Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Diagnostic utility on Zenodo CROSSRARE-BENCH
Loading...
63
Accuracy
Global RAG
0.6
16.8
33
49.2
Jun 11, 2026
Accuracy
F1 Score
Judge Score
Updated 1mo ago
Evaluation Results
Method
Method
Links
Accuracy
F1 Score
Judge Score
Global RAG
Host Model=MediPhi, Co...
2026.06
63
61
71
Dist. RAG
Host Model=MediPhi, Co...
2026.06
62
57
70
MedLatentDx
Host Model=MediPhi, Co...
2026.06
62
59
72
Struct. RAG
Host Model=MediPhi, Co...
2026.06
59
55
71
Single RAG
Host Model=MediPhi, Co...
2026.06
51
46
58
LatentMAS
Host Model=MediPhi, Co...
2026.06
47
46
71
Raw KV
Host Model=MediPhi, Co...
2026.06
43
49
71
TextMAS
Host Model=MediPhi, Co...
2026.06
31
36
49
Zero-shot
Host Model=MediPhi, Co...
2026.06
3
6
9
Feedback
Search any
task
Search any
task