{"task":"Multiple Choice Question Answering (MCQA)","dataset":"MMLU (Anatomy)","metric_names":["Accuracy"],"rows":[{"id":25094,"task":"Multiple Choice Question Answering (MCQA)","parent_task":"Question Answering","dataset":"MMLU (Anatomy)","model_name":"Med-PaLM 2 (ER)","metrics":{"Accuracy":"84.4"},"paper_url":"https://arxiv.org/abs/2305.09617v1","paper_title":"Towards Expert-Level Medical Question Answering with Large Language Models","paper_date":"2023-05-16","code_links":[{"title":"m42-health/med42","url":"https://github.com/m42-health/med42"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":25095,"task":"Multiple Choice Question Answering (MCQA)","parent_task":"Question Answering","dataset":"MMLU (Anatomy)","model_name":"Med-PaLM 2 (CoT + SC)","metrics":{"Accuracy":"80.0"},"paper_url":"https://arxiv.org/abs/2305.09617v1","paper_title":"Towards Expert-Level Medical Question Answering with Large Language Models","paper_date":"2023-05-16","code_links":[{"title":"m42-health/med42","url":"https://github.com/m42-health/med42"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":25096,"task":"Multiple Choice Question Answering (MCQA)","parent_task":"Question Answering","dataset":"MMLU (Anatomy)","model_name":"Med-PaLM 2 (5-shot)","metrics":{"Accuracy":"77.8"},"paper_url":"https://arxiv.org/abs/2305.09617v1","paper_title":"Towards Expert-Level Medical Question Answering with Large Language Models","paper_date":"2023-05-16","code_links":[{"title":"m42-health/med42","url":"https://github.com/m42-health/med42"}],"metrics_order":"[\"Accuracy\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]}]}