Compare AI models

Specifications
Parameters
16B/236B1.5B/4B
Context window
128k8k
Benchmarks
MMLU
79.2%54.84%
GSM8K
94.9%54.89%
Overview
CompanyDeepSeekZ.ai
Release dateJun 14 2024Nov 29 2024
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

DeepSeek Coder V2 leads GLM-Edge on 2 of the 2 benchmarks they both report (MMLU, GSM8K). DeepSeek Coder V2 shipped 168 days before GLM-Edge, so benchmark comparisons should account for the intervening progress.

DeepSeek Coder V2 has 16B/236B parameters, while GLM-Edge has 1.5B/4B. Context windows are 128k (DeepSeek Coder V2) vs 8k (GLM-Edge).

On MMLU, DeepSeek Coder V2 leads at 79.2% vs GLM-Edge at 54.84%. On GSM8K, DeepSeek Coder V2 leads at 94.9% vs GLM-Edge at 54.89%.