Compare AI models

Specifications
Parameters
7B14.3B
Context window
32k32k
Benchmarks
GSM8K
77.1%61.5%
Overview
CompanyMistralQwen
Release dateJul 16 2024Mar 28 2024
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Mathstral 7B leads Qwen1.5-MoE on 1 of the 1 benchmark they both report (GSM8K). Qwen1.5-MoE shipped 110 days before Mathstral 7B, so benchmark comparisons should account for the intervening progress.

Mathstral 7B has 7B parameters, while Qwen1.5-MoE has 14.3B. Context windows are 32k (Mathstral 7B) vs 32k (Qwen1.5-MoE).

On GSM8K, Mathstral 7B leads at 77.1% vs Qwen1.5-MoE at 61.5%.