Compare AI models

Specifications
Parameters
—0.6B/1.7B/4B/8B/14B/30B/32B/235B
Context window
256k—
API pricing
Cheapest input
—$0.064DeepInfra
Cheapest output
—$0.192DeepInfra
—$30.00DeepInfra · fp8
Benchmarks
LiveCodeBench
37.9%70.7%
Overview
CompanyMistralQwen
Release dateJan 13 2025Apr 29 2025
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

Qwen3 leads Codestral 25.01 on 1 of the 1 benchmark they both report (LiveCodeBench). Codestral 25.01 shipped 106 days before Qwen3, so benchmark comparisons should account for the intervening progress.

Codestral 25.01 is closed, while Qwen3 is open weight.

On LiveCodeBench, Qwen3 leads at 70.7% vs Codestral 25.01 at 37.9%.