Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Medical Question Answering on HealthBench Professional
Loading...
62.7
Score
MDIA v1.0.53
42.94
48.07
53.2
58.33
May 23, 2026
Score
Average Response Length
Delta vs MDIA v1.0.40
Updated 8d ago
Evaluation Results
Method
Method
Links
Score
Average Response Length
Delta vs MDIA v1.0.40
MDIA v1.0.53
System configuration=l...
2026.05
62.7
2,789
4.2
MDIA v1.0.50
System configuration=H...
2026.05
61.7
4,383
3.2
ChatGPT for Clinicians
System configuration=O...
2026.05
59
-
0.5
MDIA v1.0.40
System configuration=m...
2026.05
58.5
-
-
MDIA v1.0.36
System configuration=l...
2026.05
52.2
-
6.3
GPT-5.4 base
System configuration=s...
2026.05
48.1
-
10.4
Physician-written baseline
Grader model=GPT-5.4 low
2026.05
43.7
-
14.9
Feedback
Search any
task
Search any
task