Compare AI models

Specifications
Parameters
123B7B
Context window
128k64k
API pricing
Cheapest input
$2.00Mistral—
Cheapest output
$6.00Mistral—
$700Mistral—
Benchmarks
HumanEval
92.1%83.5%
Overview
CompanyMistralQwen
Release dateJul 24 2024Apr 16 2024
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Mistral Large 2 leads CodeQwen1.5 on 1 of the 1 benchmark they both report (HumanEval). CodeQwen1.5 shipped 99 days before Mistral Large 2, so benchmark comparisons should account for the intervening progress.

Mistral Large 2 has 123B parameters, while CodeQwen1.5 has 7B. Context windows are 128k (Mistral Large 2) vs 64k (CodeQwen1.5).

On HumanEval, Mistral Large 2 leads at 92.1% vs CodeQwen1.5 at 83.5%.