Compare AI models

Specifications
Parameters
7B314B
Context window
32k8k
Benchmarks
HumanEval
38.4%63.2%
MATH
13.2%23.9%
Overview
CompanyMistralSpaceXSI
Release dateMay 22 2024Nov 3 2023
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Grok‑1 leads Mistral 7B v0.3 on 2 of the 2 benchmarks they both report (HumanEval, MATH). Grok‑1 shipped 201 days before Mistral 7B v0.3, so benchmark comparisons should account for the intervening progress.

Mistral 7B v0.3 has 7B parameters, while Grok‑1 has 314B. Context windows are 32k (Mistral 7B v0.3) vs 8k (Grok‑1).

On HumanEval, Grok‑1 leads at 63.2% vs Mistral 7B v0.3 at 38.4%. On MATH, Grok‑1 leads at 23.9% vs Mistral 7B v0.3 at 13.2%.