Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Medical Question Answering on Multilingual Medical Evaluation Arabic (test)
Loading...
5.1
ECE
BioMedGPT-LM-7B
4.628
7.814
11
14.186
Feb 15, 2024
ECE
Delta ECE (vs Mistral 7B Instruct)
Updated 4d ago
Evaluation Results
Method
Method
Links
ECE
Delta ECE (vs Mistral 7B Instruct)
BioMedGPT-LM-7B
Parameters=7B
2024.02
5.1
11.5
MedAlpaca 7B
Parameters=7B
2024.02
7.8
8.8
MediTron-7B
Parameters=7B
2024.02
10.5
6.1
BioMistral 7B
Parameters=7B
2024.02
13.9
2.7
BioMistral 7B SLERP
Merging Strategy=SLERP
2024.02
14.8
1.8
PMC-LLAMA 7B
Parameters=7B
2024.02
15.1
1.5
BioMistral 7B TIES
Merging Strategy=TIES
2024.02
15.7
0.9
Mistral 7B Instruct
Parameters=7B
2024.02
16.6
-
BioMistral 7B DARE
Merging Strategy=DARE
2024.02
16.9
-0.3
Feedback
Search any
task
Search any
task