Compare AI models

Specifications
Parameters
671B6B
Context window
128k8k
API pricing
Cheapest input
$0.256DeepInfra—
Cheapest output
$0.712DeepInfra—
$103StreamLake—
Benchmarks
MMLU
88.5%61.4%
Overview
CompanyDeepSeekZ.ai
Release dateDec 26 2024Oct 27 2023
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

DeepSeek V3 leads ChatGLM3-6B on 1 of the 1 benchmark they both report (MMLU). ChatGLM3-6B shipped 426 days before DeepSeek V3, so benchmark comparisons should account for the intervening progress.

DeepSeek V3 has 671B parameters, while ChatGLM3-6B has 6B. Context windows are 128k (DeepSeek V3) vs 8k (ChatGLM3-6B).

On MMLU, DeepSeek V3 leads at 88.5% vs ChatGLM3-6B at 61.4%.