gpt-5.2 | OpenAI’s most capable model for professional knowledge work. First model above 90% on ARC-AGI-1 with a 400K context window. |
claude-opus-4.5 | Anthropic’s flagship model optimized for coding, agents, and computer use. Achieves 80.9% on SWE-bench Verified. |
gemini-3-flash-preview | Google’s high-speed model for agentic workflows with 1M token context. Near Pro-level reasoning at lower latency and cost. |
gemini-3-pro-preview | Google’s advanced multimodal model with state-of-the-art reasoning and real-world knowledge. |
gemini-3-pro-image-preview | Google’s Nano Banana Pro model for high-quality image generation and editing with accurate text rendering. |