Compare AI models

Specifications
Parameters
8B14.3B
Context window
128k32k
Benchmarks
HumanEval
76.8%34.2%
Overview
CompanyMistralQwen
Release dateOct 16 2024Mar 28 2024
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Ministral 8B leads Qwen1.5-MoE on 1 of the 1 benchmark they both report (HumanEval). Qwen1.5-MoE shipped 202 days before Ministral 8B, so benchmark comparisons should account for the intervening progress.

Ministral 8B has 8B parameters, while Qwen1.5-MoE has 14.3B. Context windows are 128k (Ministral 8B) vs 32k (Qwen1.5-MoE).

On HumanEval, Ministral 8B leads at 76.8% vs Qwen1.5-MoE at 34.2%.