Compare AI models

Specifications
Parameters
—14B
Context window
128k2k
API pricing
Cheapest input
$0.44Mistral—
Cheapest output
$2.20Mistral—
$198Mistral—
Benchmarks
HumanEval
92.1%32.3%
Overview
CompanyMistralQwen
Release dateMay 7 2025Sep 25 2023
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

Mistral Medium 3 leads Qwen-14B on 1 of the 1 benchmark they both report (HumanEval). Qwen-14B shipped 590 days before Mistral Medium 3, so benchmark comparisons should account for the intervening progress.

Context windows are 128k (Mistral Medium 3) vs 2k (Qwen-14B). Mistral Medium 3 is closed, while Qwen-14B is open weight.

On HumanEval, Mistral Medium 3 leads at 92.1% vs Qwen-14B at 32.3%.