Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Mathematical Reasoning on GSM8K (Accuracy Deg %, BERTScore)
Loading...
2.15
Accuracy Deg %
PCG
-1.0012
-0.1831
0.635
1.4531
Sep 3, 2025
Accuracy Deg %
BERTScore
Updated 9d ago
Evaluation Results
Method
Method
Links
Accuracy Deg %
BERTScore
PCG
Model=Deepseek-d-qwen
2025.09
2.15
0.43
PCG
Model=TinyLlama-chat
2025.09
2.08
0.51
PCG
Model=Gemma2-it
2025.09
1.73
0.5
PC*
Model=Gemma2-it
2025.09
0.56
0.61
PC*
Model=Deepseek-d-qwen
2025.09
0.45
0.77
PC*
Model=TinyLlama-chat
2025.09
0.22
0.64
PromptCOS
Model=Gemma2-it
2025.09
0.01
0.68
PromptCOS
Model=TinyLlama-chat
2025.09
-0.08
0.63
PromptCOS
Model=Deepseek-d-qwen
2025.09
-0.88
0.72
Feedback
Search any
task
Search any
task
