Compare AI models

Specifications
Parameters
47B14.3B
Context window
32k32k
Benchmarks
HumanEval
40.2%34.2%
MMLU
70.6%62.5%
GSM8K
58.4%61.5%
Overview
CompanyMistralQwen
Release dateDec 8 2023Mar 28 2024
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Mixtral 8×7B leads Qwen1.5-MoE on 2 of the 3 benchmarks they both report (HumanEval, MMLU, GSM8K). Mixtral 8×7B shipped 111 days before Qwen1.5-MoE, so benchmark comparisons should account for the intervening progress.

Mixtral 8×7B has 47B parameters, while Qwen1.5-MoE has 14.3B. Context windows are 32k (Mixtral 8×7B) vs 32k (Qwen1.5-MoE).

On HumanEval, Mixtral 8×7B leads at 40.2% vs Qwen1.5-MoE at 34.2%. On MMLU, Mixtral 8×7B leads at 70.6% vs Qwen1.5-MoE at 62.5%. On GSM8K, Qwen1.5-MoE leads at 61.5% vs Mixtral 8×7B at 58.4%.