Compare AI models

Specifications
Parameters
47B14B
Context window
32k2k
Benchmarks
HumanEval
40.2%32.3%
MMLU
70.6%66.3%
GSM8K
58.4%61.3%
Overview
CompanyMistralQwen
Release dateDec 8 2023Sep 25 2023
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Mixtral 8×7B leads Qwen-14B on 2 of the 3 benchmarks they both report (HumanEval, MMLU, GSM8K). Qwen-14B shipped 74 days before Mixtral 8×7B, so benchmark comparisons should account for the intervening progress.

Mixtral 8×7B has 47B parameters, while Qwen-14B has 14B. Context windows are 32k (Mixtral 8×7B) vs 2k (Qwen-14B).

On HumanEval, Mixtral 8×7B leads at 40.2% vs Qwen-14B at 32.3%. On MMLU, Mixtral 8×7B leads at 70.6% vs Qwen-14B at 66.3%. On GSM8K, Qwen-14B leads at 61.3% vs Mixtral 8×7B at 58.4%.