Compare AI models

Specifications
Parameters
8B—
Context window
128k—
Benchmarks
HumanEval
76.8%85.7%
MATH
54.5%73%
Overview
CompanyMistralSpaceXSI
Release dateOct 16 2024Aug 13 2024
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

Grok‑2 mini leads Ministral 8B on 2 of the 2 benchmarks they both report (HumanEval, MATH). Grok‑2 mini shipped 64 days before Ministral 8B, so benchmark comparisons should account for the intervening progress.

Ministral 8B is open weight, while Grok‑2 mini is closed.

On HumanEval, Grok‑2 mini leads at 85.7% vs Ministral 8B at 76.8%. On MATH, Grok‑2 mini leads at 73% vs Ministral 8B at 54.5%.