Compare AI models

Specifications
Parameters
7B/14B—
Context window
1M128k
Benchmarks
HumanEval
88.4%75.7%
IFEval
84.3%75.2%
MATH
79.5%57.9%
GSM8K
94.8%90.9%
Overview
CompanyQwenZ.ai
Release dateJan 27 2025Jun 5 2024
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

Qwen2.5-1M leads GLM-4-Air on 4 of the 4 benchmarks they both report (HumanEval, IFEval, MATH, GSM8K). GLM-4-Air shipped 236 days before Qwen2.5-1M, so benchmark comparisons should account for the intervening progress.

Context windows are 1M (Qwen2.5-1M) vs 128k (GLM-4-Air). Qwen2.5-1M is open weight, while GLM-4-Air is closed.

On HumanEval, Qwen2.5-1M leads at 88.4% vs GLM-4-Air at 75.7%. On IFEval, Qwen2.5-1M leads at 84.3% vs GLM-4-Air at 75.2%. On MATH, Qwen2.5-1M leads at 79.5% vs GLM-4-Air at 57.9%. On GSM8K, Qwen2.5-1M leads at 94.8% vs GLM-4-Air at 90.9%.