Compare AI models

Specifications
Parameters
3B14B
Context window
128k2k
Benchmarks
HumanEval
77.4%32.3%
MATH
51.7%24.8%
Overview
CompanyMistralQwen
Release dateOct 16 2024Sep 25 2023
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

Ministral 3B leads Qwen-14B on 2 of the 2 benchmarks they both report (HumanEval, MATH). Qwen-14B shipped 387 days before Ministral 3B, so benchmark comparisons should account for the intervening progress.

Ministral 3B has 3B parameters, while Qwen-14B has 14B. Context windows are 128k (Ministral 3B) vs 2k (Qwen-14B). Ministral 3B is closed, while Qwen-14B is open weight.

On HumanEval, Ministral 3B leads at 77.4% vs Qwen-14B at 32.3%. On MATH, Ministral 3B leads at 51.7% vs Qwen-14B at 24.8%.