Compare AI models

Specifications
Parameters
22B1.5B/7B/72B
Context window
32k4k
These models have no shared benchmark scores.
Overview
CompanyMistralQwen
Release dateSep 17 2024Aug 8 2024
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Mistral Small 2 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 40 days before Mistral Small 2, so benchmark comparisons should account for the intervening progress.

Mistral Small 2 has 22B parameters, while Qwen2-Math has 1.5B/7B/72B. Context windows are 32k (Mistral Small 2) vs 4k (Qwen2-Math).

Direct benchmark comparisons are unavailable — Mistral Small 2 and Qwen2-Math don't publish scores on any of the same benchmarks.