Compare AI models

Specifications
Parameters
1.5B/7B/72B6B
Context window
4k32k
Benchmarks
MATH
85.9%6.9%
GSM8K
95.9%25.9%
Overview
CompanyQwenZ.ai
Release dateSep 19 2024Jun 25 2023
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Qwen2.5-Math leads ChatGLM2-6B on 2 of the 2 benchmarks they both report (MATH, GSM8K). ChatGLM2-6B shipped 452 days before Qwen2.5-Math, so benchmark comparisons should account for the intervening progress.

Qwen2.5-Math has 1.5B/7B/72B parameters, while ChatGLM2-6B has 6B. Context windows are 4k (Qwen2.5-Math) vs 32k (ChatGLM2-6B).

On MATH, Qwen2.5-Math leads at 85.9% vs ChatGLM2-6B at 6.9%. On GSM8K, Qwen2.5-Math leads at 95.9% vs ChatGLM2-6B at 25.9%.