List your company
ResearchFormerly WizWand

Reasoning on Reasoning Tasks Average

68.6Average ScoreLlama-3-8B
33.55242.65151.7560.849Mar 17, 2025Apr 26, 2025Jun 5, 2025Jul 15, 2025Aug 24, 2025Oct 3, 2025Nov 13, 2025
Updated 8mo ago

Evaluation results

MethodLinks
Llama-3-8BBackbone=Llama-3-8B, #Bit=16.00, Zero-shot=true2025.0368.6
ClusCompBackbone=Llama-3-8B, #Bit=4.13, Zero-shot=true2025.0368.4
AWQBackbone=Llama-3-8B, #Bit=4.13, Zero-shot=true2025.0368.2
SliM-LLMBackbone=Llama-3-8B, #Bit=4.13, Zero-shot=true2025.0367.9
GPTQBackbone=Llama-3-8B, #Bit=4.13, Zero-shot=true2025.0367.3
ClusCompBackbone=Llama-3-8B, #Bit=2.87, Zero-shot=true2025.0364.9
SliM-LLMBackbone=Llama-3-8B, #Bit=3.13, Zero-shot=true2025.0364.5
AWQBackbone=Llama-3-8B, #Bit=3.13, Zero-shot=true2025.0364.4
RTNBackbone=Llama-3-8B, #Bit=4.13, Zero-shot=true2025.0363.9
QuIPBackbone=Llama-3-8B, #Bit=3.00, Zero-shot=true2025.0363.7
FP16Zero-shot=true2025.1162.8
ParoQuantType=linear, Zero-shot=true2025.1161.9
GPTQBackbone=Llama-3-8B, #Bit=3.13, Zero-shot=true2025.0361.7
QTIPType=vector, Zero-shot=true2025.1161
AWQType=linear, Zero-shot=true2025.1159.5
AWQBackbone=Llama-3-8B, #Bit=3.00, Zero-shot=true2025.0357.8
ClusCompBackbone=Llama-3-8B, #Bit=2.27, Zero-shot=true2025.0356.4
E-QATType=linear, Zero-shot=true2025.1155.6
ClusCompBackbone=Llama-3-8B, #Bit=2.01, Zero-shot=true2025.0353.6
ClusCompBackbone=Llama-3-8B, #Bit=2.14, Zero-shot=true2025.0351.7
GPTQBackbone=Llama-3-8B, #Bit=3.00, Zero-shot=true2025.0344.9
SliM-LLMBackbone=Llama-3-8B, #Bit=2.13, Zero-shot=true2025.0340.8
RTNBackbone=Llama-3-8B, #Bit=3.13, Zero-shot=true2025.0340.2
PB-LLMBackbone=Llama-3-8B, #Bit=2.13, Zero-shot=true2025.0338.8
QuIPBackbone=Llama-3-8B, #Bit=2.00, Zero-shot=true2025.0336.8
GPTQBackbone=Llama-3-8B, #Bit=2.13, Zero-shot=true2025.0336.2
RTNBackbone=Llama-3-8B, #Bit=2.13, Zero-shot=true2025.0336
RTNBackbone=Llama-3-8B, #Bit=3.00, Zero-shot=true2025.0335.6
AWQBackbone=Llama-3-8B, #Bit=2.00, Zero-shot=true2025.0335.5
RTNBackbone=Llama-3-8B, #Bit=2.00, Zero-shot=true2025.0335.3
AWQBackbone=Llama-3-8B, #Bit=2.13, Zero-shot=true2025.0334.9
GPTQBackbone=Llama-3-8B, #Bit=2.00, Zero-shot=true2025.0334.9