Compare AI models

Specifications
Parameters
236B314B
Context window
128k8k
Benchmarks
HumanEval
84.76%63.2%
MATH
71.02%23.9%
Overview
CompanyDeepSeekSpaceXSI
Release dateJun 28 2024Nov 3 2023
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

DeepSeek V2-0628 leads Grok‑1 on 2 of the 2 benchmarks they both report (HumanEval, MATH). Grok‑1 shipped 238 days before DeepSeek V2-0628, so benchmark comparisons should account for the intervening progress.

DeepSeek V2-0628 has 236B parameters, while Grok‑1 has 314B. Context windows are 128k (DeepSeek V2-0628) vs 8k (Grok‑1).

On HumanEval, DeepSeek V2-0628 leads at 84.76% vs Grok‑1 at 63.2%. On MATH, DeepSeek V2-0628 leads at 71.02% vs Grok‑1 at 23.9%.