Pii Masking
Frontier
Evaluates models' ability to identify and mask personally identifiable information in text
- Domain
- rl-env
- License
- unknown
- Published
- Oct 2025
Cite
Notes
Only stored in your browser.
Top score 0.0% by GPT-5 Nano - 5 models reporting (3 frontier)
Score history
3Top models
5
Related tools
1Implementations, trainers, datasets and scaffolds linked to this eval.
FAQ
- What is Pii Masking?
- Evaluates models' ability to identify and mask personally identifiable information in text
- What is the current top score on Pii Masking?
- The top reported score is 0.0% by GPT-5 Nano, across 5 models reporting (3 from frontier labs).
- How can a model improve its Pii Masking score?
- Tools linked to Pii Masking on Sophon include PII Masking RL Env (Community) - RL environments, datasets, and scaffolds that target this eval.
- What license is Pii Masking under?
- Pii Masking is available under unknown.