Compare AI models

Specifications
Parameters
—14B
Context window
128k2k
Benchmarks
HumanEval
83.7%32.3%
MATH
64.3%24.8%
MMLU
84.7%66.3%
Overview
CompanyOpenAIQwen
Release dateNov 6 2023Sep 25 2023
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

GPT-4 Turbo leads Qwen-14B on 3 of the 3 benchmarks they both report (HumanEval, MATH, MMLU). Qwen-14B shipped 42 days before GPT-4 Turbo, so benchmark comparisons should account for the intervening progress.

Context windows are 128k (GPT-4 Turbo) vs 2k (Qwen-14B). GPT-4 Turbo is closed, while Qwen-14B is open weight.

On HumanEval, GPT-4 Turbo leads at 83.7% vs Qwen-14B at 32.3%. On MATH, GPT-4 Turbo leads at 64.3% vs Qwen-14B at 24.8%. On MMLU, GPT-4 Turbo leads at 84.7% vs Qwen-14B at 66.3%.