PII Detection on PII-Distract v1 (test)
94.8Entity F1 ScoreClaude3.5
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| Claude3.5Model Category=API-based Large Language Model2025.02 | 94.8 | 0.91 | 0.911 | |
| Llama3.1Model Category=Open-source Large Language Model2025.02 | 94.6 | 0.834 | 0.835 | |
| DeepSeekV3Model Category=API-based Large Language Model2025.02 | 94.5 | 0.658 | 0.658 | |
| Qwen2.5Model Category=Open-source Large Language Model2025.02 | 94.1 | 0.647 | 0.649 | |
| Llama3.1-SLMModel Category=Open-source Small Language Model2025.02 | 87.6 | 0.551 | 0.552 | |
| GPT4oModel Category=API-based Large Language Model2025.02 | 86.8 | 0.715 | 0.716 | |
| Qwen2.5-SLMModel Category=Open-source Small Language Model2025.02 | 81.5 | 0.454 | 0.456 | |
| BiLSTM-CRFModel Category=Traditional Model2025.02 | 78.7 | — | — |