GPT-5.2-Codex
GPT-5.2-Codex is a closed AI model from OpenAI with an index score of 152 (GPT-4 = 100), rank 63 of 217.
152135–169Index score#63 of 217 models
$1.75/ $14Price per million tokensinput / output · via OpenRouter
400KContext windowtokens it reads at once
18 Dec 2025ReleasedReplaced by GPT-5.3-Codex
Where it sitson the frontier
Gemini 3 Pro reached this score 1 month earlier.
Test resultsby area · tick = best by any model
Reasoning & knowledgeevidence
Mathsevidence
Codingevidence
Agentsno evidence yet
Professional workno evidence yet
Novel problemsno evidence yet
Long tasksno evidence yet
Third-party results only, at the model’s best standard setting. Hover a bar for who ran it.
What others sayrank on 2 leaderboards
The Model Indexthird-party tests, our method#63of 217 · 152
LMArena · WebDevbuilding web apps and front ends#108of 133 · 1339Best attop three among current models
Replaced by GPT-5.3-Codex; it no longer leads any category among current models.
Where to use itprices checked 18 Nov 2026
API providers 1 · per 1M tokens, in / out
Host prices from OpenRouter; going direct can differ.
Facts and sources
Released18 Dec 2025
Announcementopenai.com ↗
Release entryGPT-5.2-Codex
Scored asGPT-5.2-Codex
Output speed–
Hugging Faceclosed weights