Compare AI models

Specifications
Parameters
1B/3B/11B/90B—
Context window
128k—
API pricing
Cheapest input
$0.027Cloudflare—
Cheapest output
$0.201Cloudflare—
$15.45Cloudflare—
Benchmarks
MATH
68%73%
MMLU
86%86.2%
MathVista
57.3%68.1%
MMMU
60.3%63.2%
Overview
CompanyMetaSpaceXSI
Release dateSep 25 2024Aug 13 2024
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

Grok‑2 mini leads LLaMA 3.2 on 4 of the 4 benchmarks they both report (MATH, MMLU, MathVista, MMMU). Grok‑2 mini shipped 43 days before LLaMA 3.2, so benchmark comparisons should account for the intervening progress.

LLaMA 3.2 is open weight, while Grok‑2 mini is closed.

On MATH, Grok‑2 mini leads at 73% vs LLaMA 3.2 at 68%. On MMLU, Grok‑2 mini leads at 86.2% vs LLaMA 3.2 at 86%. On MathVista, Grok‑2 mini leads at 68.1% vs LLaMA 3.2 at 57.3%. On MMMU, Grok‑2 mini leads at 63.2% vs LLaMA 3.2 at 60.3%.