Compare AI models

Specifications
Parameters
16B1.5B/4B
Context window
4k8k
Benchmarks
MMLU
47.2%54.84%
GSM8K
62.2%54.89%
Overview
CompanyDeepSeekZ.ai
Release dateJan 11 2024Nov 29 2024
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

DeepSeek-MoE and GLM-Edge are evenly matched across the 2 benchmarks they both report (MMLU, GSM8K). DeepSeek-MoE shipped 323 days before GLM-Edge, so benchmark comparisons should account for the intervening progress.

DeepSeek-MoE has 16B parameters, while GLM-Edge has 1.5B/4B. Context windows are 4k (DeepSeek-MoE) vs 8k (GLM-Edge).

On MMLU, GLM-Edge leads at 54.84% vs DeepSeek-MoE at 47.2%. On GSM8K, DeepSeek-MoE leads at 62.2% vs GLM-Edge at 54.89%.