Compare AI models

Specifications
Parameters
236B—
Context window
128k128k
Benchmarks
HumanEval
84.76%74.1%
MATH
71.02%50.6%
Overview
CompanyDeepSeekSpaceXSI
Release dateJun 28 2024Mar 28 2024
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

DeepSeek V2-0628 leads Grok‑1.5 on 2 of the 2 benchmarks they both report (HumanEval, MATH). Grok‑1.5 shipped 92 days before DeepSeek V2-0628, so benchmark comparisons should account for the intervening progress.

Context windows are 128k (DeepSeek V2-0628) vs 128k (Grok‑1.5). DeepSeek V2-0628 is open weight, while Grok‑1.5 is closed.

On HumanEval, DeepSeek V2-0628 leads at 84.76% vs Grok‑1.5 at 74.1%. On MATH, DeepSeek V2-0628 leads at 71.02% vs Grok‑1.5 at 50.6%.