GPT-5.2 Pro is OpenAI’s most advanced model, offering major improvements in agentic coding and long context performance over GPT-5 Pro. It is optimized for complex tasks that require step-by-step reasoning,...
Tested on 6 benchmarks · BenchGecko score 70.2. Top scores: ARC-AGI (90.5%), FrontierMath-Tiers-1-3-v2-Private (74.0%), ARC-AGI-2 (54.2%).
Qwen3.5 397B A17B scores 69.7 (99% as good) at $0.55/1M input · 97% cheaper
Abstraction and Reasoning Corpus. Tests fluid intelligence through novel visual pattern recognition puzzles. Core measure of general intelligence.
ARC-AGI 2, harder sequel to ARC. More complex abstract reasoning patterns that test generalization ability beyond training data.
Deceptively simple questions that humans find easy but AI models often get wrong. Tests common sense and reasoning gaps.
Hardest tier of FrontierMath. Problems at the frontier of human mathematical ability, many unsolved by most mathematicians.
- Typemultimodal
- Context400K tokens (~200 books)
- ReleasedDec 2025
- LicenseProprietary
- StatusActive
- Cost / Message~$0.210
Frequently Asked Questions
Related Models
Qwen3.7 Max · Alibaba QwenQwen3.5 397B A17B · Alibaba QwenQwen2.5 14B Instruct · Alibabaphi-3-medium 14B · MicrosoftQwen2.5 Coder 32B Instruct · Alibaba QwenKey facts · as of 2026-10-05
- GPT-5.2 Pro by OpenAI. BenchGecko score 70.2, rank 36 of 312 scored models (normalized average of public benchmark scores).
- List price $21.00 input · $168.00 output per 1M tokens (as of 2026-10-05).
- Sold by 1 provider (as of 2026-10-05): OpenAI $21.00 in / $168.00 out.
How to cite · data as of 2026-10-05
GPT-5.2 Pro · benchmarks, pricing and providers. BenchGecko, data as of 2026-10-05. https://benchgecko.ai/model/gpt-5-2-pro
Credit "Source: BenchGecko" with a link. Prices per provider and Gecko Tests are BenchGecko data (CC BY 4.0); benchmark scores keep their original source, listed in the JSON. JSON · llms.txt · MCP