Compare AI models

Specifications
Parameters
—1.5B/7B/72B
Context window
32k4k
Benchmarks
MATH
53.2%84%
GSM8K
88.9%96.7%
Overview
CompanyGoogleQwen
Release dateFeb 8 2024Aug 8 2024
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

Qwen2-Math leads Gemini 1.0 Ultra on 2 of the 2 benchmarks they both report (MATH, GSM8K). Gemini 1.0 Ultra shipped 182 days before Qwen2-Math, so benchmark comparisons should account for the intervening progress.

Context windows are 32k (Gemini 1.0 Ultra) vs 4k (Qwen2-Math). Gemini 1.0 Ultra is closed, while Qwen2-Math is open weight.

On MATH, Qwen2-Math leads at 84% vs Gemini 1.0 Ultra at 53.2%. On GSM8K, Qwen2-Math leads at 96.7% vs Gemini 1.0 Ultra at 88.9%.