Compare AI models

Specifications
Parameters
—0.5B/1.5B/7B/57B/72B
Context window
8k128k
API pricing
Cheapest input
$30.00Azure—
Cheapest output
$60.00Azure—
$9,000Azure—
Benchmarks
HumanEval
67%86%
MMLU
86.4%82.3%
GSM8K
92%91.1%
Overview
CompanyOpenAIQwen
Release dateMar 14 2023Jun 6 2024
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

GPT-4 leads Qwen2 on 2 of the 3 benchmarks they both report (HumanEval, MMLU, GSM8K). GPT-4 shipped 450 days before Qwen2, so benchmark comparisons should account for the intervening progress.

Context windows are 8k (GPT-4) vs 128k (Qwen2). GPT-4 is closed, while Qwen2 is open weight.

On HumanEval, Qwen2 leads at 86% vs GPT-4 at 67%. On MMLU, GPT-4 leads at 86.4% vs Qwen2 at 82.3%. On GSM8K, GPT-4 leads at 92% vs Qwen2 at 91.1%.