Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Pathology Report Generation on HistGen overlapping skin cases subset of 67
Loading...
0.85
Diagnostic Consistency (mean/3)
Baseline
0.6004
0.6652
0.73
0.7948
May 29, 2026
Diagnostic Consistency (mean/3)
Key Findings Coverage (mean/2)
Composite Score (mean/5)
Exact/Equivalent Diagnosis Count
Partial/Full Consistent Diagnosis Count
Most Key Findings Coverage Count
Pairwise Composite Wins Count
Pairwise Ties Count
Updated 2d ago
Evaluation Results
Method
Method
Links
Diagnostic Consistency (mean/3)
Key Findings Coverage (mean/2)
Composite Score (mean/5)
Exact/Equivalent Diagnosis Count
Partial/Full Consistent Diagnosis Count
Most Key Findings Coverage Count
Pairwise Composite Wins Count
Pairwise Ties Count
Baseline
Stage=1
2026.05
0.85
1.64
2.49
12
18
47
20
39
HistoGPT
2026.05
0.61
1.63
2.24
5
12
44
8
39
Feedback
Search any
task
Search any
task