Compare AI models

Specifications
Parameters
671B—
Context window
128k—
Benchmarks
MMLU-Pro
84%72%
MMLU
90.8%86.2%
Overview
CompanyDeepSeekSpaceXSI
Release dateJan 20 2025Aug 13 2024
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

DeepSeek R1 leads Grok‑2 mini on 2 of the 2 benchmarks they both report (MMLU-Pro, MMLU). Grok‑2 mini shipped 160 days before DeepSeek R1, so benchmark comparisons should account for the intervening progress.

DeepSeek R1 is open weight, while Grok‑2 mini is closed.

On MMLU-Pro, DeepSeek R1 leads at 84% vs Grok‑2 mini at 72%. On MMLU, DeepSeek R1 leads at 90.8% vs Grok‑2 mini at 86.2%.