Compare AI models

Specifications
Parameters
—6B
Context window
1M8k
API pricing
Cheapest input
$0.10Azure—
Cheapest output
$0.40Azure—
$40.00Azure—
Benchmarks
HumanEval
87%35.9%
Overview
CompanyOpenAIZ.ai
Release dateApr 14 2025Jul 25 2023
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

GPT-4.1 nano leads CodeGeeX2-6B on 1 of the 1 benchmark they both report (HumanEval). CodeGeeX2-6B shipped 629 days before GPT-4.1 nano, so benchmark comparisons should account for the intervening progress.

Context windows are 1M (GPT-4.1 nano) vs 8k (CodeGeeX2-6B). GPT-4.1 nano is closed, while CodeGeeX2-6B is open weight.

On HumanEval, GPT-4.1 nano leads at 87% vs CodeGeeX2-6B at 35.9%.