Compare AI models

Specifications
Parameters
7B/13B/33B/65B—
Context window
2k1M
Benchmarks
HumanEval
23.7%86.6%
MATH
10.6%81.1%
GSM8K
50.9%93.8%
Overview
CompanyMetaQwen
Release dateFeb 24 2023Nov 15 2024
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

Qwen2.5-Turbo (1M) leads LLaMA 1 on 3 of the 3 benchmarks they both report (HumanEval, MATH, GSM8K). LLaMA 1 shipped 630 days before Qwen2.5-Turbo (1M), so benchmark comparisons should account for the intervening progress.

Context windows are 2k (LLaMA 1) vs 1M (Qwen2.5-Turbo (1M)). LLaMA 1 is open weight, while Qwen2.5-Turbo (1M) is closed.

On HumanEval, Qwen2.5-Turbo (1M) leads at 86.6% vs LLaMA 1 at 23.7%. On MATH, Qwen2.5-Turbo (1M) leads at 81.1% vs LLaMA 1 at 10.6%. On GSM8K, Qwen2.5-Turbo (1M) leads at 93.8% vs LLaMA 1 at 50.9%.