Compare AI models

Specifications
Parameters
7B1.5B/7B/72B
Context window
256k4k
These models have no shared benchmark scores.
Overview
CompanyMistralQwen
Release dateJul 16 2024Aug 8 2024
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Codestral Mamba 7B and Qwen2-Math don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. Codestral Mamba 7B shipped 23 days before Qwen2-Math, so benchmark comparisons should account for the intervening progress.

Codestral Mamba 7B has 7B parameters, while Qwen2-Math has 1.5B/7B/72B. Context windows are 256k (Codestral Mamba 7B) vs 4k (Qwen2-Math).

Direct benchmark comparisons are unavailable — Codestral Mamba 7B and Qwen2-Math don't publish scores on any of the same benchmarks.