Compare AI models

Specifications
Parameters
7B/67B—
Context window
4k—
Benchmarks
HumanEval
73.8%85.7%
MATH
32.6%73%
MMLU
71.1%86.2%
Overview
CompanyDeepSeekSpaceXSI
Release dateNov 29 2023Aug 13 2024
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

Grok‑2 mini leads DeepSeek-LLM on 3 of the 3 benchmarks they both report (HumanEval, MATH, MMLU). DeepSeek-LLM shipped 258 days before Grok‑2 mini, so benchmark comparisons should account for the intervening progress.

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

On HumanEval, Grok‑2 mini leads at 85.7% vs DeepSeek-LLM at 73.8%. On MATH, Grok‑2 mini leads at 73% vs DeepSeek-LLM at 32.6%. On MMLU, Grok‑2 mini leads at 86.2% vs DeepSeek-LLM at 71.1%.