Compare AI models

Specifications
Parameters
1.5B/7B/72B1.5B/4B
Context window
4k8k
Benchmarks
GSM8K
95.9%54.89%
Overview
CompanyQwenZ.ai
Release dateSep 19 2024Nov 29 2024
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Qwen2.5-Math leads GLM-Edge on 1 of the 1 benchmark they both report (GSM8K). Qwen2.5-Math shipped 71 days before GLM-Edge, so benchmark comparisons should account for the intervening progress.

Qwen2.5-Math has 1.5B/7B/72B parameters, while GLM-Edge has 1.5B/4B. Context windows are 4k (Qwen2.5-Math) vs 8k (GLM-Edge).

On GSM8K, Qwen2.5-Math leads at 95.9% vs GLM-Edge at 54.89%.