Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Biomedical Question Answering on PubMedQA PQA-L In-Domain (test)
Loading...
78
Accuracy
Human (expert)
0.728
20.789
40.85
60.911
Aug 18, 2023
Accuracy
Updated 4d ago
Evaluation Results
Method
Method
Links
Accuracy
Human (expert)
Setting=Manual
2023.08
78
BioMedGPT-10B
Setting=Fine-tuning
2023.08
76.1
Llama2-Chat
Setting=Fine-tuning
2023.08
75.5
Llama
Setting=Fine-tuning
2023.08
73.4
InstructGPT
Setting=Zero-shot
2023.08
73.2
PMC-Llama
Setting=Fine-tuning
2023.08
69.5
ChatGPT
Setting=Zero-shot
2023.08
63.9
Human (pass)
Setting=Manual
2023.08
60
Llama2-Chat
Setting=Zero-shot
2023.08
21.9
Llama
Setting=Zero-shot
2023.08
5.2
Llama2
Setting=Zero-shot
2023.08
3.7
Feedback
Search any
task
Search any
task