Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Math Programming on GSM8K Python
Loading...
78.5
Pass@100
Minerva
26.396
39.923
53.45
66.977
May 13, 2023
Pass@100
Updated 4d ago
Evaluation Results
Method
Method
Links
Pass@100
Minerva
Learning mode=Few-shot...
2023.05
78.5
CodeT5+
Learning mode=Finetuni...
2023.05
73.8
code-davinci
Learning mode=Few-shot...
2023.05
71
CodeT5+
Learning mode=Finetuni...
2023.05
70.5
LLaMA
Learning mode=Few-shot...
2023.05
69.7
Minerva
Learning mode=Few-shot...
2023.05
68.5
CodeT5
Learning mode=Finetuni...
2023.05
58.4
LLaMA
Learning mode=Few-shot...
2023.05
53.1
CodeGen-mono
Learning mode=Finetuni...
2023.05
47.8
GPT-Neo
Learning mode=Finetuni...
2023.05
41.4
CodeGen-mono
Learning mode=Finetuni...
2023.05
38.7
LLaMA
Learning mode=Few-shot...
2023.05
29.3
Minerva
Learning mode=Few-shot...
2023.05
28.4
Feedback
Search any
task
Search any
task