Compare AI models

Specifications
Parameters
236B24B
Context window
128k128k
API pricing
Cheapest input
—$0.351Cloudflare
Cheapest output
—$0.555Cloudflare
—$97.95Cloudflare
Benchmarks
HumanEval
84.76%88.41%
MATH
71.02%69.3%
Overview
CompanyDeepSeekMistral
Release dateJun 28 2024Mar 17 2025
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

DeepSeek V2-0628 and Mistral Small 3.1 are evenly matched across the 2 benchmarks they both report (HumanEval, MATH). DeepSeek V2-0628 shipped 262 days before Mistral Small 3.1, so benchmark comparisons should account for the intervening progress.

DeepSeek V2-0628 has 236B parameters, while Mistral Small 3.1 has 24B. Context windows are 128k (DeepSeek V2-0628) vs 128k (Mistral Small 3.1).

On HumanEval, Mistral Small 3.1 leads at 88.41% vs DeepSeek V2-0628 at 84.76%. On MATH, DeepSeek V2-0628 leads at 71.02% vs Mistral Small 3.1 at 69.3%.