Compare AI models

Specifications
Parameters
123B14B
Context window
128k2k
API pricing
Cheapest input
$2.00Mistral—
Cheapest output
$6.00Mistral—
$700Mistral—
Benchmarks
HumanEval
92.1%32.3%
MMLU
84%66.3%
Overview
CompanyMistralQwen
Release dateJul 24 2024Sep 25 2023
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Mistral Large 2 leads Qwen-14B on 2 of the 2 benchmarks they both report (HumanEval, MMLU). Qwen-14B shipped 303 days before Mistral Large 2, so benchmark comparisons should account for the intervening progress.

Mistral Large 2 has 123B parameters, while Qwen-14B has 14B. Context windows are 128k (Mistral Large 2) vs 2k (Qwen-14B).

On HumanEval, Mistral Large 2 leads at 92.1% vs Qwen-14B at 32.3%. On MMLU, Mistral Large 2 leads at 84% vs Qwen-14B at 66.3%.