Compare AI models

Specifications
Parameters
141B7B/14B
Context window
64k1M
API pricing
Cheapest input
$2.00Mistral—
Cheapest output
$6.00Mistral—
$700Mistral · zdr—
Benchmarks
HumanEval
45.1%88.4%
GSM8K
78.6%94.8%
Overview
CompanyMistralQwen
Release dateApr 10 2024Jan 27 2025
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Qwen2.5-1M leads Mixtral 8×22B on 2 of the 2 benchmarks they both report (HumanEval, GSM8K). Mixtral 8×22B shipped 292 days before Qwen2.5-1M, so benchmark comparisons should account for the intervening progress.

Mixtral 8×22B has 141B parameters, while Qwen2.5-1M has 7B/14B. Context windows are 64k (Mixtral 8×22B) vs 1M (Qwen2.5-1M).

On HumanEval, Qwen2.5-1M leads at 88.4% vs Mixtral 8×22B at 45.1%. On GSM8K, Qwen2.5-1M leads at 94.8% vs Mixtral 8×22B at 78.6%.