Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Scan-level report labelling on Cauda Equina Compression (test)
Loading...
100
Balanced Accuracy
Direct Query
87.728
90.914
94.1
97.286
Oct 22, 2024
Balanced Accuracy
EER
AU ROC
F1 Score
Updated 3mo ago
Evaluation Results
Method
Method
Links
Balanced Accuracy
EER
AU ROC
F1 Score
Direct Query
Query Model=GPT-4
2024.10
100
-
-
100
Summary-Query
Summary Model=Llama3,...
2024.10
100
0
1
100
Summary-Query
Summary Model=Zephyr,...
2024.10
97.1
0.039
0.998
97
Direct Query
Query Model=Llama3
2024.10
94.1
0.026
0.998
93.8
Direct Query
Query Model=Zephyr
2024.10
91.2
0.013
0.972
90.3
Summary-Query
Summary Model=Z-SFT, Q...
2024.10
88.2
0.013
0.988
86.7
Feedback
Search any
task
Search any
task