Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Mathematical Reasoning on GSM8K (GSM8K Score)
Loading...
90
GSM8K Score
GRPO
77.52
80.76
84
87.24
May 26, 2025
GSM8K Score
Updated 1mo ago
Evaluation Results
Method
Method
Links
GSM8K Score
GRPO
Backbone=LLaMA-3.1-8B
2025.05
90
TI-DPO
Backbone=LLaMA-3.1-8B
2025.05
89
TPO
Backbone=LLaMA-3.1-8B
2025.05
88
CPO
Backbone=LLaMA-3.1-8B
2025.05
86.5
KTO
Backbone=LLaMA-3.1-8B
2025.05
86
DPO
Backbone=LLaMA-3.1-8B
2025.05
85
SFT
Backbone=LLaMA-3.1-8B
2025.05
84
TDPO
Backbone=LLaMA-3.1-8B
2025.05
83
IPO
Backbone=LLaMA-3.1-8B
2025.05
80
SIMPO
Backbone=LLaMA-3.1-8B
2025.05
78
Feedback
Search any
task
Search any
task
