Compare AI models

Specifications
Parameters
8B110B
Context window
128k32k
Benchmarks
HumanEval
76.8%52.4%
MATH
54.5%49.6%
Overview
CompanyMistralQwen
Release dateOct 16 2024Apr 25 2024
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Ministral 8B leads Qwen1.5-110B on 2 of the 2 benchmarks they both report (HumanEval, MATH). Qwen1.5-110B shipped 174 days before Ministral 8B, so benchmark comparisons should account for the intervening progress.

Ministral 8B has 8B parameters, while Qwen1.5-110B has 110B. Context windows are 128k (Ministral 8B) vs 32k (Qwen1.5-110B).

On HumanEval, Ministral 8B leads at 76.8% vs Qwen1.5-110B at 52.4%. On MATH, Ministral 8B leads at 54.5% vs Qwen1.5-110B at 49.6%.