Compare AI models

Specifications
Parameters
236B—
Context window
128k—
Benchmarks
HumanEval
89%85.7%
Overview
CompanyDeepSeekSpaceXSI
Release dateSep 5 2024Aug 13 2024
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

DeepSeek V2.5 leads Grok‑2 mini on 1 of the 1 benchmark they both report (HumanEval). Grok‑2 mini shipped 23 days before DeepSeek V2.5, so benchmark comparisons should account for the intervening progress.

DeepSeek V2.5 is open weight, while Grok‑2 mini is closed.

On HumanEval, DeepSeek V2.5 leads at 89% vs Grok‑2 mini at 85.7%.