Compare AI models

Specifications
Parameters
—0.5B/1.5B/3B/7B/14B/32B
Context window
128k128k
API pricing
Input price
$2.50—
Output price
$10.00—
Cached input price
$1.25—
Cheapest input
$2.50Azure$0.66Cloudflare
Cheapest output
$10.00Azure$1.00Cloudflare
$1,000OpenAI list price$182Cloudflare
Benchmarks
HumanEval
91%92.7%
MATH
76.6%76.4%
MMLU
87.2%77.6%
Overview
CompanyOpenAIQwen
Release dateMay 13 2024Sep 19 2024
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

GPT-4o leads Qwen2.5-Coder on 2 of the 3 benchmarks they both report (HumanEval, MATH, MMLU). Only GPT-4o has a verified first-party price for an available API: $2.50 per million input tokens and $10.00 per million output tokens. No currently available pay-as-you-go API rate is tracked for Qwen2.5-Coder. GPT-4o shipped 129 days before Qwen2.5-Coder, so benchmark comparisons should account for the intervening progress.

Context windows are 128k (GPT-4o) vs 128k (Qwen2.5-Coder). GPT-4o is closed, while Qwen2.5-Coder is open weight.

On HumanEval, Qwen2.5-Coder leads at 92.7% vs GPT-4o at 91%. On MATH, GPT-4o leads at 76.6% vs Qwen2.5-Coder at 76.4%. On MMLU, GPT-4o leads at 87.2% vs Qwen2.5-Coder at 77.6%.