Compare AI models

Specifications
Parameters
—14B
Context window
400k2k
API pricing
Cheapest input
$1.25Azure—
Cheapest output
$10.00Azure—
$750Azure—
These models have no shared benchmark scores.
Overview
CompanyOpenAIQwen
Release dateNov 13 2025Sep 25 2023
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

GPT-5.1-Codex and Qwen-14B don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. Qwen-14B shipped 780 days before GPT-5.1-Codex, so benchmark comparisons should account for the intervening progress.

Context windows are 400k (GPT-5.1-Codex) vs 2k (Qwen-14B). GPT-5.1-Codex is closed, while Qwen-14B is open weight.

Direct benchmark comparisons are unavailable — GPT-5.1-Codex and Qwen-14B don't publish scores on any of the same benchmarks.