Compare AI models

Specifications
Parameters
—0.5B/1.5B/7B/57B/72B
Context window
128k128k
API pricing
Input price
$0.15—
Output price
$0.60—
Cached input price
$0.075—
Cheapest input
$0.15Azure—
Cheapest output
$0.60Azure—
$60.00OpenAI list price—
Benchmarks
HumanEval
87.2%86%
MATH
70.2%69%
MMLU
82%82.3%
Overview
CompanyOpenAIQwen
Release dateJul 18 2024Jun 6 2024
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

GPT-4o mini leads Qwen2 on 2 of the 3 benchmarks they both report (HumanEval, MATH, MMLU). Only GPT-4o mini has a verified first-party price for an available API: $0.15 per million input tokens and $0.60 per million output tokens. No currently available pay-as-you-go API rate is tracked for Qwen2. Qwen2 shipped 42 days before GPT-4o mini, so benchmark comparisons should account for the intervening progress.

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

On HumanEval, GPT-4o mini leads at 87.2% vs Qwen2 at 86%. On MATH, GPT-4o mini leads at 70.2% vs Qwen2 at 69%. On MMLU, Qwen2 leads at 82.3% vs GPT-4o mini at 82%.