Compare AI models

Specifications
Parameters
1.5B/7B/72B6B
Context window
4k2k
Benchmarks
MATH
85.9%3.1%
GSM8K
95.9%1.5%
Overview
CompanyQwenZ.ai
Release dateSep 19 2024Mar 14 2023
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Qwen2.5-Math leads ChatGLM-6B on 2 of the 2 benchmarks they both report (MATH, GSM8K). ChatGLM-6B shipped 555 days before Qwen2.5-Math, so benchmark comparisons should account for the intervening progress.

Qwen2.5-Math has 1.5B/7B/72B parameters, while ChatGLM-6B has 6B. Context windows are 4k (Qwen2.5-Math) vs 2k (ChatGLM-6B).

On MATH, Qwen2.5-Math leads at 85.9% vs ChatGLM-6B at 3.1%. On GSM8K, Qwen2.5-Math leads at 95.9% vs ChatGLM-6B at 1.5%.