DxB: Diagnostic Prediction Benchmarking
Diagnostic prediction benchmarking tests GenAI in predicting possible disease causes from all available information, including symptoms and diagnostic tests.
Scoreboard
Dataset |
Diseases |
OpenAI ChatGPT-4 |
Google Gemini-1.5 |
Baidu Ernie-4 |
Date |
Neurology |
63 |
93.22% |
92.14% |
90.56% |
20240509 |
Oncology |
112 |
85.98% |
86.22% |
89.88% |
20240404 |