Compare AI models

Specifications
Parameters
7B14B
Context window
8k2k
Benchmarks
HumanEval
26.2%32.3%
MMLU
62.5%66.3%
GSM8K
36.5%61.3%
Overview
CompanyMistralQwen
Release dateSep 27 2023Sep 25 2023
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Qwen-14B leads Mistral 7B on 3 of the 3 benchmarks they both report (HumanEval, MMLU, GSM8K). Qwen-14B shipped 2 days before Mistral 7B, so benchmark comparisons should account for the intervening progress.

Mistral 7B has 7B parameters, while Qwen-14B has 14B. Context windows are 8k (Mistral 7B) vs 2k (Qwen-14B).

On HumanEval, Qwen-14B leads at 32.3% vs Mistral 7B at 26.2%. On MMLU, Qwen-14B leads at 66.3% vs Mistral 7B at 62.5%. On GSM8K, Qwen-14B leads at 61.3% vs Mistral 7B at 36.5%.