Compare AI models

Specifications
Parameters
22B0.5B/1.8B/4B/7B/14B/72B
Context window
32k32k
Overview
CompanyMistralQwen
Release dateSep 17 2024Feb 4 2024
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Mistral Small 2 and Qwen1.5 don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. Qwen1.5 shipped 226 days before Mistral Small 2, so benchmark comparisons should account for the intervening progress.

Mistral Small 2 has 22B parameters, while Qwen1.5 has 0.5B/1.8B/4B/7B/14B/72B. Context windows are 32k (Mistral Small 2) vs 32k (Qwen1.5).

Direct benchmark comparisons are unavailable — Mistral Small 2 and Qwen1.5 don't publish scores on any of the same benchmarks.