Compare AI models

Specifications
Parameters
—4B/30B/235B
Context window
400k256k
API pricing
Cheapest input
$1.75Azure—
Cheapest output
$14.00Azure—
$1,050Azure—
These models have no shared benchmark scores.
Overview
CompanyOpenAIQwen
Release dateDec 18 2025Jul 21 2025
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

GPT-5.2-Codex and Qwen3-2507 don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. Qwen3-2507 shipped 150 days before GPT-5.2-Codex, so benchmark comparisons should account for the intervening progress.

Context windows are 400k (GPT-5.2-Codex) vs 256k (Qwen3-2507). GPT-5.2-Codex is closed, while Qwen3-2507 is open weight.

Direct benchmark comparisons are unavailable — GPT-5.2-Codex and Qwen3-2507 don't publish scores on any of the same benchmarks.