1. Strongest Agentic Coding Model

• State-of-the-art on Terminal-Bench 2.0 (82.7%), Expert-SWE (73.1%), and SWE-Bench Pro (58.6%), outperforming GPT-5.4 on complex coding tasks.
• Holds context across large systems, reasons through ambiguous failures, and carries changes through surrounding codebases with fewer tokens.

2. Higher Intelligence at GPT-5.4 Latency

• Co-designed, trained, and served on NVIDIA GB200/GB300 NVL72 systems to match GPT-5.4 per-token latency while performing at a significantly higher level.
• Uses fewer tokens to complete the same tasks, making it more efficient as well as more capable.

3. Powerful for Knowledge Work & Computer Use

• Scores 84.9% on GDPval (44 occupations) and 78.7% on OSWorld-Verified for autonomous computer operation.
• Excels at generating documents, spreadsheets, and reports; naturally moves across finding information, using tools, and checking output.

4. Scientific Research Co-Scientist

• Leading performance on GeneBench, BixBench, and FrontierMath; helped discover a new proof about Ramsey numbers verified in Lean.
• Strong enough to meaningfully accelerate progress at the frontiers of biomedical and mathematical research.

1. Optimized for Long-Horizon Coding Tasks

• OpenAI describes GPT-5.2 Codex as a highly intelligent coding model built for long-horizon, agentic coding work.
• Well suited to planning, refactoring, debugging, and multi-step implementation flows inside real codebases.

2. Adjustable Reasoning for Coding Work

• Supports configurable reasoning effort from low to xhigh depending on speed and quality needs.
• Accepts both text and image inputs while producing text output.

3. Large Context + Long Output

• 400 k token context window supports broad repository understanding and larger working sets.
• Allows up to 128 k output tokens for longer patches, code generation, and technical explanations.

4. Up-to-Date Model Snapshot

• Knowledge cut-off of Aug 31 2025 keeps it current with newer tools and frameworks.
• Supports streaming, function calling, and structured outputs for tool-driven coding workflows.