Share your thoughts, 1 month free Claude Pro on usSee more

Language Modeling on LAMBADA standard (LS) (Accuracy)

65.57Accuracy (LAMBADA)

Baseline

Updated 9d ago

Evaluation Results

Method	Links
Baseline 2026.04		65.57
Baseline 2026.04		63.26
Baseline 2026.04		61.36
MoBiE 2026.04		45.55
GPTQ 2026.04		41.7
NoWag 2026.04		39.31
MoBiE 2026.04		29.85
MoBiE 2026.04		28.62
ARB-LLM 2026.04		27.75
GPTQ 2026.04		25.88
GPTQ 2026.04		25.88
ARB-LLM 2026.04		24.98
NoWag 2026.04		21.77
ARB-LLM 2026.04		20.05
NoWag 2026.04		19.31
BiLLM 2026.04		19.1
BiLLM 2026.04		14.56
BiLLM 2026.04		14.13
MoEQuant 2026.04		10.15
MoEQuant 2026.04		10.11
MoEQuant 2026.04		8.2
AWQ 2026.04		1.22
AWQ 2026.04		0.55
AWQ 2026.04		0.26
AWQ 2026.04		0
GPTQ 2026.04		0
AWQ 2026.04		0
GPTQ 2026.04		0
AWQ 2026.04		0
GPTQ 2026.04		0