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. High-quality image generation

• Produces sharper, more detailed images than Gemini 2.0 Flash.
• Designed to generate professional-grade, aesthetically consistent visuals.

2. Advanced image editing capabilities

• Supports targeted, natural-language-driven edits (remove objects, change poses, recolor, blur backgrounds, etc.).
• Enables precise local transformations with simple prompts.

3. Multi-image fusion

• Can merge multiple input images intelligently into a single coherent scene.
• Useful for room restyling, product placement, and photorealistic composite images.

4. Character consistency across prompts

• Maintains the same character or object across multiple scenes and prompts.
• Suitable for brand assets, storytelling, product showcases, and multi-angle rendering.

5. Strong world knowledge

• Inherits Gemini's semantic understanding to reason about real-world objects.
• Can interpret hand-drawn diagrams and follow complex editing instructions.

6. Low latency + developer-friendly

• Based on the Gemini Flash family, optimized for responsiveness and cost-effectiveness.
• Easily testable and remixable using Google AI Studio's app builder.

7. Invisible SynthID watermarking

• All generated and edited images include Google's invisible SynthID watermark.
• Ensures traceability and responsible AI output.

8. Works with text + image input

• Accepts multiple images and text instructions simultaneously.
• Ideal for building interactive image tools, editors, and creative workflows.