Compare AI models

Specifications
Parameters
7B/13B/33B/65B7B/14B
Context window
2k1M
Benchmarks
HumanEval
23.7%88.4%
MATH
10.6%79.5%
GSM8K
50.9%94.8%
Overview
CompanyMetaQwen
Release dateFeb 24 2023Jan 27 2025
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Qwen2.5-1M leads LLaMA 1 on 3 of the 3 benchmarks they both report (HumanEval, MATH, GSM8K). LLaMA 1 shipped 703 days before Qwen2.5-1M, so benchmark comparisons should account for the intervening progress.

LLaMA 1 has 7B/13B/33B/65B parameters, while Qwen2.5-1M has 7B/14B. Context windows are 2k (LLaMA 1) vs 1M (Qwen2.5-1M).

On HumanEval, Qwen2.5-1M leads at 88.4% vs LLaMA 1 at 23.7%. On MATH, Qwen2.5-1M leads at 79.5% vs LLaMA 1 at 10.6%. On GSM8K, Qwen2.5-1M leads at 94.8% vs LLaMA 1 at 50.9%.