paper-with-me

Multiple Choice Question Answering (MCQA) 벤치마크

Multiple Choice Question Answering (MCQA) on MMLU (Anatomy)

3개 결과 · ⬇ CSV · JSON

Accuracy

77.8 79.45 81.1 82.75 84.4 2023-05 2026-09 Med-PaLM 2 (ER) — 84.4 (2023-05-16) Med-PaLM 2 (CoT + SC) — 80.0 (2023-05-16) Med-PaLM 2 (5-shot) — 77.8 (2023-05-16) Med-PaLM 2 (ER) — 84.4 (2023-05-16)
RankModel Accuracy PaperCodeYear
1 Med-PaLM 2 (ER) 84.4 Towards Expert-Level Medical Question Answering with Large Language Models m42-health/med42 2023
2 Med-PaLM 2 (CoT + SC) 80.0 Towards Expert-Level Medical Question Answering with Large Language Models m42-health/med42 2023
3 Med-PaLM 2 (5-shot) 77.8 Towards Expert-Level Medical Question Answering with Large Language Models m42-health/med42 2023
1–3 / 3 페이지당 10 20 50 100