Compare AI models

Specifications
Parameters
3B1.5B/7B/72B
Context window
128k4k
Benchmarks
MATH
51.7%85.9%
Overview
CompanyMistralQwen
Release dateOct 16 2024Sep 19 2024
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

Qwen2.5-Math leads Ministral 3B on 1 of the 1 benchmark they both report (MATH). Qwen2.5-Math shipped 27 days before Ministral 3B, so benchmark comparisons should account for the intervening progress.

Ministral 3B has 3B parameters, while Qwen2.5-Math has 1.5B/7B/72B. Context windows are 128k (Ministral 3B) vs 4k (Qwen2.5-Math). Ministral 3B is closed, while Qwen2.5-Math is open weight.

On MATH, Qwen2.5-Math leads at 85.9% vs Ministral 3B at 51.7%.