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. Most powerful open-weight model

• 117B parameters (5.1B active) while fitting on a single H100 GPU.
• High reasoning quality compared to other open models.

2. Apache 2.0 license

• Fully permissive, no copyleft or patent restrictions.
• Safe for commercial products, research, and redistribution.

3. Configurable reasoning effort

• Supports adjustable reasoning: low, medium, high.
• Lets developers balance latency vs. depth.

4. Full chain-of-thought access

• Unlike closed commercial models, this exposes complete reasoning traces.
• Useful for debugging, auditing, safety research, and transparency.

5. Fine-tunable

• Fully supports parameter fine-tuning.
• Can be adapted to domain-specific workflows and proprietary datasets.

6. Agentic capabilities

• Built-in function calling.
• Native support for web browsing, Python execution, and structured outputs.
• Ideal for open-source agents, full-stack automation, and developer tooling.

7. Tooling ecosystem support

• Compatible with Chat Completions, Responses API, Assistants, Realtime, Batch, and Fine-tuning endpoints.
• Supports Image Generation, Code Interpreter (via Python runtime), and more.

8. Open-source availability

• Downloadable on HuggingFace for local or on-prem deployment.
• Supports full offline, private, or self-hosted usage.

9. Streaming + function calling support

• Real-time interactions.
• Strong for interactive agents, coding assistants, and UI-driven workflows.