# Jailbreak Attack on AdvBench GPT-4o-mini 1.0 (test) Source: [Jailbreak Attack on AdvBench GPT-4o-mini 1.0 (test)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:23:54.671Z Evaluation of model susceptibility to jailbreak attacks using the AdvBench GPT-4o-mini 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-mini 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 | | --- | --- | --- | --- | | EquaCode | 81.35 | Not recorded | 69535c9253fdd5c36173da26 | | DRA | 70 | Not recorded | 69535c9253fdd5c36173da26 | | Flipattack | 61.92 | Not recorded | 69535c9253fdd5c36173da26 | | ReNeLLM | 55.77 | Not recorded | 69535c9253fdd5c36173da26 | | CodeChameleon | 51.54 | Not recorded | 69535c9253fdd5c36173da26 | | GPTFuzzer | 41.35 | Not recorded | 69535c9253fdd5c36173da26 | | AutoDAN | 27.31 | Not recorded | 69535c9253fdd5c36173da26 | | DeepInception | 20.38 | Not recorded | 69535c9253fdd5c36173da26 | | COLD-Attack | 10.92 | Not recorded | 69535c9253fdd5c36173da26 | | TAP | 6.54 | Not recorded | 69535c9253fdd5c36173da26 | | PAIR | 3.46 | Not recorded | 69535c9253fdd5c36173da26 | | Base64 | 3.08 | Not recorded | 69535c9253fdd5c36173da26 | | GCG | 2.5 | Not recorded | 69535c9253fdd5c36173da26 | | MAC | 1.92 | Not recorded | 69535c9253fdd5c36173da26 | | ArtPromopt | 0.77 | Not recorded | 69535c9253fdd5c36173da26 | | PromptAttack | 0 | Not recorded | 69535c9253fdd5c36173da26 | | SelfCipher | 0 | Not recorded | 69535c9253fdd5c36173da26 | ### EquaCode ASR: 81.35. Result ID: 6996f9dd5698665ec446aaa5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluator":"GPT-4"}. This record does not assert independent reproduction. ### DRA ASR: 70. Result ID: 6996f9dd5698665ec446aa9e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Attack Type":"Manual","Evaluator":"GPT-4"}. This record does not assert independent reproduction. ### Flipattack ASR: 61.92. Result ID: 6996f9dd5698665ec446aaa4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Attack Type":"Manual","Evaluator":"GPT-4"}. This record does not assert independent reproduction. ### ReNeLLM ASR: 55.77. Result ID: 6996f9dd5698665ec446aaa3. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Attack Type":"Manual","Evaluator":"GPT-4"}. This record does not assert independent reproduction. ### CodeChameleon ASR: 51.54. Result ID: 6996f9dd5698665ec446aaa2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Attack Type":"Manual","Evaluator":"GPT-4"}. This record does not assert independent reproduction. ### GPTFuzzer ASR: 41.35. Result ID: 6996f9dd5698665ec446aa9c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Attack Type":"Automated","Evaluator":"GPT-4"}. This record does not assert independent reproduction. ### AutoDAN ASR: 27.31. Result ID: 6996f9dd5698665ec446aa96. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Attack Type":"Automated","Evaluator":"GPT-4"}. This record does not assert independent reproduction. ### DeepInception ASR: 20.38. Result ID: 6996f9dd5698665ec446aa9d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Attack Type":"Manual","Evaluator":"GPT-4"}. This record does not assert independent reproduction. ### COLD-Attack ASR: 10.92. Result ID: 6996f9dd5698665ec446aa98. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Attack Type":"Automated","Evaluator":"GPT-4"}. This record does not assert independent reproduction. ### TAP ASR: 6.54. Result ID: 6996f9dd5698665ec446aa9a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Attack Type":"Automated","Evaluator":"GPT-4"}. This record does not assert independent reproduction. ### PAIR ASR: 3.46. Result ID: 6996f9dd5698665ec446aa99. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Attack Type":"Automated","Evaluator":"GPT-4"}. This record does not assert independent reproduction. ### Base64 ASR: 3.08. Result ID: 6996f9dd5698665ec446aa9b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Attack Type":"Automated","Evaluator":"GPT-4"}. This record does not assert independent reproduction. ### GCG ASR: 2.5. Result ID: 6996f9dd5698665ec446aa95. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Attack Type":"Automated","Evaluator":"GPT-4"}. This record does not assert independent reproduction. ### MAC ASR: 1.92. Result ID: 6996f9dd5698665ec446aa97. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Attack Type":"Automated","Evaluator":"GPT-4"}. This record does not assert independent reproduction. ### ArtPromopt ASR: 0.77. Result ID: 6996f9dd5698665ec446aa9f. [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: 6996f9dd5698665ec446aaa0. [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: 6996f9dd5698665ec446aaa1. [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.