Compare AI models

Specifications
Parameters
—0.6B/1.7B/4B/8B/14B/30B/32B/235B
Context window
128k—
API pricing
Cheapest input
$0.44Mistral$0.064DeepInfra
Cheapest output
$2.20Mistral$0.192DeepInfra
$198Mistral$30.00DeepInfra · fp8
Benchmarks
GPQA Diamond
65.7%71.1%
Overview
CompanyMistralQwen
Release dateAug 12 2025Apr 29 2025
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

Qwen3 leads Mistral Medium 3.1 on 1 of the 1 benchmark they both report (GPQA Diamond). Qwen3 shipped 105 days before Mistral Medium 3.1, so benchmark comparisons should account for the intervening progress.

Mistral Medium 3.1 is closed, while Qwen3 is open weight.

On GPQA Diamond, Qwen3 leads at 71.1% vs Mistral Medium 3.1 at 65.7%.