Compare AI models

Specifications
Parameters
—1.5B/7B/72B
Context window
128k4k
These models have no shared benchmark scores.
Overview
CompanyMistralQwen
Release dateJul 10 2025Sep 19 2024
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

Devstral Medium and Qwen2.5-Math don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. Qwen2.5-Math shipped 294 days before Devstral Medium, so benchmark comparisons should account for the intervening progress.

Context windows are 128k (Devstral Medium) vs 4k (Qwen2.5-Math). Devstral Medium is closed, while Qwen2.5-Math is open weight.

Direct benchmark comparisons are unavailable — Devstral Medium and Qwen2.5-Math don't publish scores on any of the same benchmarks.