Compare AI models

Specifications
Parameters
7B/67B1.5B/4B
Context window
4k8k
Benchmarks
MMLU
71.1%54.84%
GSM8K
84.1%54.89%
Overview
CompanyDeepSeekZ.ai
Release dateNov 29 2023Nov 29 2024
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

DeepSeek-LLM leads GLM-Edge on 2 of the 2 benchmarks they both report (MMLU, GSM8K). DeepSeek-LLM shipped 366 days before GLM-Edge, so benchmark comparisons should account for the intervening progress.

DeepSeek-LLM has 7B/67B parameters, while GLM-Edge has 1.5B/4B. Context windows are 4k (DeepSeek-LLM) vs 8k (GLM-Edge).

On MMLU, DeepSeek-LLM leads at 71.1% vs GLM-Edge at 54.84%. On GSM8K, DeepSeek-LLM leads at 84.1% vs GLM-Edge at 54.89%.