Compare AI models

Specifications
Parameters
—0.6B/1.7B/4B/8B/14B/30B/32B/235B
Context window
40k—
API pricing
Cheapest input
—$0.064DeepInfra
Cheapest output
—$0.192DeepInfra
—$30.00DeepInfra · fp8
Benchmarks
LiveCodeBench
59.35%70.7%
AIME 2024
72.03%85.7%
AIME 2025
60.99%81.5%
GPQA Diamond
71.46%71.1%
Overview
CompanyMistralQwen
Release dateJul 24 2025Apr 29 2025
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

Qwen3 leads Magistral Medium 1.1 on 3 of the 4 benchmarks they both report (LiveCodeBench, AIME 2024, AIME 2025, GPQA Diamond). Qwen3 shipped 86 days before Magistral Medium 1.1, so benchmark comparisons should account for the intervening progress.

Magistral Medium 1.1 is closed, while Qwen3 is open weight.

On LiveCodeBench, Qwen3 leads at 70.7% vs Magistral Medium 1.1 at 59.35%. On AIME 2024, Qwen3 leads at 85.7% vs Magistral Medium 1.1 at 72.03%. On AIME 2025, Qwen3 leads at 81.5% vs Magistral Medium 1.1 at 60.99%. On GPQA Diamond, Magistral Medium 1.1 leads at 71.46% vs Qwen3 at 71.1%.