Compare AI models

Specifications
Parameters
1.5B/7B/72B9B
Context window
4k128k
Benchmarks
MATH
85.9%50.6%
GSM8K
95.9%79.6%
Overview
CompanyQwenZ.ai
Release dateSep 19 2024Jun 5 2024
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Qwen2.5-Math leads GLM-4-9B on 2 of the 2 benchmarks they both report (MATH, GSM8K). GLM-4-9B shipped 106 days before Qwen2.5-Math, so benchmark comparisons should account for the intervening progress.

Qwen2.5-Math has 1.5B/7B/72B parameters, while GLM-4-9B has 9B. Context windows are 4k (Qwen2.5-Math) vs 128k (GLM-4-9B).

On MATH, Qwen2.5-Math leads at 85.9% vs GLM-4-9B at 50.6%. On GSM8K, Qwen2.5-Math leads at 95.9% vs GLM-4-9B at 79.6%.