Meditron-70B (CoT + SC)

Reported on 3 benchmarks across 1 task · 1 paper · 2 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Natural Language Processing3 results

Question AnsweringonPubMedQA
Accuracy· 2023-11-27
81.6
SOTA
MEDITRON-70B: Scaling Medical Pretraining for Large Language Models arXiv:2311.16079
Question AnsweringonMedMCQA
Dev Set (Acc-%)· 2023-11-27
66
SOTA
MEDITRON-70B: Scaling Medical Pretraining for Large Language Models arXiv:2311.16079
Question AnsweringonMedQA
Accuracy· 2023-11-27
70.2
best: 91.1 (Med-Gemini)
MEDITRON-70B: Scaling Medical Pretraining for Large Language Models arXiv:2311.16079