# Text Anonymization on MedQA Source: [Text Anonymization on MedQA]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:58:59.041Z Evaluation of Text Anonymization performance on the MedQA dataset, measured by Privacy Score and Utility Score. 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 | Text Anonymization | | Dataset (including any stated split) | MedQA | | Metric | Privacy Score | | Unit | SCALAR | | Direction | Higher is better | | Results loaded | 16 of 16 | | 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 - [Privacy Score](): Higher is better; unit: SCALAR. - [Utility Score](): Higher is better; unit: PERCENT. ## Recorded results | Method | Privacy Score | Result date | Report paper | | --- | --- | --- | --- | | Optimized Prompt | 24.6 | Not recorded | 699e81ed6017c4460ffacdaf | | Qwen3-30B-A3B (Optimized) | 24.6 | Not recorded | 699e81ed6017c4460ffacdaf | | AF | 24.4 | Not recorded | 699e81ed6017c4460ffacdaf | | Optimized Prompt | 14.3 | Not recorded | 699e81ed6017c4460ffacdaf | | Seed Prompt | 12 | Not recorded | 699e81ed6017c4460ffacdaf | | AF | 11.7 | Not recorded | 699e81ed6017c4460ffacdaf | | Task-Specific Prompt | 10.7 | Not recorded | 699e81ed6017c4460ffacdaf | | Prompt | 10.7 | Not recorded | 699e81ed6017c4460ffacdaf | | AF | 9.39 | Not recorded | 699e81ed6017c4460ffacdaf | | Task-Specific Prompt | 8.25 | Not recorded | 699e81ed6017c4460ffacdaf | | Optimized Prompt | 8.06 | Not recorded | 699e81ed6017c4460ffacdaf | | Task-Specific Prompt | 7.33 | Not recorded | 699e81ed6017c4460ffacdaf | | AF | 6.53 | Not recorded | 699e81ed6017c4460ffacdaf | | OpenPII | 3.8 | Not recorded | 699e81ed6017c4460ffacdaf | | Seed Prompt | 3.52 | Not recorded | 699e81ed6017c4460ffacdaf | | Seed Prompt | 2.91 | Not recorded | 699e81ed6017c4460ffacdaf | ### Optimized Prompt Privacy Score: 24.6. Result ID: 699eb69e5698665ec4851f90. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone Model":"Qwen3-30B-A3B"}. This record does not assert independent reproduction. ### Qwen3-30B-A3B (Optimized) Privacy Score: 24.6. Result ID: 699eb69e5698665ec4851fa5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-30B-A3B","Status":"Optimized"}. This record does not assert independent reproduction. ### AF Privacy Score: 24.4. Result ID: 699eb69e5698665ec4851fa3. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"GPT-5"}. This record does not assert independent reproduction. ### Optimized Prompt Privacy Score: 14.3. Result ID: 699eb69e5698665ec4851f8c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone Model":"Gemma-3-27b-it"}. This record does not assert independent reproduction. ### Seed Prompt Privacy Score: 12. Result ID: 699eb69e5698665ec4851f8b. [Reporting paper]() Recorded evaluation configuration: {"Backbone Model":"Gemma-3-27b-it"}. This record does not assert independent reproduction. ### AF Privacy Score: 11.7. Result ID: 699eb69e5698665ec4851f89. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone Model":"Gemma-3-27b-it"}. This record does not assert independent reproduction. ### Task-Specific Prompt Privacy Score: 10.7. Result ID: 699eb69e5698665ec4851f8a. [Reporting paper]() Recorded evaluation configuration: {"Backbone Model":"Gemma-3-27b-it"}. This record does not assert independent reproduction. ### Prompt Privacy Score: 10.7. Result ID: 699eb69e5698665ec4851fa4. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"GPT-5"}. This record does not assert independent reproduction. ### AF Privacy Score: 9.39. Result ID: 699eb69e5698665ec4851f85. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone Model":"Mistral-Small-3.2-24B"}. This record does not assert independent reproduction. ### Task-Specific Prompt Privacy Score: 8.25. Result ID: 699eb69e5698665ec4851f8e. [Reporting paper]() Recorded evaluation configuration: {"Backbone Model":"Qwen3-30B-A3B"}. This record does not assert independent reproduction. ### Optimized Prompt Privacy Score: 8.06. Result ID: 699eb69e5698665ec4851f88. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone Model":"Mistral-Small-3.2-24B"}. This record does not assert independent reproduction. ### Task-Specific Prompt Privacy Score: 7.33. Result ID: 699eb69e5698665ec4851f86. [Reporting paper]() Recorded evaluation configuration: {"Backbone Model":"Mistral-Small-3.2-24B"}. This record does not assert independent reproduction. ### AF Privacy Score: 6.53. Result ID: 699eb69e5698665ec4851f8d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone Model":"Qwen3-30B-A3B"}. This record does not assert independent reproduction. ### OpenPII Privacy Score: 3.8. Result ID: 699eb69e5698665ec4851fa2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Seed Prompt Privacy Score: 3.52. Result ID: 699eb69e5698665ec4851f8f. [Reporting paper]() Recorded evaluation configuration: {"Backbone Model":"Qwen3-30B-A3B"}. This record does not assert independent reproduction. ### Seed Prompt Privacy Score: 2.91. Result ID: 699eb69e5698665ec4851f87. [Reporting paper]() Recorded evaluation configuration: {"Backbone Model":"Mistral-Small-3.2-24B"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.