Compare AI models

Specifications
Parameters
—0.5B/1.5B/7B/57B/72B
Context window
1M128k
API pricing
Cheapest input
$0.10Azure—
Cheapest output
$0.40Azure—
$40.00Azure—
Benchmarks
HumanEval
87%86%
MMLU
80.1%82.3%
Overview
CompanyOpenAIQwen
Release dateApr 14 2025Jun 6 2024
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

GPT-4.1 nano and Qwen2 are evenly matched across the 2 benchmarks they both report (HumanEval, MMLU). Qwen2 shipped 312 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). GPT-4.1 nano is closed, while Qwen2 is open weight.

On HumanEval, GPT-4.1 nano leads at 87% vs Qwen2 at 86%. On MMLU, Qwen2 leads at 82.3% vs GPT-4.1 nano at 80.1%.