Compare AI models

Specifications
Parameters
—0.5B/1.5B/3B/7B/14B/32B
Context window
1M128k
API pricing
Cheapest input
$0.10Azure$0.66Cloudflare
Cheapest output
$0.40Azure$1.00Cloudflare
$40.00Azure$182Cloudflare
Benchmarks
HumanEval
87%92.7%
IFEval
74.5%79.9%
MMLU
80.1%77.6%
Overview
CompanyOpenAIQwen
Release dateApr 14 2025Sep 19 2024
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

Qwen2.5-Coder leads GPT-4.1 nano on 2 of the 3 benchmarks they both report (HumanEval, IFEval, MMLU). Qwen2.5-Coder shipped 207 days before GPT-4.1 nano, so benchmark comparisons should account for the intervening progress.

Context windows are 1M (GPT-4.1 nano) vs 128k (Qwen2.5-Coder). GPT-4.1 nano is closed, while Qwen2.5-Coder is open weight.

On HumanEval, Qwen2.5-Coder leads at 92.7% vs GPT-4.1 nano at 87%. On IFEval, Qwen2.5-Coder leads at 79.9% vs GPT-4.1 nano at 74.5%. On MMLU, GPT-4.1 nano leads at 80.1% vs Qwen2.5-Coder at 77.6%.