Compare AI models

Specifications
Parameters
16B—
Context window
4k—
Benchmarks
HumanEval
45.7%85.7%
MATH
15.2%73%
MMLU
47.2%86.2%
Overview
CompanyDeepSeekSpaceXSI
Release dateJan 11 2024Aug 13 2024
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

Grok‑2 mini leads DeepSeek-MoE on 3 of the 3 benchmarks they both report (HumanEval, MATH, MMLU). DeepSeek-MoE shipped 215 days before Grok‑2 mini, so benchmark comparisons should account for the intervening progress.

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

On HumanEval, Grok‑2 mini leads at 85.7% vs DeepSeek-MoE at 45.7%. On MATH, Grok‑2 mini leads at 73% vs DeepSeek-MoE at 15.2%. On MMLU, Grok‑2 mini leads at 86.2% vs DeepSeek-MoE at 47.2%.