Compare AI models

Specifications
Parameters
—7B/14B
Context window
128k1M
API pricing
Cheapest input
$0.44Mistral—
Cheapest output
$2.20Mistral—
$198Mistral—
Benchmarks
LiveCodeBench
30.3%38.6%
HumanEval
92.1%88.4%
IFEval
89.4%84.3%
MMLU-Pro
77.2%63.3%
Overview
CompanyMistralQwen
Release dateMay 7 2025Jan 27 2025
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

Mistral Medium 3 leads Qwen2.5-1M on 3 of the 4 benchmarks they both report (LiveCodeBench, HumanEval, IFEval, MMLU-Pro). Qwen2.5-1M shipped 100 days before Mistral Medium 3, so benchmark comparisons should account for the intervening progress.

Context windows are 128k (Mistral Medium 3) vs 1M (Qwen2.5-1M). Mistral Medium 3 is closed, while Qwen2.5-1M is open weight.

On LiveCodeBench, Qwen2.5-1M leads at 38.6% vs Mistral Medium 3 at 30.3%. On HumanEval, Mistral Medium 3 leads at 92.1% vs Qwen2.5-1M at 88.4%. On IFEval, Mistral Medium 3 leads at 89.4% vs Qwen2.5-1M at 84.3%. On MMLU-Pro, Mistral Medium 3 leads at 77.2% vs Qwen2.5-1M at 63.3%.