Compare AI models

Specifications
Parameters
7B1.5B/7B/72B
Context window
8k4k
Benchmarks
GSM8K
36.5%96.7%
Overview
CompanyMistralQwen
Release dateSep 27 2023Aug 8 2024
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Qwen2-Math leads Mistral 7B on 1 of the 1 benchmark they both report (GSM8K). Mistral 7B shipped 316 days before Qwen2-Math, so benchmark comparisons should account for the intervening progress.

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

On GSM8K, Qwen2-Math leads at 96.7% vs Mistral 7B at 36.5%.