AI Models
AI Model Comparison & Intelligence Matrix
Compare flagship AI models across OpenAI, Anthropic, Google, DeepSeek, and Meta. Benchmark context windows, input/output token pricing, reasoning scores, coding abilities, and latency.
Compare enterprise AI foundation models side-by-side. Benchmark token pricing per 1M tokens, maximum context limits, reasoning scores, and latency.
Flagship Model Intelligence Matrix (11 Models)
| Model | Provider | Context (Tokens) | Input / 1M | Output / 1M | Action |
|---|---|---|---|---|---|
| GPT-4o | OpenAI | 128,000 | $2.5 | $10 | Specs → |
| GPT-4o Mini | OpenAI | 128,000 | $0.15 | $0.6 | Specs → |
| Claude 3.5 Sonnet | Anthropic | 200,000 | $3 | $15 | Specs → |
| Claude 3 Haiku | Anthropic | 200,000 | $0.25 | $1.25 | Specs → |
| Gemini 2.0 Flash | 1,000,000 | $0.1 | $0.4 | Specs → | |
| Gemini 2.5 Pro | 1,000,000 | $1.25 | $10 | Specs → | |
| DeepSeek V3 | DeepSeek | 128,000 | $0.27 | $1.1 | Specs → |
| DeepSeek R1 | DeepSeek | 128,000 | $0.55 | $2.19 | Specs → |
| Llama 3.3 70B | Meta | 128,000 | $0 | $0 | Specs → |
| Qwen 2.5 72B | Alibaba | 128,000 | $0.4 | $1.2 | Specs → |
| Mistral Large 2 | Mistral AI | 128,000 | $2 | $6 | Specs → |
Compare Outputs in Real-Time
Test GPT-4o, Claude 3.5 Sonnet, and Gemini 2.0 with the same prompt in Agent Studio.
Test Models Side-by-Side