Compare AI models

Specifications
Parameters
7B1.5B/7B/72B
Context window
32k4k
Benchmarks
MATH
13.2%85.9%
Overview
CompanyMistralQwen
Release dateMay 22 2024Sep 19 2024
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Qwen2.5-Math leads Mistral 7B v0.3 on 1 of the 1 benchmark they both report (MATH). Mistral 7B v0.3 shipped 120 days before Qwen2.5-Math, so benchmark comparisons should account for the intervening progress.

Mistral 7B v0.3 has 7B parameters, while Qwen2.5-Math has 1.5B/7B/72B. Context windows are 32k (Mistral 7B v0.3) vs 4k (Qwen2.5-Math).

On MATH, Qwen2.5-Math leads at 85.9% vs Mistral 7B v0.3 at 13.2%.