Compare AI models

Specifications
Parameters
24B1.5B/7B/72B
Context window
40k4k
These models have no shared benchmark scores.
Overview
CompanyMistralQwen
Release dateJun 10 2025Aug 8 2024
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Magistral Small and Qwen2-Math don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. Qwen2-Math shipped 306 days before Magistral Small, so benchmark comparisons should account for the intervening progress.

Magistral Small has 24B parameters, while Qwen2-Math has 1.5B/7B/72B. Context windows are 40k (Magistral Small) vs 4k (Qwen2-Math).

Direct benchmark comparisons are unavailable — Magistral Small and Qwen2-Math don't publish scores on any of the same benchmarks.