# Probed Adversary Evaluation on 792 Privacy Evaluation Scenarios final benchmark 1.0 Source: [Probed Adversary Evaluation on 792 Privacy Evaluation Scenarios final benchmark 1.0]() Collection index: [llms.txt]() Data updated: 2026-04-09T23:27:58.890Z Evaluation of model performance using the 792 Privacy Evaluation Scenarios final benchmark 1.0 dataset, focusing on Probed Adversary Evaluation results. 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 | Probed Adversary Evaluation | | Dataset (including any stated split) | 792 Privacy Evaluation Scenarios final benchmark 1.0 | | Metric | HLSp Score | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 28 of 28 | | 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 - [HLSp Score](): Higher is better; unit: PERCENT. - [Utility](): Higher is better; unit: PERCENT. - [IS-ADp Score](): Higher is better; unit: PERCENT. ## Recorded results | Method | HLSp Score | Result date | Report paper | | --- | --- | --- | --- | | Kimi K2.5 | 41 | Not recorded | 69d732727d0172140ec76a2d | | Gemini 3.1 Pro | 40 | Not recorded | 69d732727d0172140ec76a2d | | MiniMax M2.1 | 32 | Not recorded | 69d732727d0172140ec76a2d | | Kimi K2.5 | 31 | Not recorded | 69d732727d0172140ec76a2d | | GLM-5 | 30 | Not recorded | 69d732727d0172140ec76a2d | | GPT-5.4 | 30 | Not recorded | 69d732727d0172140ec76a2d | | MiniMax M2.1 | 30 | Not recorded | 69d732727d0172140ec76a2d | | Gemini 3.1 Pro | 29 | Not recorded | 69d732727d0172140ec76a2d | | GPT-5.4 | 27 | Not recorded | 69d732727d0172140ec76a2d | | MiniMax M2.1 | 27 | Not recorded | 69d732727d0172140ec76a2d | | GLM-5 | 25 | Not recorded | 69d732727d0172140ec76a2d | | GPT-5.4 | 25 | Not recorded | 69d732727d0172140ec76a2d | | Kimi K2.5 | 24 | Not recorded | 69d732727d0172140ec76a2d | | GLM-5 | 23 | Not recorded | 69d732727d0172140ec76a2d | | Gemini 3.1 Pro | 22 | Not recorded | 69d732727d0172140ec76a2d | | MiniMax M2.1 | 22 | Not recorded | 69d732727d0172140ec76a2d | | GPT-5.4 | 21 | Not recorded | 69d732727d0172140ec76a2d | | GLM-5 | 18 | Not recorded | 69d732727d0172140ec76a2d | | Qwen3-8B | 18 | Not recorded | 69d732727d0172140ec76a2d | | Kimi K2.5 | 17 | Not recorded | 69d732727d0172140ec76a2d | | Gemini 3.1 Pro | 16 | Not recorded | 69d732727d0172140ec76a2d | | MiniMax M2.5 | 15 | Not recorded | 69d732727d0172140ec76a2d | | Qwen3-8B | 15 | Not recorded | 69d732727d0172140ec76a2d | | Qwen3-8B | 14 | Not recorded | 69d732727d0172140ec76a2d | | MiniMax M2.5 | 13 | Not recorded | 69d732727d0172140ec76a2d | | MiniMax M2.5 | 13 | Not recorded | 69d732727d0172140ec76a2d | | Qwen3-8B | 12 | Not recorded | 69d732727d0172140ec76a2d | | MiniMax M2.5 | 9 | Not recorded | 69d732727d0172140ec76a2d | ### Kimi K2.5 HLSp Score: 41. Result ID: 69d833e347f34ce924bfe356. [Reporting paper]() Recorded evaluation configuration: {"Strategy":"None"}. This record does not assert independent reproduction. ### Gemini 3.1 Pro HLSp Score: 40. Result ID: 69d833e347f34ce924bfe34a. [Reporting paper]() Recorded evaluation configuration: {"Strategy":"None"}. This record does not assert independent reproduction. ### MiniMax M2.1 HLSp Score: 32. Result ID: 69d833e347f34ce924bfe35a. [Reporting paper]() Recorded evaluation configuration: {"Strategy":"None"}. This record does not assert independent reproduction. ### Kimi K2.5 HLSp Score: 31. Result ID: 69d833e347f34ce924bfe358. [Reporting paper]() Recorded evaluation configuration: {"Strategy":"Generalization"}. This record does not assert independent reproduction. ### GLM-5 HLSp Score: 30. Result ID: 69d833e347f34ce924bfe34e. [Reporting paper]() Recorded evaluation configuration: {"Strategy":"None"}. This record does not assert independent reproduction. ### GPT-5.4 HLSp Score: 30. Result ID: 69d833e347f34ce924bfe352. [Reporting paper]() Recorded evaluation configuration: {"Strategy":"None"}. This record does not assert independent reproduction. ### MiniMax M2.1 HLSp Score: 30. Result ID: 69d833e347f34ce924bfe35d. [Reporting paper]() Recorded evaluation configuration: {"Strategy":"Pseudonymization"}. This record does not assert independent reproduction. ### Gemini 3.1 Pro HLSp Score: 29. Result ID: 69d833e347f34ce924bfe34c. [Reporting paper]() Recorded evaluation configuration: {"Strategy":"Generalization"}. This record does not assert independent reproduction. ### GPT-5.4 HLSp Score: 27. Result ID: 69d833e347f34ce924bfe354. [Reporting paper]() Recorded evaluation configuration: {"Strategy":"Generalization"}. This record does not assert independent reproduction. ### MiniMax M2.1 HLSp Score: 27. Result ID: 69d833e347f34ce924bfe35c. [Reporting paper]() Recorded evaluation configuration: {"Strategy":"Generalization"}. This record does not assert independent reproduction. ### GLM-5 HLSp Score: 25. Result ID: 69d833e347f34ce924bfe350. [Reporting paper]() Recorded evaluation configuration: {"Strategy":"Generalization"}. This record does not assert independent reproduction. ### GPT-5.4 HLSp Score: 25. Result ID: 69d833e347f34ce924bfe355. [Reporting paper]() Recorded evaluation configuration: {"Strategy":"Pseudonymization"}. This record does not assert independent reproduction. ### Kimi K2.5 HLSp Score: 24. Result ID: 69d833e347f34ce924bfe359. [Reporting paper]() Recorded evaluation configuration: {"Strategy":"Pseudonymization"}. This record does not assert independent reproduction. ### GLM-5 HLSp Score: 23. Result ID: 69d833e347f34ce924bfe351. [Reporting paper]() Recorded evaluation configuration: {"Strategy":"Pseudonymization"}. This record does not assert independent reproduction. ### Gemini 3.1 Pro HLSp Score: 22. Result ID: 69d833e347f34ce924bfe34d. [Reporting paper]() Recorded evaluation configuration: {"Strategy":"Pseudonymization"}. This record does not assert independent reproduction. ### MiniMax M2.1 HLSp Score: 22. Result ID: 69d833e347f34ce924bfe35b. [Reporting paper]() Recorded evaluation configuration: {"Strategy":"Suppression"}. This record does not assert independent reproduction. ### GPT-5.4 HLSp Score: 21. Result ID: 69d833e347f34ce924bfe353. [Reporting paper]() Recorded evaluation configuration: {"Strategy":"Suppression"}. This record does not assert independent reproduction. ### GLM-5 HLSp Score: 18. Result ID: 69d833e347f34ce924bfe34f. [Reporting paper]() Recorded evaluation configuration: {"Strategy":"Suppression"}. This record does not assert independent reproduction. ### Qwen3-8B HLSp Score: 18. Result ID: 69d833e347f34ce924bfe362. [Reporting paper]() Recorded evaluation configuration: {"Strategy":"None"}. This record does not assert independent reproduction. ### Kimi K2.5 HLSp Score: 17. Result ID: 69d833e347f34ce924bfe357. [Reporting paper]() Recorded evaluation configuration: {"Strategy":"Suppression"}. This record does not assert independent reproduction. ### Gemini 3.1 Pro HLSp Score: 16. Result ID: 69d833e347f34ce924bfe34b. [Reporting paper]() Recorded evaluation configuration: {"Strategy":"Suppression"}. This record does not assert independent reproduction. ### MiniMax M2.5 HLSp Score: 15. Result ID: 69d833e347f34ce924bfe35e. [Reporting paper]() Recorded evaluation configuration: {"Strategy":"None"}. This record does not assert independent reproduction. ### Qwen3-8B HLSp Score: 15. Result ID: 69d833e347f34ce924bfe365. [Reporting paper]() Recorded evaluation configuration: {"Strategy":"Pseudonymization"}. This record does not assert independent reproduction. ### Qwen3-8B HLSp Score: 14. Result ID: 69d833e347f34ce924bfe364. [Reporting paper]() Recorded evaluation configuration: {"Strategy":"Generalization"}. This record does not assert independent reproduction. ### MiniMax M2.5 HLSp Score: 13. Result ID: 69d833e347f34ce924bfe360. [Reporting paper]() Recorded evaluation configuration: {"Strategy":"Generalization"}. This record does not assert independent reproduction. ### MiniMax M2.5 HLSp Score: 13. Result ID: 69d833e347f34ce924bfe361. [Reporting paper]() Recorded evaluation configuration: {"Strategy":"Pseudonymization"}. This record does not assert independent reproduction. ### Qwen3-8B HLSp Score: 12. Result ID: 69d833e347f34ce924bfe363. [Reporting paper]() Recorded evaluation configuration: {"Strategy":"Suppression"}. This record does not assert independent reproduction. ### MiniMax M2.5 HLSp Score: 9. Result ID: 69d833e347f34ce924bfe35f. [Reporting paper]() Recorded evaluation configuration: {"Strategy":"Suppression"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.