# Jailbreak Attack on AdvBench GPT-4-turbo 1.0 (test) Source: [Jailbreak Attack on AdvBench GPT-4-turbo 1.0 (test)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:23:54.629Z Evaluation of model susceptibility to jailbreak attacks using the AdvBench dataset, specifically targeting the GPT-4-turbo 1.0 model on the test split, 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-turbo 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 | 9846 | Not recorded | 69535c9253fdd5c36173da26 | | Flipattack | 9404 | Not recorded | 69535c9253fdd5c36173da26 | | CodeChameleon | 9264 | Not recorded | 69535c9253fdd5c36173da26 | | DRA | 9192 | Not recorded | 69535c9253fdd5c36173da26 | | ReNeLLM | 8385 | Not recorded | 69535c9253fdd5c36173da26 | | GPTFuzzer | 5135 | Not recorded | 69535c9253fdd5c36173da26 | | TAP | 3681 | Not recorded | 69535c9253fdd5c36173da26 | | AutoDAN | 3192 | Not recorded | 69535c9253fdd5c36173da26 | | PAIR | 2396 | Not recorded | 69535c9253fdd5c36173da26 | | DeepInception | 583 | Not recorded | 69535c9253fdd5c36173da26 | | ArtPromopt | 192 | Not recorded | 69535c9253fdd5c36173da26 | | PromptAttack | 96 | Not recorded | 69535c9253fdd5c36173da26 | | GCG | 38 | Not recorded | 69535c9253fdd5c36173da26 | | MAC | 19 | Not recorded | 69535c9253fdd5c36173da26 | | COLD-Attack | 19 | Not recorded | 69535c9253fdd5c36173da26 | | Base64 | 19 | Not recorded | 69535c9253fdd5c36173da26 | | SelfCipher | 0 | Not recorded | 69535c9253fdd5c36173da26 | ### EquaCode ASR: 9846. Result ID: 6996f9dd5698665ec446aa72. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluator":"GPT-4"}. This record does not assert independent reproduction. ### Flipattack ASR: 9404. Result ID: 6996f9dd5698665ec446aa71. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Attack Type":"Manual","Evaluator":"GPT-4"}. This record does not assert independent reproduction. ### CodeChameleon ASR: 9264. Result ID: 6996f9dd5698665ec446aa6f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Attack Type":"Manual","Evaluator":"GPT-4"}. This record does not assert independent reproduction. ### DRA ASR: 9192. Result ID: 6996f9dd5698665ec446aa6b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Attack Type":"Manual","Evaluator":"GPT-4"}. This record does not assert independent reproduction. ### ReNeLLM ASR: 8385. Result ID: 6996f9dd5698665ec446aa70. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Attack Type":"Manual","Evaluator":"GPT-4"}. This record does not assert independent reproduction. ### GPTFuzzer ASR: 5135. Result ID: 6996f9dd5698665ec446aa69. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Attack Type":"Automated","Evaluator":"GPT-4"}. This record does not assert independent reproduction. ### TAP ASR: 3681. Result ID: 6996f9dd5698665ec446aa67. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Attack Type":"Automated","Evaluator":"GPT-4"}. This record does not assert independent reproduction. ### AutoDAN ASR: 3192. Result ID: 6996f9dd5698665ec446aa63. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Attack Type":"Automated","Evaluator":"GPT-4"}. This record does not assert independent reproduction. ### PAIR ASR: 2396. Result ID: 6996f9dd5698665ec446aa66. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Attack Type":"Automated","Evaluator":"GPT-4"}. This record does not assert independent reproduction. ### DeepInception ASR: 583. Result ID: 6996f9dd5698665ec446aa6a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Attack Type":"Manual","Evaluator":"GPT-4"}. This record does not assert independent reproduction. ### ArtPromopt ASR: 192. Result ID: 6996f9dd5698665ec446aa6c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Attack Type":"Manual","Evaluator":"GPT-4"}. This record does not assert independent reproduction. ### PromptAttack ASR: 96. Result ID: 6996f9dd5698665ec446aa6d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Attack Type":"Manual","Evaluator":"GPT-4"}. This record does not assert independent reproduction. ### GCG ASR: 38. Result ID: 6996f9dd5698665ec446aa62. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Attack Type":"Automated","Evaluator":"GPT-4"}. This record does not assert independent reproduction. ### MAC ASR: 19. Result ID: 6996f9dd5698665ec446aa64. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Attack Type":"Automated","Evaluator":"GPT-4"}. This record does not assert independent reproduction. ### COLD-Attack ASR: 19. Result ID: 6996f9dd5698665ec446aa65. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Attack Type":"Automated","Evaluator":"GPT-4"}. This record does not assert independent reproduction. ### Base64 ASR: 19. Result ID: 6996f9dd5698665ec446aa68. [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: 6996f9dd5698665ec446aa6e. [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.