Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Medical Diagnosis on MedAction 300 Hard
Loading...
82
Diag. Acc.
GPT-5.4
44.56
54.28
64
73.72
May 8, 2026
Diag. Acc.
Updated 23d ago
Evaluation Results
Method
Method
Links
Diag. Acc.
GPT-5.4
Model Source=Closed-So...
2026.05
82
II-Medical-8B SFT
Model Source=Open-Sour...
2026.05
69
OpenAI-o3-mini
Model Source=Closed-So...
2026.05
67
Baichuan-M3
Model Source=Open-Sour...
2026.05
66
Gemini 2.5 Flash-Lite
Model Source=Closed-So...
2026.05
63
MedGemma
Model Source=Open-Sour...
2026.05
63
Qwen-QwQ
Model Source=Open-Sour...
2026.05
58
Baichuan-M1
Model Source=Open-Sour...
2026.05
56
II-Medical-8B
Model Source=Open-Sour...
2026.05
46
Feedback
Search any
task
Search any
task