# Jailbreak Attack on AdvBench GPT-4o 1.0 (test) Source: [Jailbreak Attack on AdvBench GPT-4o 1.0 (test)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:23:54.648Z Evaluation of model susceptibility to jailbreak attacks using the AdvBench GPT-4o 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-4o 1.0 (test) | | Metric | ASR | | Unit | PERCENT | | Direction | Higher 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](): Higher is better; unit: PERCENT. ## Recorded results | Method | ASR | Result date | Report paper | | --- | --- | --- | --- | | CodeChameleon | 92.67 | Not recorded | 69535c9253fdd5c36173da26 | | Flipattack | 90.77 | Not recorded | 69535c9253fdd5c36173da26 | | DRA | 88.84 | Not recorded | 69535c9253fdd5c36173da26 | | EquaCode | 87.12 | Not recorded | 69535c9253fdd5c36173da26 | | ReNeLLM | 85.38 | Not recorded | 69535c9253fdd5c36173da26 | | GPTFuzzer | 66.73 | Not recorded | 69535c9253fdd5c36173da26 | | TAP | 61.63 | Not recorded | 69535c9253fdd5c36173da26 | | Base64 | 57.88 | Not recorded | 69535c9253fdd5c36173da26 | | PAIR | 47.83 | Not recorded | 69535c9253fdd5c36173da26 | | AutoDAN | 46.92 | Not recorded | 69535c9253fdd5c36173da26 | | DeepInception | 40.04 | Not recorded | 69535c9253fdd5c36173da26 | | ArtPromopt | 4.42 | Not recorded | 69535c9253fdd5c36173da26 | | PromptAttack | 1.92 | Not recorded | 69535c9253fdd5c36173da26 | | GCG | 1.15 | Not recorded | 69535c9253fdd5c36173da26 | | MAC | 0.58 | Not recorded | 69535c9253fdd5c36173da26 | | COLD-Attack | 0.19 | Not recorded | 69535c9253fdd5c36173da26 | | SelfCipher | 0 | Not recorded | 69535c9253fdd5c36173da26 | ### CodeChameleon ASR: 92.67. Result ID: 6996f9dd5698665ec446aa91. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Attack Type":"Manual","Evaluator":"GPT-4"}. This record does not assert independent reproduction. ### Flipattack ASR: 90.77. Result ID: 6996f9dd5698665ec446aa93. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Attack Type":"Manual","Evaluator":"GPT-4"}. This record does not assert independent reproduction. ### DRA ASR: 88.84. Result ID: 6996f9dd5698665ec446aa8d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Attack Type":"Manual","Evaluator":"GPT-4"}. This record does not assert independent reproduction. ### EquaCode ASR: 87.12. Result ID: 6996f9dd5698665ec446aa94. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluator":"GPT-4"}. This record does not assert independent reproduction. ### ReNeLLM ASR: 85.38. Result ID: 6996f9dd5698665ec446aa92. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Attack Type":"Manual","Evaluator":"GPT-4"}. This record does not assert independent reproduction. ### GPTFuzzer ASR: 66.73. Result ID: 6996f9dd5698665ec446aa8b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Attack Type":"Automated","Evaluator":"GPT-4"}. This record does not assert independent reproduction. ### TAP ASR: 61.63. Result ID: 6996f9dd5698665ec446aa89. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Attack Type":"Automated","Evaluator":"GPT-4"}. This record does not assert independent reproduction. ### Base64 ASR: 57.88. Result ID: 6996f9dd5698665ec446aa8a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Attack Type":"Automated","Evaluator":"GPT-4"}. This record does not assert independent reproduction. ### PAIR ASR: 47.83. Result ID: 6996f9dd5698665ec446aa88. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Attack Type":"Automated","Evaluator":"GPT-4"}. This record does not assert independent reproduction. ### AutoDAN ASR: 46.92. Result ID: 6996f9dd5698665ec446aa85. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Attack Type":"Automated","Evaluator":"GPT-4"}. This record does not assert independent reproduction. ### DeepInception ASR: 40.04. Result ID: 6996f9dd5698665ec446aa8c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Attack Type":"Manual","Evaluator":"GPT-4"}. This record does not assert independent reproduction. ### ArtPromopt ASR: 4.42. Result ID: 6996f9dd5698665ec446aa8e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Attack Type":"Manual","Evaluator":"GPT-4"}. This record does not assert independent reproduction. ### PromptAttack ASR: 1.92. Result ID: 6996f9dd5698665ec446aa8f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Attack Type":"Manual","Evaluator":"GPT-4"}. This record does not assert independent reproduction. ### GCG ASR: 1.15. Result ID: 6996f9dd5698665ec446aa84. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Attack Type":"Automated","Evaluator":"GPT-4"}. This record does not assert independent reproduction. ### MAC ASR: 0.58. Result ID: 6996f9dd5698665ec446aa86. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Attack Type":"Automated","Evaluator":"GPT-4"}. This record does not assert independent reproduction. ### COLD-Attack ASR: 0.19. Result ID: 6996f9dd5698665ec446aa87. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Attack Type":"Automated","Evaluator":"GPT-4"}. This record does not assert independent reproduction. ### SelfCipher ASR: 0. Result ID: 6996f9dd5698665ec446aa90. [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.