Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Scan-level report labelling on Cancer (test)
Loading...
100
Balanced Accuracy
Direct Query
97.712
98.306
98.9
99.494
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=Z-SFT, Q...
2024.10
99.4
0
1
99.3
Direct Query
Query Model=Zephyr
2024.10
99.3
0
1
99.2
Summary-Query
Summary Model=Zephyr,...
2024.10
98.5
0
1
98.5
Direct Query
Query Model=Llama3
2024.10
97.8
0.014
0.999
97.7
Feedback
Search any
task
Search any
task