Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Phenotype Mining on CSC
Loading...
67.4
Precision
RAG (RD / HPO) (Llama 3.3 70B)
-2.696
15.502
33.7
51.898
Jul 14, 2025
Precision
Recall
F1 Score
Updated 20d ago
Evaluation Results
Method
Method
Links
Precision
Recall
F1 Score
RAG (RD / HPO) (Llama 3.3 70B)
FT=✗
2025.07
67.4
58
62.4
RDMA (Mistral 24B)
FT=✗
2025.07
64.4
67.1
65.7
BioBERT
FT=✓
2025.07
61.4
27.8
38.2
Dictionary Match
FT=✗
2025.07
60
21
31
PhenoGPT
FT=✓
2025.07
57
39
46
FastHPOCR
FT=✗
2025.07
52
45
48
i2b2 Clinical BERT
FT=✓
2025.07
48
60
53
BioClinicalBERT
FT=✓
2025.07
44.9
34.8
39.2
Zero-Shot (Llama 3.3 70B)
FT=✗
2025.07
0
0
0
Feedback
Search any
task
Search any
task