Compare AI models

Specifications
Parameters
236B—
Context window
128k—
Benchmarks
HumanEval
84.76%85.7%
MATH
71.02%73%
Overview
CompanyDeepSeekSpaceXSI
Release dateJun 28 2024Aug 13 2024
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

Grok‑2 mini leads DeepSeek V2-0628 on 2 of the 2 benchmarks they both report (HumanEval, MATH). DeepSeek V2-0628 shipped 46 days before Grok‑2 mini, so benchmark comparisons should account for the intervening progress.

DeepSeek V2-0628 is open weight, while Grok‑2 mini is closed.

On HumanEval, Grok‑2 mini leads at 85.7% vs DeepSeek V2-0628 at 84.76%. On MATH, Grok‑2 mini leads at 73% vs DeepSeek V2-0628 at 71.02%.