Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Mathematical Reasoning on GSM8K (test) (HS, FA)
Loading...
71.5
Hit Score (HS)
Booster
2.964
20.757
38.55
56.343
May 7, 2026
Hit Score (HS)
Failure Analysis Score (FA)
Updated 26d ago
Evaluation Results
Method
Method
Links
Hit Score (HS)
Failure Analysis Score (FA)
Booster
Backbone=Llama3.1-8B
2026.05
71.5
76.2
SFT
Backbone=Llama3.1-8B
2026.05
71.1
82.8
Vaccine
Backbone=Llama3.1-8B
2026.05
64.3
75.1
Lisa
Backbone=Llama3.1-8B
2026.05
40.4
72.2
DeepAlign
Backbone=Llama3.1-8B
2026.05
20.7
88
SBR
Backbone=Llama3.1-8B
2026.05
5.6
82.6
Feedback
Search any
task
Search any
task