Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Span-level PHI extraction on SHIELD PHONE category 1.0 (test)
Loading...
98
Precision
GPT-OSS 120B
96.96
97.23
97.5
97.77
May 5, 2026
Precision
Recall
Updated 2mo ago
Evaluation Results
Method
Method
Links
Precision
Recall
GPT-OSS 120B
mode=zero-shot extraction
2026.05
98
92
Gemini Flash
mode=zero-shot extraction
2026.05
97
85
Flash Lite
mode=zero-shot extraction
2026.05
97
95
GPT-OSS 20B
mode=zero-shot extraction
2026.05
97
92
Feedback
Search any
task
Search any
task