GPT-5.2
OpenAI's GPT-5.2 is a chat model that excels in various tasks, including code generation, reasoning, and text generation, with a notable capability to handle extremely long context windows of up to 272,000 tokens. Its strengths are evident in benchmark scores, where it achieves top 10% performance in multiple indices, including Intelligence, Coding, and Math.
Input
Output
Context
272K
Max Output
128K
Parameters
-
Technical Specifications
Model TypeChat
Context Window272,000 tokens
Max Output Tokens128,000 tokens
ParametersNot available
Release DateDec 9, 2025
Training CutoffAug 31, 2025
Licenseproprietary
Open SourceNo
Input Modalities
ImageText
Output Modalities
ImageText
Capabilities
Benchmarks
Artificial Analysis
35.4%
HLE
90.3%
GPQA
52.1%
SciCode
87.4%
MMLU Pro
99.0
Math
48.7
Coding
88.9%
LiveCodeBench
42.2
Intelligence
80.8
Speed (tok/s)
122
TTFA (s)
122
TTFT (s)
Resources & Links
proprietary, Proprietary - API access only
Related Tools
Data sourced from official provider APIs and documentation
Last updated: Jun 24, 2026
Start building with the right model.
Automatically route workloads to the right model for every task, every time.