Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Mathematical Reasoning on GSM8K (HS & FA)
Loading...
78.4
HS
Non-Aligned
50.32
57.61
64.9
72.19
Feb 2, 2024
HS
FA
Updated 4d ago
Evaluation Results
Method
Method
Links
HS
FA
Non-Aligned
Backbone=Llama2-7B
2024.02
78.4
27.8
SFT
Backbone=Llama2-7B
2024.02
68.4
23.4
Vaccine
Backbone=Llama2-7B
2024.02
65
22.4
EWC
Backbone=Llama2-7B
2024.02
51.4
5.8
Feedback
Search any
task
Search any
task