Compare AI models

Specifications
Context window
128k1M
API pricing
Cheapest input
$0.44Mistral—
Cheapest output
$2.20Mistral—
$198Mistral—
Benchmarks
LiveCodeBench
30.3%37.8%
HumanEval
92.1%86.6%
IFEval
89.4%76.3%
MMLU-Pro
77.2%64.5%
Overview
CompanyMistralQwen
Release dateMay 7 2025Nov 15 2024
AccessClosedClosed
Model detailsView modelView model

Frequently asked questions

Mistral Medium 3 leads Qwen2.5-Turbo (1M) on 3 of the 4 benchmarks they both report (LiveCodeBench, HumanEval, IFEval, MMLU-Pro). Qwen2.5-Turbo (1M) shipped 173 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-Turbo (1M)).

On LiveCodeBench, Qwen2.5-Turbo (1M) leads at 37.8% vs Mistral Medium 3 at 30.3%. On HumanEval, Mistral Medium 3 leads at 92.1% vs Qwen2.5-Turbo (1M) at 86.6%. On IFEval, Mistral Medium 3 leads at 89.4% vs Qwen2.5-Turbo (1M) at 76.3%. On MMLU-Pro, Mistral Medium 3 leads at 77.2% vs Qwen2.5-Turbo (1M) at 64.5%.