List your company

Mathematical Reasoning on GSM8K (HS, FA)

38.24Hit Score (HS)Vaccine
-0.88489.272619.4329.5874Feb 28, 2026

Evaluation results

MethodLinks
VaccineBackbone=Gemma-2-9B2026.0238.2454.37
SFTBackbone=Gemma-2-9B2026.0232.0556.73
VaccineBackbone=Average2026.0226.6742.76
SFTBackbone=Llama-2-7B2026.0223.9410.9
VaccineBackbone=Llama-2-7B2026.0223.611.7
SFTBackbone=Average2026.0223.5144.1
BoosterBackbone=Gemma-2-9B2026.0222.1358.97
VaccineBackbone=Qwen-2-7B2026.0218.1762.2
SFTBackbone=Qwen-2-7B2026.0214.5464.66
LisaBackbone=Gemma-2-9B2026.0213.0254.97
BoosterBackbone=Average2026.0211.1347.96
BoosterBackbone=Llama-2-7B2026.029.0616.27
LisaBackbone=Average2026.027.642.7
LisaBackbone=Llama-2-7B2026.025.869.23
LisaBackbone=Qwen-2-7B2026.023.9163.9
BoosterBackbone=Qwen-2-7B2026.022.1968.63
AntibodyBackbone=Llama-2-7B2026.021.2415.07
AntibodyBackbone=Average2026.020.9246.6
AntibodyBackbone=Gemma-2-9B2026.020.9157.43
AntibodyBackbone=Qwen-2-7B2026.020.6267.3