Compare AI models

Specifications
Parameters
2B/7B1.5B/7B/72B
Context window
8k4k
Benchmarks
MATH
24.3%84%
GSM8K
46.4%96.7%
Overview
CompanyGoogleQwen
Release dateFeb 21 2024Aug 8 2024
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Qwen2-Math leads Gemma 1 on 2 of the 2 benchmarks they both report (MATH, GSM8K). Gemma 1 shipped 169 days before Qwen2-Math, so benchmark comparisons should account for the intervening progress.

Gemma 1 has 2B/7B parameters, while Qwen2-Math has 1.5B/7B/72B. Context windows are 8k (Gemma 1) vs 4k (Qwen2-Math).

On MATH, Qwen2-Math leads at 84% vs Gemma 1 at 24.3%. On GSM8K, Qwen2-Math leads at 96.7% vs Gemma 1 at 46.4%.