Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Clinical Reasoning on HealthBench Professional (525 cases)
Loading...
62.72
Overall Score
MDIA v1.0.53
35.0352
42.2226
49.41
56.5974
May 23, 2026
Overall Score
Updated 8d ago
Evaluation Results
Method
Method
Links
Overall Score
MDIA v1.0.53
Description=Hydra Plat...
2026.05
62.72
MDIA v1.0.50
Description=Hydra Plat...
2026.05
61.66
ChatGPT for Clinicians
Note=best in OpenAI pa...
2026.05
59
MDIA v1.0.41
Description=Hydra Plat...
2026.05
57.75
GPT-5.4 base
Reference=OpenAI 2026
2026.05
48.1
Claude Opus 4.7
Reference=OpenAI 2026
2026.05
47
GPT-5
Reference=OpenAI 2026
2026.05
46.2
GPT-5.2
Reference=OpenAI 2026
2026.05
45.9
Gemini 3.1 Pro
Reference=OpenAI 2026
2026.05
43.8
Physician-written baseline
Reference=OpenAI 2026
2026.05
43.7
Grok 4.20
Reference=OpenAI 2026
2026.05
36.1
Feedback
Search any
task
Search any
task