• Open-weight / Apache 2.0 licensed: you can use, modify, and deploy freely (commercially & academically) under permissive terms.
• Large model size (≈ 21B parameters) with Mixture-of-Experts (MoE) architecture: only ~3.6B parameters active per token, yielding efficient inference.
• Very long context window support: up to ~128 K tokens (or ~131 K tokens per some sources) enabling in-depth reasoning, long documents, or multi-turn context.
• Adjustable reasoning effort: you can trade latency vs quality by tuning “reasoning effort” levels.
• Efficient hardware requirements (for its class): designed to run on a single 16 GB-class GPU or optimized local deployments for lower latency applications.
• Strong for tasks such as reasoning, tool-use, structured output, chain-of-thought debugging: because the model is open and you can inspect its chain of thought.
• Flexibility: since weights are available, you can self-host, fine-tune, or deploy offline, giving more control than closed API models.

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