Compare AI models

Specifications
Parameters
3B7B/14B
Context window
128k1M
Benchmarks
HumanEval
77.4%88.4%
MATH
51.7%79.5%
Overview
CompanyMistralQwen
Release dateOct 16 2024Jan 27 2025
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

Qwen2.5-1M leads Ministral 3B on 2 of the 2 benchmarks they both report (HumanEval, MATH). Ministral 3B shipped 103 days before Qwen2.5-1M, so benchmark comparisons should account for the intervening progress.

Ministral 3B has 3B parameters, while Qwen2.5-1M has 7B/14B. Context windows are 128k (Ministral 3B) vs 1M (Qwen2.5-1M). Ministral 3B is closed, while Qwen2.5-1M is open weight.

On HumanEval, Qwen2.5-1M leads at 88.4% vs Ministral 3B at 77.4%. On MATH, Qwen2.5-1M leads at 79.5% vs Ministral 3B at 51.7%.