Compare AI models

Specifications
Parameters
14.3B6B
Context window
32k8k
Benchmarks
HumanEval
34.2%58.5%
MMLU
62.5%61.4%
GSM8K
61.5%72.3%
Overview
CompanyQwenZ.ai
Release dateMar 28 2024Oct 27 2023
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

ChatGLM3-6B leads Qwen1.5-MoE on 2 of the 3 benchmarks they both report (HumanEval, MMLU, GSM8K). ChatGLM3-6B shipped 153 days before Qwen1.5-MoE, so benchmark comparisons should account for the intervening progress.

Qwen1.5-MoE has 14.3B parameters, while ChatGLM3-6B has 6B. Context windows are 32k (Qwen1.5-MoE) vs 8k (ChatGLM3-6B).

On HumanEval, ChatGLM3-6B leads at 58.5% vs Qwen1.5-MoE at 34.2%. On MMLU, Qwen1.5-MoE leads at 62.5% vs ChatGLM3-6B at 61.4%. On GSM8K, ChatGLM3-6B leads at 72.3% vs Qwen1.5-MoE at 61.5%.