Compare AI models

Specifications
Parameters
—14B
Context window
32k2k
Benchmarks
HumanEval
45.1%32.3%
MMLU
81.2%66.3%
GSM8K
81%61.3%
Overview
CompanyMistralQwen
Release dateFeb 26 2024Sep 25 2023
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

Mistral Large leads Qwen-14B on 3 of the 3 benchmarks they both report (HumanEval, MMLU, GSM8K). Qwen-14B shipped 154 days before Mistral Large, so benchmark comparisons should account for the intervening progress.

Context windows are 32k (Mistral Large) vs 2k (Qwen-14B). Mistral Large is closed, while Qwen-14B is open weight.

On HumanEval, Mistral Large leads at 45.1% vs Qwen-14B at 32.3%. On MMLU, Mistral Large leads at 81.2% vs Qwen-14B at 66.3%. On GSM8K, Mistral Large leads at 81% vs Qwen-14B at 61.3%.