Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Clinical Diagnosis on MedQA
Loading...
13.5
Exact Match (EM)
AutoRefine-Embedding
-0.54
3.105
6.75
10.395
May 27, 2026
Exact Match (EM)
Knowledge Graph Score (KG)
Average Score (Avg)
Updated 6d ago
Evaluation Results
Method
Method
Links
Exact Match (EM)
Knowledge Graph Score (KG)
Average Score (Avg)
AutoRefine-Embedding
Backbone=Qwen2.5-7B
2026.05
13.5
22.1
17.8
IGPO
Backbone=Qwen2.5-7B
2026.05
13
22.6
17.8
AutoRefine
Backbone=Qwen2.5-7B
2026.05
12
19.8
15.9
Search-R1
Backbone=Qwen2.5-7B
2026.05
11
20.8
15.9
AutoRefine-ICDTree
Backbone=Qwen2.5-7B
2026.05
11
23.7
17.35
C-MIG
Backbone=Qwen2.5-7B
2026.05
11
20.4
15.7
AutoRefine-HardSearch
Backbone=Qwen2.5-7B
2026.05
10.5
23.4
16.95
AutoRefine-HardDoc
Backbone=Qwen2.5-7B
2026.05
10.5
20.2
15.35
Qwen2.5-7B
Backbone=Qwen2.5-7B
2026.05
0
2.9
1.45
Feedback
Search any
task
Search any
task