Compare AI models

Specifications
Parameters
12B7B/14B
Context window
128k1M
Benchmarks
HumanEval
72%88.4%
IFEval
61.3%84.3%
MATH
48.1%79.5%
Overview
CompanyMistralQwen
Release dateSep 11 2024Jan 27 2025
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Qwen2.5-1M leads Pixtral 24.09 on 3 of the 3 benchmarks they both report (HumanEval, IFEval, MATH). Pixtral 24.09 shipped 138 days before Qwen2.5-1M, so benchmark comparisons should account for the intervening progress.

Pixtral 24.09 has 12B parameters, while Qwen2.5-1M has 7B/14B. Context windows are 128k (Pixtral 24.09) vs 1M (Qwen2.5-1M).

On HumanEval, Qwen2.5-1M leads at 88.4% vs Pixtral 24.09 at 72%. On IFEval, Qwen2.5-1M leads at 84.3% vs Pixtral 24.09 at 61.3%. On MATH, Qwen2.5-1M leads at 79.5% vs Pixtral 24.09 at 48.1%.