Compare AI ModelsSide by Side
Unbiased comparisons of Claude, GPT-4o, Gemini, and more. Find the best AI model for your use case — with real benchmarks, up-to-date pricing, and honest pros & cons.
Benchmark Comparisons
MMLU, HumanEval, MATH and more — see how every model stacks up on standardized tests.
Transparent Pricing
Up-to-date API pricing per million tokens so you can estimate costs before committing.
Capability Matrix
Context window, multimodal support, max output — every spec in one place.
Use-Case Guides
Not sure which AI to pick? Our guides match you to the right model for coding, writing, research, and more.
All AI Models
Click any column header to sort. Click a model name for full details.
| Model | Tier | Context | Input / 1M | Output / 1M | MMLU | Multimodal | Link |
|---|---|---|---|---|---|---|---|
Claude Sonnet 4.6 Anthropic | frontier | 200K | $3.00 | $15.00 | 88.7 | Yes | Try |
GPT-4o OpenAI | frontier | 128K | $2.50 | $10.00 | 88.7 | Yes | Try |
Llama 3.1 405B Meta | frontier | 128K | $3.00 | $3.00 | 88.6 | No | Try |
Grok 2 xAI | frontier | 131K | $2.00 | $10.00 | 87.5 | No | Try |
Gemini 1.5 Pro Google | frontier | 2.0M | $1.25 | $5.00 | 85.9 | Yes | Try |
GPT-4o mini OpenAI | budget | 128K | $0.150 | $0.600 | 82 | Yes | Try |
Gemini 1.5 Flash Google | budget | 1.0M | $0.075 | $0.300 | 78.9 | Yes | Try |
Claude Haiku 4.5 Anthropic | budget | 200K | $0.800 | $4.00 | 73.8 | Yes | Try |
Top Frontier Models
View all models →Claude Sonnet 4.6
Anthropic's latest and most capable model, excelling at complex reasoning, coding, and nuanced instruction following.
GPT-4o
OpenAI's flagship omnimodal model with strong performance across text, vision, and audio tasks.