Compare AI models

Specifications
Parameters
3B110B
Context window
128k32k
Benchmarks
HumanEval
77.4%52.4%
MATH
51.7%49.6%
Overview
CompanyMistralQwen
Release dateOct 16 2024Apr 25 2024
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

Ministral 3B leads Qwen1.5-110B on 2 of the 2 benchmarks they both report (HumanEval, MATH). Qwen1.5-110B shipped 174 days before Ministral 3B, so benchmark comparisons should account for the intervening progress.

Ministral 3B has 3B parameters, while Qwen1.5-110B has 110B. Context windows are 128k (Ministral 3B) vs 32k (Qwen1.5-110B). Ministral 3B is closed, while Qwen1.5-110B is open weight.

On HumanEval, Ministral 3B leads at 77.4% vs Qwen1.5-110B at 52.4%. On MATH, Ministral 3B leads at 51.7% vs Qwen1.5-110B at 49.6%.