Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Clinical Diagnosis on MedDDx-Plus
Loading...
60.82
EM Score
C-MIG
0.6768
16.2909
31.905
47.5191
May 27, 2026
EM Score
KG Score
Average Score
Updated 6d ago
Evaluation Results
Method
Method
Links
EM Score
KG Score
Average Score
C-MIG
Backbone=Qwen2.5-7B
2026.05
60.82
65.12
62.97
AutoRefine-HardSearch
Backbone=Qwen2.5-7B
2026.05
58.62
63.51
61.06
AutoRefine-Embedding
Backbone=Qwen2.5-7B
2026.05
58.03
63.19
60.61
AutoRefine-HardDoc
Backbone=Qwen2.5-7B
2026.05
57.03
60.82
58.92
Search-R1
Backbone=Qwen2.5-7B
2026.05
55.43
58.82
57.12
AutoRefine
Backbone=Qwen2.5-7B
2026.05
53.94
56.49
55.22
IGPO
Backbone=Qwen2.5-7B
2026.05
52.84
56.21
54.53
AutoRefine-ICDTree
Backbone=Qwen2.5-7B
2026.05
47.16
60.92
54.04
Qwen2.5-7B
Backbone=Qwen2.5-7B
2026.05
2.99
5.8
4.39
Feedback
Search any
task
Search any
task