Compare AI models

Specifications
Parameters
14B—
Context window
2k128k
Benchmarks
HumanEval
32.3%75.7%
MATH
24.8%57.9%
MMLU
66.3%81.9%
GSM8K
61.3%90.9%
Overview
CompanyQwenZ.ai
Release dateSep 25 2023Jun 5 2024
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

GLM-4-Air leads Qwen-14B on 4 of the 4 benchmarks they both report (HumanEval, MATH, MMLU, GSM8K). Qwen-14B shipped 254 days before GLM-4-Air, so benchmark comparisons should account for the intervening progress.

Context windows are 2k (Qwen-14B) vs 128k (GLM-4-Air). Qwen-14B is open weight, while GLM-4-Air is closed.

On HumanEval, GLM-4-Air leads at 75.7% vs Qwen-14B at 32.3%. On MATH, GLM-4-Air leads at 57.9% vs Qwen-14B at 24.8%. On MMLU, GLM-4-Air leads at 81.9% vs Qwen-14B at 66.3%. On GSM8K, GLM-4-Air leads at 90.9% vs Qwen-14B at 61.3%.