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. Highest reasoning quality in the GPT-5 family

• Uses significantly more compute to "think harder" before responding.
• Designed for the toughest reasoning tasks where answer quality matters more than speed.
• Produces more precise, reliable, and detailed outputs than standard GPT-5.

2. Advanced multi-turn reasoning via Responses API

• Available only in the Responses API to support:
  • Multi-turn internal model interactions before returning a reply.
  • Advanced control patterns (e.g., background mode for long-running jobs).
• Ideal for complex workflows, deep planning, and multi-step analysis.

3. Configured for maximum effort by default

• Always runs with reasoning.effort: 'high' (no lower-effort mode).
• Prioritizes depth and correctness over latency and cost.

4. Multimodal input

• Accepts text + image as input.
• Outputs text, with strong instruction-following and analysis capabilities.

5. Tooling and ecosystem integration

• Supports Web Search, File Search, and Image Generation (as tools).
• Supports MCP and other Responses API tooling patterns.
• Does not support Code Interpreter and does not support Computer Use, keeping focus on pure reasoning + tools.