List your company

Mathematical Reasoning on SimulEq out-of-domain (test)

77AccuracyMathCoder-L
1.28820.94440.660.256Oct 5, 2023

Evaluation results

MethodLinks
MathCoder-LBase=Llama-2, Size=70B2023.1077
MathCoder-CLBase=CodeLlama, Size=34B2023.1065.8
MathCoder-LBase=Llama-2, Size=13B2023.1062.3
MathCoder-CLBase=CodeLlama, Size=13B2023.1060.7
MathCoder-CLBase=CodeLlama, Size=7B2023.1049.6
MathCoder-LBase=Llama-2, Size=7B2023.1047.5
WizardMathBase=Llama-2, Size=70B2023.1037.9
WizardMathBase=Llama-2, Size=13B2023.1014.9
GalacticaSize=30B2023.1013.2
Llama-1 RFTBase=Llama-1, Size=34B2023.1012.8
WizardMathBase=Llama-2, Size=7B2023.1012.8
Llama-1 RFTBase=Llama-1, Size=7B2023.1011
Llama-1 RFTBase=Llama-1, Size=13B2023.1010.1
GalacticaSize=6.7B2023.104.2