|
Med-Gemini
|
Capabilities of Gemini Models in Medicine
|
91.10
|
2024-04-29
|
|
|
GPT-4
|
Can Generalist Foundation Models Outcompete Speci…
|
90.20
|
2023-11-28
|
|
|
Med-PaLM 2
|
Towards Expert-Level Medical Question Answering w…
|
85.40
|
2023-05-16
|
|
|
Med-PaLM 2 (CoT + SC)
|
Towards Expert-Level Medical Question Answering w…
|
83.70
|
2023-05-16
|
|
|
Med-PaLM 2 (5-shot)
|
Towards Expert-Level Medical Question Answering w…
|
79.70
|
2023-05-16
|
|
|
MedMobile (3.8B)
|
MedMobile: A mobile-sized language model with exp…
|
75.70
|
2024-10-11
|
|
|
Meerkat-7B
|
Small Language Models Learn Enhanced Reasoning Sk…
|
74.30
|
2024-03-30
|
|
|
Meerkat-7B (Single)
|
Small Language Models Learn Enhanced Reasoning Sk…
|
70.60
|
2024-03-30
|
|
|
Meditron-70B (CoT + SC)
|
MEDITRON-70B: Scaling Medical Pretraining for Lar…
|
70.20
|
2023-11-27
|
|
|
Flan-PaLM (540 B)
|
Large Language Models Encode Clinical Knowledge
|
67.60
|
2022-12-26
|
|
|
LLAMA-2 (70B SC CoT)
|
MEDITRON-70B: Scaling Medical Pretraining for Lar…
|
61.50
|
2023-11-27
|
|
|
Shakti-LLM (2.5B)
|
SHAKTI: A 2.5 Billion Parameter Small Language Mo…
|
60.30
|
2024-10-15
|
|
|
Codex 5-shot CoT
|
Can large language models reason about medical qu…
|
60.20
|
2022-07-17
|
|
|
LLAMA-2 (70B)
|
MEDITRON-70B: Scaling Medical Pretraining for Lar…
|
59.20
|
2023-11-27
|
|
|
VOD (BioLinkBERT)
|
Variational Open-Domain Question Answering
|
55.00
|
2022-09-23
|
|
|
BioMedGPT-10B
|
BioMedGPT: Open Multimodal Generative Pre-trained…
|
50.40
|
2023-08-18
|
|
|
PubMedGPT (2.7 B)
|
Large Language Models Encode Clinical Knowledge
|
50.30
|
2022-12-26
|
|
|
DRAGON + BioLinkBERT
|
Deep Bidirectional Language-Knowledge Graph Pretr…
|
47.50
|
2022-10-17
|
|
|
BioLinkBERT (340 M)
|
Large Language Models Encode Clinical Knowledge
|
45.10
|
2022-12-26
|
|
|
GAL 120B (zero-shot)
|
Galactica: A Large Language Model for Science
|
44.40
|
2022-11-16
|
|
|
BioLinkBERT (base)
|
LinkBERT: Pretraining Language Models with Docume…
|
40.00
|
2022-03-29
|
|
|
GrapeQA: PEGA
|
GrapeQA: GRaph Augmentation and Pruning to Enhanc…
|
39.51
|
2023-03-22
|
|
|
BioBERT (large)
|
BioBERT: a pre-trained biomedical language repres…
|
36.70
|
2019-01-25
|
|
|
BioBERT (base)
|
BioBERT: a pre-trained biomedical language repres…
|
34.10
|
2019-01-25
|
|
|
GPT-Neo (2.7 B)
|
Large Language Models Encode Clinical Knowledge
|
33.30
|
2022-12-26
|
|
|
BLOOM (few-shot, k=5)
|
Galactica: A Large Language Model for Science
|
23.30
|
2022-11-16
|
|
|
OPT (few-shot, k=5)
|
Galactica: A Large Language Model for Science
|
22.80
|
2022-11-16
|
|