# Privacy Extraction on PersonaMem v2 (test) Source: [Privacy Extraction on PersonaMem v2 (test)]() Collection index: [llms.txt]() Data updated: 2026-05-12T12:24:57.887Z Evaluation of model performance on extracting privacy-sensitive information from the PersonaMem v2 test set, measured by F1, Precision, Recall, and inference time. 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 | Privacy Extraction | | Dataset (including any stated split) | PersonaMem v2 (test) | | Metric | F1 Score | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 18 of 18 | | 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 - [F1 Score](): Higher is better; unit: PERCENT. - [Precision](): Higher is better; unit: PERCENT. - [Recall](): Higher is better; unit: PERCENT. - [Inference Time (s)](): Lower is better; unit: TIME. ## Recorded results | Method | F1 Score | Result date | Report paper | | --- | --- | --- | --- | | MemPrivacy-4B-RL | 0.9448 | Not recorded | 6a02b46cdbc836b87d824b78 | | MemPrivacy-4B-SFT | 0.9443 | Not recorded | 6a02b46cdbc836b87d824b78 | | MemPrivacy-1.7B-RL | 0.9402 | Not recorded | 6a02b46cdbc836b87d824b78 | | MemPrivacy-0.6B-RL | 0.934 | Not recorded | 6a02b46cdbc836b87d824b78 | | MemPrivacy-1.7B-SFT | 0.9316 | Not recorded | 6a02b46cdbc836b87d824b78 | | DeepSeek-V3.2-Think | 0.9218 | Not recorded | 6a02b46cdbc836b87d824b78 | | MemPrivacy-0.6B-SFT | 0.9208 | Not recorded | 6a02b46cdbc836b87d824b78 | | GPT-5.2 | 0.8806 | Not recorded | 6a02b46cdbc836b87d824b78 | | GLM-5 | 0.8787 | Not recorded | 6a02b46cdbc836b87d824b78 | | Kimi-K2 | 0.8735 | Not recorded | 6a02b46cdbc836b87d824b78 | | LongCat-Flash-Chat | 0.8679 | Not recorded | 6a02b46cdbc836b87d824b78 | | DeepSeek-V3.2 | 0.8661 | Not recorded | 6a02b46cdbc836b87d824b78 | | Gemini-3.1-Pro | 0.8659 | Not recorded | 6a02b46cdbc836b87d824b78 | | Qwen3-4B | 0.8636 | Not recorded | 6a02b46cdbc836b87d824b78 | | DeepSeek-V3.1-Terminus | 0.8591 | Not recorded | 6a02b46cdbc836b87d824b78 | | OpenAI-Privacy-Filter | 0.8527 | Not recorded | 6a02b46cdbc836b87d824b78 | | Qwen3-0.6B | 0.0932 | Not recorded | 6a02b46cdbc836b87d824b78 | | Qwen3-1.7B | 0.0692 | Not recorded | 6a02b46cdbc836b87d824b78 | ### MemPrivacy-4B-RL F1 Score: 0.9448. Result ID: 6a031bfc47f34ce924e74177. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Category":"Privacy Models","Model Scale":"4B","Training Stage":"RL"}. This record does not assert independent reproduction. ### MemPrivacy-4B-SFT F1 Score: 0.9443. Result ID: 6a031bfc47f34ce924e74174. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Category":"Privacy Models","Model Scale":"4B","Training Stage":"SFT"}. This record does not assert independent reproduction. ### MemPrivacy-1.7B-RL F1 Score: 0.9402. Result ID: 6a031bfc47f34ce924e74176. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Category":"Privacy Models","Model Scale":"1.7B","Training Stage":"RL"}. This record does not assert independent reproduction. ### MemPrivacy-0.6B-RL F1 Score: 0.934. Result ID: 6a031bfc47f34ce924e74175. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Category":"Privacy Models","Model Scale":"0.6B","Training Stage":"RL"}. This record does not assert independent reproduction. ### MemPrivacy-1.7B-SFT F1 Score: 0.9316. Result ID: 6a031bfc47f34ce924e74173. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Category":"Privacy Models","Model Scale":"1.7B","Training Stage":"SFT"}. This record does not assert independent reproduction. ### DeepSeek-V3.2-Think F1 Score: 0.9218. Result ID: 6a031bfc47f34ce924e7416f. [Reporting paper]() Recorded evaluation configuration: {"Model Category":"General Models"}. This record does not assert independent reproduction. ### MemPrivacy-0.6B-SFT F1 Score: 0.9208. Result ID: 6a031bfc47f34ce924e74172. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Category":"Privacy Models","Model Scale":"0.6B","Training Stage":"SFT"}. This record does not assert independent reproduction. ### GPT-5.2 F1 Score: 0.8806. Result ID: 6a031bfc47f34ce924e7416c. [Reporting paper]() Recorded evaluation configuration: {"Model Category":"General Models"}. This record does not assert independent reproduction. ### GLM-5 F1 Score: 0.8787. Result ID: 6a031bfc47f34ce924e7416e. [Reporting paper]() Recorded evaluation configuration: {"Model Category":"General Models"}. This record does not assert independent reproduction. ### Kimi-K2 F1 Score: 0.8735. Result ID: 6a031bfc47f34ce924e7416d. [Reporting paper]() Recorded evaluation configuration: {"Model Category":"General Models"}. This record does not assert independent reproduction. ### LongCat-Flash-Chat F1 Score: 0.8679. Result ID: 6a031bfc47f34ce924e74169. [Reporting paper]() Recorded evaluation configuration: {"Model Category":"General Models"}. This record does not assert independent reproduction. ### DeepSeek-V3.2 F1 Score: 0.8661. Result ID: 6a031bfc47f34ce924e7416b. [Reporting paper]() Recorded evaluation configuration: {"Model Category":"General Models"}. This record does not assert independent reproduction. ### Gemini-3.1-Pro F1 Score: 0.8659. Result ID: 6a031bfc47f34ce924e74170. [Reporting paper]() Recorded evaluation configuration: {"Model Category":"General Models"}. This record does not assert independent reproduction. ### Qwen3-4B F1 Score: 0.8636. Result ID: 6a031bfc47f34ce924e74168. [Reporting paper]() Recorded evaluation configuration: {"Model Category":"General Models","Model Scale":"4B"}. This record does not assert independent reproduction. ### DeepSeek-V3.1-Terminus F1 Score: 0.8591. Result ID: 6a031bfc47f34ce924e7416a. [Reporting paper]() Recorded evaluation configuration: {"Model Category":"General Models"}. This record does not assert independent reproduction. ### OpenAI-Privacy-Filter F1 Score: 0.8527. Result ID: 6a031bfc47f34ce924e74171. [Reporting paper]() Recorded evaluation configuration: {"Model Category":"Privacy Models","Type":"Token-classification"}. This record does not assert independent reproduction. ### Qwen3-0.6B F1 Score: 0.0932. Result ID: 6a031bfc47f34ce924e74166. [Reporting paper]() Recorded evaluation configuration: {"Model Category":"General Models","Model Scale":"0.6B"}. This record does not assert independent reproduction. ### Qwen3-1.7B F1 Score: 0.0692. Result ID: 6a031bfc47f34ce924e74167. [Reporting paper]() Recorded evaluation configuration: {"Model Category":"General Models","Model Scale":"1.7B"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.