Compare AI models

Specifications
Parameters
671B6B
Context window
128k8k
Benchmarks
MMLU
90.8%61.4%
Overview
CompanyDeepSeekZ.ai
Release dateJan 20 2025Oct 27 2023
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

DeepSeek R1 leads ChatGLM3-6B on 1 of the 1 benchmark they both report (MMLU). ChatGLM3-6B shipped 451 days before DeepSeek R1, so benchmark comparisons should account for the intervening progress.

DeepSeek R1 has 671B parameters, while ChatGLM3-6B has 6B. Context windows are 128k (DeepSeek R1) vs 8k (ChatGLM3-6B).

On MMLU, DeepSeek R1 leads at 90.8% vs ChatGLM3-6B at 61.4%.