Compare AI models

Specifications
Parameters
7B14B
Context window
256k2k
Benchmarks
HumanEval
75%32.3%
Overview
CompanyMistralQwen
Release dateJul 16 2024Sep 25 2023
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Codestral Mamba 7B leads Qwen-14B on 1 of the 1 benchmark they both report (HumanEval). Qwen-14B shipped 295 days before Codestral Mamba 7B, so benchmark comparisons should account for the intervening progress.

Codestral Mamba 7B has 7B parameters, while Qwen-14B has 14B. Context windows are 256k (Codestral Mamba 7B) vs 2k (Qwen-14B).

On HumanEval, Codestral Mamba 7B leads at 75% vs Qwen-14B at 32.3%.