Compare AI models

Specifications
Parameters
—7B
Context window
200k64k
Benchmarks
HumanEval
99.3%83.5%
Overview
CompanyOpenAIQwen
Release dateApr 16 2025Apr 16 2024
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

o4-mini-high leads CodeQwen1.5 on 1 of the 1 benchmark they both report (HumanEval). CodeQwen1.5 shipped 365 days before o4-mini-high, so benchmark comparisons should account for the intervening progress.

Context windows are 200k (o4-mini-high) vs 64k (CodeQwen1.5). o4-mini-high is closed, while CodeQwen1.5 is open weight.

On HumanEval, o4-mini-high leads at 99.3% vs CodeQwen1.5 at 83.5%.