# Morality Attack on Designed Morality Attacks 1.0 (test) Source: [Morality Attack on Designed Morality Attacks 1.0 (test)]() Collection index: [llms.txt]() Data updated: 2026-04-21T09:45:25.402Z Evaluation of model performance on morality attacks using the Designed Morality Attacks 1.0 test set, reporting RN, VN, FN, BN, and Average metrics. 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 | Morality Attack | | Dataset (including any stated split) | Designed Morality Attacks 1.0 (test) | | Metric | RN | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 15 of 15 | | 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 - [RN](): Higher is better; unit: PERCENT. - [VN](): Higher is better; unit: PERCENT. - [FN](): Higher is better; unit: PERCENT. - [BN](): Higher is better; unit: PERCENT. - [Average Performance](): Higher is better; unit: PERCENT. - [Caution Rate](): Lower is better; unit: PERCENT. ## Recorded results | Method | RN | Result date | Report paper | | --- | --- | --- | --- | | ShieldGemma-9B | 99.8 | Not recorded | 69e704c37d0172140ec7eef6 | | Llama-Guard-4 | 98.8 | Not recorded | 69e704c37d0172140ec7eef6 | | Claude-Sonnet-4 | 91.6 | Not recorded | 69e704c37d0172140ec7eef6 | | Gemini-2.5-pro | 91.6 | Not recorded | 69e704c37d0172140ec7eef6 | | GPT-5 | 90.4 | Not recorded | 69e704c37d0172140ec7eef6 | | Granite-Guardian-3.3-8B | 90.1 | Not recorded | 69e704c37d0172140ec7eef6 | | Qwen3-235B-A22B | 85.6 | Not recorded | 69e704c37d0172140ec7eef6 | | WildGuard | 84.2 | Not recorded | 69e704c37d0172140ec7eef6 | | DeepSeek-V3.1 | 83.6 | Not recorded | 69e704c37d0172140ec7eef6 | | Llama-4-Maverick | 80.4 | Not recorded | 69e704c37d0172140ec7eef6 | | GPT-4.1-mini | 79.2 | Not recorded | 69e704c37d0172140ec7eef6 | | Agent Permissive(CP) | 58.8 | Not recorded | 69e704c37d0172140ec7eef6 | | Llama-3.1-8B | 53.2 | Not recorded | 69e704c37d0172140ec7eef6 | | MDJudge | 49.3 | Not recorded | 69e704c37d0172140ec7eef6 | | Agent Defensive(CP) | 36.7 | Not recorded | 69e704c37d0172140ec7eef6 | ### ShieldGemma-9B RN: 99.8. Result ID: 69e7458f47f34ce924cde54a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Justification":"false"}. This record does not assert independent reproduction. ### Llama-Guard-4 RN: 98.8. Result ID: 69e7458f47f34ce924cde549. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Justification":"false"}. This record does not assert independent reproduction. ### Claude-Sonnet-4 RN: 91.6. Result ID: 69e7458f47f34ce924cde53b. [Reporting paper]() Recorded evaluation configuration: {"Justification":"true"}. This record does not assert independent reproduction. ### Gemini-2.5-pro RN: 91.6. Result ID: 69e7458f47f34ce924cde53c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Justification":"true"}. This record does not assert independent reproduction. ### GPT-5 RN: 90.4. Result ID: 69e7458f47f34ce924cde53a. [Reporting paper]() Recorded evaluation configuration: {"Justification":"true"}. This record does not assert independent reproduction. ### Granite-Guardian-3.3-8B RN: 90.1. Result ID: 69e7458f47f34ce924cde548. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Justification":"true"}. This record does not assert independent reproduction. ### Qwen3-235B-A22B RN: 85.6. Result ID: 69e7458f47f34ce924cde538. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Justification":"true"}. This record does not assert independent reproduction. ### WildGuard RN: 84.2. Result ID: 69e7458f47f34ce924cde547. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Justification":"false"}. This record does not assert independent reproduction. ### DeepSeek-V3.1 RN: 83.6. Result ID: 69e7458f47f34ce924cde539. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Justification":"true"}. This record does not assert independent reproduction. ### Llama-4-Maverick RN: 80.4. Result ID: 69e7458f47f34ce924cde537. [Reporting paper]() Recorded evaluation configuration: {"Justification":"true"}. This record does not assert independent reproduction. ### GPT-4.1-mini RN: 79.2. Result ID: 69e7458f47f34ce924cde536. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Justification":"true"}. This record does not assert independent reproduction. ### Agent Permissive(CP) RN: 58.8. Result ID: 69e7458f47f34ce924cde545. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Justification":"false"}. This record does not assert independent reproduction. ### Llama-3.1-8B RN: 53.2. Result ID: 69e7458f47f34ce924cde535. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Justification":"true"}. This record does not assert independent reproduction. ### MDJudge RN: 49.3. Result ID: 69e7458f47f34ce924cde546. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Justification":"true"}. This record does not assert independent reproduction. ### Agent Defensive(CP) RN: 36.7. Result ID: 69e7458f47f34ce924cde544. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Justification":"false"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.