Compare AI models

Specifications
Parameters
1.5B/7B/72B—
Context window
4k—
Benchmarks
MATH
84%73%
Overview
CompanyQwenSpaceXSI
Release dateAug 8 2024Aug 13 2024
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

Qwen2-Math leads Grok‑2 mini on 1 of the 1 benchmark they both report (MATH). Qwen2-Math shipped 5 days before Grok‑2 mini, so benchmark comparisons should account for the intervening progress.

Qwen2-Math is open weight, while Grok‑2 mini is closed.

On MATH, Qwen2-Math leads at 84% vs Grok‑2 mini at 73%.