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. Intelligence & Benchmark Performance

• Matches Claude 3 Opus (previous largest model) on many intelligence tasks.
• Surpasses Claude 3 Opus on multiple evaluations despite being a smaller, faster model.
• Major improvements across every skill category vs previous Haiku.

2. Coding Strength

• Scores 40.6% on SWE-bench Verified, outperforming:

  • Claude 3.5 Sonnet (original version)
  • GPT-4o
  • Many agent-driven systems

• Excellent for engineering assistants, agent coding tasks, and bug fixing.

3. Speed & Latency

• Same speed class as Claude 3 Haiku (ultra-fast).
• Ideal for real-time interactions, high request volumes, and UI responsiveness.

4. Tool Use & Instruction Following

• Better at following instructions than previous Haiku.
• Stronger at tool use accuracy, making it reliable for agents and workflows.

5. Best Use Cases

• High-volume, low-latency tasks
• User-facing products
• Sub-agent tasks in larger workflows
• Processing large structured datasets (pricing, inventory, purchase history)
• Rapid content or code generation where speed matters