Evaluator":"GPT-4"}. This record does not assert independent reproduction. ### SelfCipher ASR: 41.73. Result ID: 6996f9dd5698665ec446aa5d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Attack Type":"Manual","Evaluator":"GPT-4"}. This record does not assert independent reproduction. ### GPTFuzzer ASR: 42.5. Result ID: 6996f9dd5698665ec446aa58. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Attack Type":"Automated","Evaluator":"GPT-4"}. This record does not assert independent reproduction. ### ReNeLLM ASR: 68.08. Result ID: 6996f9dd5698665ec446aa5f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Attack Type":"Manual","Evaluator":"GPT-4"}. This record does not assert independent reproduction. ### DRA ASR: 82.88. Result ID: 6996f9dd5698665ec446aa5a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Attack Type":"Manual","Evaluator":"GPT-4"}. This record does not assert independent reproduction. ### Flipattack ASR: 86.73. Result ID: 6996f9dd5698665ec446aa60. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Attack Type":"Manual","Evaluator":"GPT-4"}. This record does not assert independent reproduction. ### EquaCode ASR: 91.92. Result ID: 6996f9dd5698665ec446aa61. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluator":"GPT-4"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.