Compare AI models

Specifications
Parameters
671B—
Context window
128k128k
Benchmarks
MMLU-Pro
84%75.5%
MMLU
90.8%87.5%
Overview
CompanyDeepSeekSpaceXSI
Release dateJan 20 2025Aug 13 2024
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

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

Context windows are 128k (DeepSeek R1) vs 128k (Grok‑2). DeepSeek R1 is open weight, while Grok‑2 is closed.

On MMLU-Pro, DeepSeek R1 leads at 84% vs Grok‑2 at 75.5%. On MMLU, DeepSeek R1 leads at 90.8% vs Grok‑2 at 87.5%.