Compare AI models

Specifications
Parameters
7B1.5B/7B/72B
Context window
32k4k
Benchmarks
MATH
56.6%85.9%
GSM8K
77.1%95.9%
Overview
CompanyMistralQwen
Release dateJul 16 2024Sep 19 2024
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Qwen2.5-Math leads Mathstral 7B on 2 of the 2 benchmarks they both report (MATH, GSM8K). Mathstral 7B shipped 65 days before Qwen2.5-Math, so benchmark comparisons should account for the intervening progress.

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

On MATH, Qwen2.5-Math leads at 85.9% vs Mathstral 7B at 56.6%. On GSM8K, Qwen2.5-Math leads at 95.9% vs Mathstral 7B at 77.1%.