1. High reasoning capability

• Designed for intelligent reasoning across complex domains.
• Supports reasoning tokens and adjustable reasoning effort.

2. Strong coding and agentic performance

• Optimized for multi-step coding tasks, tool-use chains, and agent workflows.
• Handles complex logic, planning, and structured problem solving reliably.

3. Multimodal input

• Accepts text + image as input.
• Produces text outputs with strong instruction following.

4. Extensive tool support

• Works with Web Search, File Search, Image Generation (as a tool), Code Interpreter, MCP, and more.
• Integrated across Chat Completions, Responses API, Realtime, Assistants, Batch, Embeddings, etc.

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