← All Models
📊

AI Model Benchmarks

Compare 9 AI models side by side — pricing, context, and performance

Model Provider Context Input / 1M Output / 1M Rank Best For
Claude Opus 4Anthropic200K$15.00$75.00#1Complex reasoning, coding, agentic tasks
GPT-4oOpenAI128K$2.50$10.00#2General purpose, coding, analysis
Claude Sonnet 4Anthropic200K$3.00$15.00#3Coding, writing, long documents
Gemini 2.5 ProGoogle DeepMind1M$1.25$10.00#4Long documents, multimodal, reasoning
Grok 3xAI128K$3.00$15.00#5Real-time info, reasoning, math
DeepSeek V3OSSDeepSeek128K$0.27$1.10#6Cost-efficient reasoning, code, math
Llama 4 MaverickOSSMeta1MFreeFree#7Open source, self-hosted, multilingual
Mistral LargeMistral AI128K$2.00$6.00#8European privacy, multilingual, code
Command R+Cohere128K$2.50$10.00#12Enterprise RAG, search, multilingual