List your company

Mathematical Reasoning on GSM8K (test) (HS, FA)

71.5Hit Score (HS)Booster
2.96420.75738.5556.343May 7, 2026

Evaluation results

MethodLinks
BoosterBackbone=Llama3.1-8B2026.0571.576.2
SFTBackbone=Llama3.1-8B2026.0571.182.8
VaccineBackbone=Llama3.1-8B2026.0564.375.1
LisaBackbone=Llama3.1-8B2026.0540.472.2
DeepAlignBackbone=Llama3.1-8B2026.0520.788
SBRBackbone=Llama3.1-8B2026.055.682.6