Private AI
GPT-5 Codex is a coding-focused variant of GPT-5 built for interactive development and long-running, autonomous engineering work. It excels at feature implementation, debugging, large-scale refactors, and code review, with higher steerability and tighter adherence to developer instructions for cleaner, production-ready code.
Context Window
256.0K
Max Output
32.8K
Input Price (Auto)
$1.25/1M
Output Price (Auto)
$10.00/1M
Cache Read (Auto)
$0.13/1M
Capabilities
Performance metrics and benchmarks
Sourced from Artificial Analysis.
Intelligence Index
36.1
Auto routing is available for this model. Explicit provider selection is not available.
Loading provider options…
GPQA Diamond
Graduate-level scientific reasoning
83.7%
Better than 80% of models compared
HLE
Humanity's Last Exam
25.6%
Better than 86% of models compared
IFBench
Instruction-following benchmark
74.1%
Better than 92% of models compared
T²-Bench Telecom
Conversational AI agents in dual-control scenarios
86.8%
Better than 80% of models compared
AA-LCR
Long context reasoning evaluation
69.0%
Better than 91% of models compared
SciCode
Python programming for scientific computing
40.9%
Better than 77% of models compared
Terminal-Bench Hard
Agentic coding and terminal use
37.9%
AIME 2025
American Invitational Mathematics Examination 2025
98.7%
Better than 99% of models compared
MMLU-Pro
Professional and academic subject knowledge
86.5%
Better than 95% of models compared
Last updated Jul 18, 2026
Artificial AnalysisBetter than 85% of models compared
LiveCodeBench
Contamination-free coding benchmark
84.0%
Better than 95% of models compared
