List your company

Mathematics Question Answering on GSM8K (test, zero-shot)

80.67Flexible EMOriginal
1.744422.234742.72563.2153Feb 9, 2026

Evaluation results

MethodLinks
OriginalModel=LLaMA3-70b2026.0280.6780.52
CIS (ours)Model=LLaMA3-70b, ρ̂=0.183, Theoretical Complexity (Comp*)=0.0117T2026.0276.1375.92
CIS* (ours)Model=LLaMA3-70b, ρ̂=0.179, Theoretical Complexity (Comp*)=0.0114T2026.0275.8475.56
CIS (ours)Model=LLaMA3-70b, ρ̂=0.082, Theoretical Complexity (Comp*)=0.0052T2026.0275.5375.26
CIS* (ours)Model=LLaMA3-70b, ρ̂=0.079, Theoretical Complexity (Comp*)=0.0050T2026.0275.4275.27
CIS* (ours)Model=LLaMA3-70b, ρ̂=0.061, Theoretical Complexity (Comp*)=0.0038T2026.0275.3675.04
CIS (ours)Model=LLaMA3-70b, ρ̂=0.064, Theoretical Complexity (Comp*)=0.0041T2026.0275.2875.11
Hshare-1Model=LLaMA3-70b, ρ̂=0.281, Theoretical Complexity (Comp*)=0.0180T2026.0275.1274.37
DSModel=LLaMA3-70b, Theoretical Complexity (Comp*)=0.0625T2026.0274.1573.92
Hshare-2Model=LLaMA3-70b, ρ̂=0.125, Theoretical Complexity (Comp*)=0.0080T2026.0274.1573.46
OriginalModel=Mistral-7b2026.0238.2138.13
CIS (ours)Model=Mistral-7b, ρ̂=0.194, Theoretical Complexity (Comp*)=0.0124T2026.0233.2533.02
CIS* (ours)Model=Mistral-7b, ρ̂=0.189, Theoretical Complexity (Comp*)=0.0121T2026.0232.9232.57
CIS (ours)Model=Mistral-7b, ρ̂=0.088, Theoretical Complexity (Comp*)=0.0056T2026.0232.8132.75
DSModel=Mistral-7b, Theoretical Complexity (Comp*)=0.0625T2026.0232.6232.27
CIS (ours)Model=Mistral-7b, ρ̂=0.065, Theoretical Complexity (Comp*)=0.0041T2026.0232.3332.01
CIS* (ours)Model=Mistral-7b, ρ̂=0.091, Theoretical Complexity (Comp*)=0.0058T2026.0232.1632.04
CIS* (ours)Model=Mistral-7b, ρ̂=0.068, Theoretical Complexity (Comp*)=0.0043T2026.0232.0431.75
Hshare-1Model=Mistral-7b, ρ̂=0.281, Theoretical Complexity (Comp*)=0.0180T2026.0231.9931.54
Hshare-2Model=Mistral-7b, ρ̂=0.125, Theoretical Complexity (Comp*)=0.0080T2026.0228.1826.84
OriginalModel=LLaMA2-7b-chat2026.0222.9722.97
CIS (ours)Model=LLaMA2-7b-chat, ρ̂=0.164, Theoretical Complexity (Comp*)=0.0104T2026.0218.4218.27
CIS* (ours)Model=LLaMA2-7b-chat, ρ̂=0.161, Theoretical Complexity (Comp*)=0.0103T2026.0218.1218.04
CIS (ours)Model=LLaMA2-7b-chat, ρ̂=0.087, Theoretical Complexity (Comp*)=0.0055T2026.0218.0417.82
Hshare-1Model=LLaMA2-7b-chat, ρ̂=0.281, Theoretical Complexity (Comp*)=0.0180T2026.0218.0317.03
CIS* (ours)Model=LLaMA2-7b-chat, ρ̂=0.084, Theoretical Complexity (Comp*)=0.0047T2026.0217.8917.82
CIS (ours)Model=LLaMA2-7b-chat, ρ̂=0.062, Theoretical Complexity (Comp*)=0.0039T2026.0217.5917.51
CIS* (ours)Model=LLaMA2-7b-chat, ρ̂=0.063, Theoretical Complexity (Comp*)=0.0040T2026.0217.3617.29
DSModel=LLaMA2-7b-chat, Theoretical Complexity (Comp*)=0.0625T2026.0217.1317.06
Hshare-2Model=LLaMA2-7b-chat, ρ̂=0.125, Theoretical Complexity (Comp*)=0.0080T2026.0215.2411.45
H2OModel=LLaMA2-7b-chat, Theoretical Complexity (Comp*)=O(1)2026.029.861.44
QuestModel=LLaMA2-7b-chat, Theoretical Complexity (Comp*)=0.1250T2026.024.784.62