Compare AI models

Specifications
Parameters
7B—
Context window
2k—
Benchmarks
HumanEval
24.4%72%
MMLU
56.7%81.5%
GSM8K
51.6%87.6%
Overview
CompanyQwenZ.ai
Release dateAug 3 2023Jan 16 2024
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

GLM-4 leads Qwen-7B on 3 of the 3 benchmarks they both report (HumanEval, MMLU, GSM8K). Qwen-7B shipped 166 days before GLM-4, so benchmark comparisons should account for the intervening progress.

Qwen-7B is open weight, while GLM-4 is closed.

On HumanEval, GLM-4 leads at 72% vs Qwen-7B at 24.4%. On MMLU, GLM-4 leads at 81.5% vs Qwen-7B at 56.7%. On GSM8K, GLM-4 leads at 87.6% vs Qwen-7B at 51.6%.