Compare AI models

Specifications
Context window
200k—
Benchmarks
HumanEval
84.9%85.7%
MMLU
88.2%86.2%
MMMU
59.4%63.2%
Overview
CompanyAnthropicSpaceXSI
Release dateMar 4 2024Aug 13 2024
AccessClosedClosed
Model detailsView modelView model

Frequently asked questions

Grok‑2 mini leads Claude 3 Opus on 2 of the 3 benchmarks they both report (HumanEval, MMLU, MMMU). Claude 3 Opus shipped 162 days before Grok‑2 mini, so benchmark comparisons should account for the intervening progress.

Published specifications for these two models are limited — see each model page for the latest details.

On HumanEval, Grok‑2 mini leads at 85.7% vs Claude 3 Opus at 84.9%. On MMLU, Claude 3 Opus leads at 88.2% vs Grok‑2 mini at 86.2%. On MMMU, Grok‑2 mini leads at 63.2% vs Claude 3 Opus at 59.4%.