Compare AI models

Specifications
Parameters
14.3B—
Context window
32k—
Benchmarks
HumanEval
34.2%72%
MMLU
62.5%81.5%
GSM8K
61.5%87.6%
Overview
CompanyQwenZ.ai
Release dateMar 28 2024Jan 16 2024
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

GLM-4 leads Qwen1.5-MoE on 3 of the 3 benchmarks they both report (HumanEval, MMLU, GSM8K). GLM-4 shipped 72 days before Qwen1.5-MoE, so benchmark comparisons should account for the intervening progress.

Qwen1.5-MoE is open weight, while GLM-4 is closed.

On HumanEval, GLM-4 leads at 72% vs Qwen1.5-MoE at 34.2%. On MMLU, GLM-4 leads at 81.5% vs Qwen1.5-MoE at 62.5%. On GSM8K, GLM-4 leads at 87.6% vs Qwen1.5-MoE at 61.5%.