Compare AI models

Specifications
Parameters
—1.5B/7B/72B
Context window
32k4k
Benchmarks
GSM8K
81%95.9%
Overview
CompanyMistralQwen
Release dateFeb 26 2024Sep 19 2024
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

Qwen2.5-Math leads Mistral Large on 1 of the 1 benchmark they both report (GSM8K). Mistral Large shipped 206 days before Qwen2.5-Math, so benchmark comparisons should account for the intervening progress.

Context windows are 32k (Mistral Large) vs 4k (Qwen2.5-Math). Mistral Large is closed, while Qwen2.5-Math is open weight.

On GSM8K, Qwen2.5-Math leads at 95.9% vs Mistral Large at 81%.