Compare AI models

Specifications
Parameters
8B14B
Context window
128k2k
Benchmarks
HumanEval
76.8%32.3%
MATH
54.5%24.8%
Overview
CompanyMistralQwen
Release dateOct 16 2024Sep 25 2023
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Ministral 8B leads Qwen-14B on 2 of the 2 benchmarks they both report (HumanEval, MATH). Qwen-14B shipped 387 days before Ministral 8B, so benchmark comparisons should account for the intervening progress.

Ministral 8B has 8B parameters, while Qwen-14B has 14B. Context windows are 128k (Ministral 8B) vs 2k (Qwen-14B).

On HumanEval, Ministral 8B leads at 76.8% vs Qwen-14B at 32.3%. On MATH, Ministral 8B leads at 54.5% vs Qwen-14B at 24.8%.