PIIMB PII Masking - Avg F2 — leaderboard
PIIMB evaluates zero-shot PII masking over OpenPII, Gretel, Nemotron-PII, and Privy datasets, with F2, F1, precision, recall, and NER metrics.
Metric: Average F2 (%). Source: huggingface.co. 33 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | OpenMed privacy-filter-multilingual-v2 | 91.68 |
| 2 | OpenMed OpenMed-PII-SuperClinical-Large-434M-v1 | 88.52 |
| 3 | OpenMed privacy-filter-nemotron-v2 | 87.34 |
| 4 | OpenMed OpenMed-PII-SuperClinical-Small-44M-v1 | 86.79 |
| 5 | antoniogr7 pii-identifier-v0.1 | 86.23 |
| 6 | kalyan-ks ettin-68m-nemotron-pii | 84.11 |
| 7 | fastino gliner2-privacy-filter-PII-multi | 83.48 |
| 8 | kalyan-ks ettin-32m-nemotron-pii | 83.08 |
| 9 | nvidia gliner-PII | 82.98 |
| 10 | knowledgator gliner-pii-large-v1.0 | 81.26 |
Interactive version: theaggregate.ai/benchmark?slug=piimb-pii-masking-avg-f2 · How the rankings work · Data refreshed daily, snapshot 2026-07-22.