Compare AI models

Specifications
Parameters
7B/13B/33B/65B1.5B/7B/72B
Context window
2k4k
Benchmarks
MATH
10.6%85.9%
GSM8K
50.9%95.9%
Overview
CompanyMetaQwen
Release dateFeb 24 2023Sep 19 2024
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Qwen2.5-Math leads LLaMA 1 on 2 of the 2 benchmarks they both report (MATH, GSM8K). LLaMA 1 shipped 573 days before Qwen2.5-Math, so benchmark comparisons should account for the intervening progress.

LLaMA 1 has 7B/13B/33B/65B parameters, while Qwen2.5-Math has 1.5B/7B/72B. Context windows are 2k (LLaMA 1) vs 4k (Qwen2.5-Math).

On MATH, Qwen2.5-Math leads at 85.9% vs LLaMA 1 at 10.6%. On GSM8K, Qwen2.5-Math leads at 95.9% vs LLaMA 1 at 50.9%.