GPT-5.2 Pro

Max input

272K

Structured output

—

Knowledge cutoff

Aug 2025

Open weights

—

Family

gpt-pro

Aliases

gpt-5.2-pro-2025-12-11

Model ID

gpt-5.2-pro

Not stated on OpenAI’s pages: reasoning can be off, max thinking budget, built-in tools.

• Epoch Capabilities Index 157.2

  #28 of 118 listed models · CI 155–159.7

• Epoch AI · Chess Puzzles 60%

  #7 of 85 listed models · xhigh effort · ±4.92

• Epoch AI · FrontierMath Tier 4 v2 46%

  #25 of 65 listed models · xhigh effort · ±7.79

• Epoch AI · FrontierMath Tiers 1–3 74%

  #24 of 84 listed models · xhigh effort · ±2.63

• Epoch AI, 'Capabilities & benchmarking'. Published online at epoch.ai. Retrieved from 'https://epoch.ai/benchmarks'. Licensed CC BY 4.0. · License · as of Oct 28 – Nov 5, 2026
• changes we made

No changes recorded yet.

• OpenAI API pricing (opens in a new tab) developers.openai.com · checked Nov 9, 2026
• GPT-5.2 Pro (opens in a new tab) developers.openai.com · checked Nov 8, 2026
• models.dev: gpt-5.2-pro (community data, MIT) (opens in a new tab) github.com · checked Sep 30, 2026
• GPT-5.2 Pro (opens in a new tab) developers.openai.com · checked Nov 4, 2026
• ChatGPT release notes | OpenAI Help Center (opens in a new tab) help.openai.com · checked Nov 4, 2026

OpenAI’s official policies: data use, privacy, terms →

Some values on this page are still waiting to be checked against official pages: a filled dot is verified, a hollow one is not yet (with or without a source on file). How we verify data

OpenAI · United States · openai.com

Snapshots, the same family and other models from this provider

• GPT-5.5 Pro
• GPT-5.4 Pro
• GPT-6-Cyber
• gpt-6-astra-law
• GPT-6 Rosalind
• GPT-6.1 Terra
• GPT-6.1 Sol
• GPT-6 Luna
• GPT-5.2 Pro vs GPT-5.4 Pro
• GPT-5.2 Pro vs GPT-5 Pro