Compare AI models

Specifications
Parameters
1.5B/7B/72B—
Context window
4k128k
Benchmarks
MATH
85.9%50.6%
GSM8K
95.9%90%
Overview
CompanyQwenSpaceXSI
Release dateSep 19 2024Mar 28 2024
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

Qwen2.5-Math leads Grok‑1.5 on 2 of the 2 benchmarks they both report (MATH, GSM8K). Grok‑1.5 shipped 175 days before Qwen2.5-Math, so benchmark comparisons should account for the intervening progress.

Context windows are 4k (Qwen2.5-Math) vs 128k (Grok‑1.5). Qwen2.5-Math is open weight, while Grok‑1.5 is closed.

On MATH, Qwen2.5-Math leads at 85.9% vs Grok‑1.5 at 50.6%. On GSM8K, Qwen2.5-Math leads at 95.9% vs Grok‑1.5 at 90%.