Compare AI models

Specifications
Parameters
16B6B
Context window
32k8k
Benchmarks
HumanEval
57.3%58.5%
MATH
27.9%25.7%
MMLU
55.7%61.4%
GSM8K
72%72.3%
Overview
CompanyDeepSeekZ.ai
Release dateMay 16 2024Oct 27 2023
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

ChatGLM3-6B leads DeepSeek V2 Lite on 3 of the 4 benchmarks they both report (HumanEval, MATH, MMLU, GSM8K). ChatGLM3-6B shipped 202 days before DeepSeek V2 Lite, so benchmark comparisons should account for the intervening progress.

DeepSeek V2 Lite has 16B parameters, while ChatGLM3-6B has 6B. Context windows are 32k (DeepSeek V2 Lite) vs 8k (ChatGLM3-6B).

On HumanEval, ChatGLM3-6B leads at 58.5% vs DeepSeek V2 Lite at 57.3%. On MATH, DeepSeek V2 Lite leads at 27.9% vs ChatGLM3-6B at 25.7%. On MMLU, ChatGLM3-6B leads at 61.4% vs DeepSeek V2 Lite at 55.7%. On GSM8K, ChatGLM3-6B leads at 72.3% vs DeepSeek V2 Lite at 72%.