| Capabilities of Gemini Models in Medicine | | 91.1 | Med-Gemini | 2024-04-29 |
| Can Generalist Foundation Models Outcompete Special-Purpose Tuning? Case Study in Medicine | ✓ Link | 90.2 | GPT-4 | 2023-11-28 |
| Towards Expert-Level Medical Question Answering with Large Language Models | ✓ Link | 85.4 | Med-PaLM 2 | 2023-05-16 |
| Towards Expert-Level Medical Question Answering with Large Language Models | ✓ Link | 83.7 | Med-PaLM 2 (CoT + SC) | 2023-05-16 |
| Towards Expert-Level Medical Question Answering with Large Language Models | ✓ Link | 79.7 | Med-PaLM 2 (5-shot) | 2023-05-16 |
| MedMobile: A mobile-sized language model with expert-level clinical capabilities | ✓ Link | 75.7 | MedMobile (3.8B) | 2024-10-11 |
| Small Language Models Learn Enhanced Reasoning Skills from Medical Textbooks | | 74.3 | Meerkat-7B | 2024-03-30 |
| Small Language Models Learn Enhanced Reasoning Skills from Medical Textbooks | | 70.6 | Meerkat-7B (Single) | 2024-03-30 |
| MEDITRON-70B: Scaling Medical Pretraining for Large Language Models | ✓ Link | 70.2 | Meditron-70B (CoT + SC) | 2023-11-27 |
| Large Language Models Encode Clinical Knowledge | ✓ Link | 67.6 | Flan-PaLM (540 B) | 2022-12-26 |
| MEDITRON-70B: Scaling Medical Pretraining for Large Language Models | ✓ Link | 61.5 | LLAMA-2 (70B SC CoT) | 2023-11-27 |
| SHAKTI: A 2.5 Billion Parameter Small Language Model Optimized for Edge AI and Low-Resource Environments | | 60.3 | Shakti-LLM (2.5B) | 2024-10-15 |
| Can large language models reason about medical questions? | ✓ Link | 60.2 | Codex 5-shot CoT | 2022-07-17 |
| MEDITRON-70B: Scaling Medical Pretraining for Large Language Models | ✓ Link | 59.2 | LLAMA-2 (70B) | 2023-11-27 |
| Variational Open-Domain Question Answering | ✓ Link | 55.0 | VOD (BioLinkBERT) | 2022-09-23 |
| BioMedGPT: Open Multimodal Generative Pre-trained Transformer for BioMedicine | ✓ Link | 50.4 | BioMedGPT-10B | 2023-08-18 |
| Large Language Models Encode Clinical Knowledge | ✓ Link | 50.3 | PubMedGPT (2.7 B) | 2022-12-26 |
| Deep Bidirectional Language-Knowledge Graph Pretraining | ✓ Link | 47.5 | DRAGON + BioLinkBERT | 2022-10-17 |
| Large Language Models Encode Clinical Knowledge | ✓ Link | 45.1 | BioLinkBERT (340 M) | 2022-12-26 |
| Galactica: A Large Language Model for Science | ✓ Link | 44.4 | GAL 120B (zero-shot) | 2022-11-16 |
| LinkBERT: Pretraining Language Models with Document Links | ✓ Link | 40.0 | BioLinkBERT (base) | 2022-03-29 |
| GrapeQA: GRaph Augmentation and Pruning to Enhance Question-Answering | | 39.51 | GrapeQA: PEGA | 2023-03-22 |
| BioBERT: a pre-trained biomedical language representation model for biomedical text mining | ✓ Link | 36.7 | BioBERT (large) | 2019-01-25 |
| BioBERT: a pre-trained biomedical language representation model for biomedical text mining | ✓ Link | 34.1 | BioBERT (base) | 2019-01-25 |
| Large Language Models Encode Clinical Knowledge | ✓ Link | 33.3 | GPT-Neo (2.7 B) | 2022-12-26 |
| Galactica: A Large Language Model for Science | ✓ Link | 23.3 | BLOOM (few-shot, k=5) | 2022-11-16 |
| Galactica: A Large Language Model for Science | ✓ Link | 22.8 | OPT (few-shot, k=5) | 2022-11-16 |