Close-ended QA on MedQA
91.1AccuracyMed-Gemini-L 1.0
Evaluation results
| Method | Links | |
|---|---|---|
| Med-Gemini-L 1.0OOD=false2024.04 | 91.1 | |
| GPT-4 with MedPromptOOD=false2024.04 | 90.2 |
| Method | Links | |
|---|---|---|
| Med-Gemini-L 1.0OOD=false2024.04 | 91.1 | |
| GPT-4 with MedPromptOOD=false2024.04 | 90.2 |