Compare AI models

Specifications
Parameters
7B/13B/70B14B
Context window
4k2k
Benchmarks
HumanEval
29.9%32.3%
MATH
13.5%24.8%
MMLU
68.9%66.3%
GSM8K
56.8%61.3%
Overview
CompanyMetaQwen
Release dateJul 18 2023Sep 25 2023
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Qwen-14B leads LLaMA 2 on 3 of the 4 benchmarks they both report (HumanEval, MATH, MMLU, GSM8K). LLaMA 2 shipped 69 days before Qwen-14B, so benchmark comparisons should account for the intervening progress.

LLaMA 2 has 7B/13B/70B parameters, while Qwen-14B has 14B. Context windows are 4k (LLaMA 2) vs 2k (Qwen-14B).

On HumanEval, Qwen-14B leads at 32.3% vs LLaMA 2 at 29.9%. On MATH, Qwen-14B leads at 24.8% vs LLaMA 2 at 13.5%. On MMLU, LLaMA 2 leads at 68.9% vs Qwen-14B at 66.3%. On GSM8K, Qwen-14B leads at 61.3% vs LLaMA 2 at 56.8%.