Compare AI models

Specifications
Parameters
12B110B
Context window
128k32k
Benchmarks
HumanEval
72%52.4%
MATH
48.1%49.6%
MMLU
69.2%80.4%
Overview
CompanyMistralQwen
Release dateSep 11 2024Apr 25 2024
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Qwen1.5-110B leads Pixtral 24.09 on 2 of the 3 benchmarks they both report (HumanEval, MATH, MMLU). Qwen1.5-110B shipped 139 days before Pixtral 24.09, so benchmark comparisons should account for the intervening progress.

Pixtral 24.09 has 12B parameters, while Qwen1.5-110B has 110B. Context windows are 128k (Pixtral 24.09) vs 32k (Qwen1.5-110B).

On HumanEval, Pixtral 24.09 leads at 72% vs Qwen1.5-110B at 52.4%. On MATH, Qwen1.5-110B leads at 49.6% vs Pixtral 24.09 at 48.1%. On MMLU, Qwen1.5-110B leads at 80.4% vs Pixtral 24.09 at 69.2%.