metadata
tags:
- medical
- mmlu
- medalpaca
- medmcqa
datasets:
- cais/mmlu
- medalpaca/medical_meadow_medqa
- medalpaca/medical_meadow_wikidoc
- openlifescienceai/medmcqa
pipeline_tag: text-generation
Evaluation results
| Dataset | GPT-3.5 | Tuned Llama 3 |
|---|---|---|
| MMLU Clinical Knowledge | 69.8 | 74.34 |
| MMLU College Biology | 72.2 | 72.92 |
| MMLU College Medicine | 61.3 | 61.85 |
| MMLU Medical Genetics | 70.0 | 76.0 |
| MMLU Professional Medicine | 70.2 | 72.43 |
| MMLU Anatomy | 56.3 | 61.48 |