# Claude 3 Opus: AI model fact sheet

- **Provider:** anthropic
- **Released:** 2024-03-04
- **Context window:** 200,000 tokens
- **Parameters:** Not disclosed
- **API pricing:** $15.00 / 1M input, $75.00 / 1M output
- **OpenRouter ID:** anthropic/claude-3-opus
- **Capabilities:** conversation, reasoning, code-generation, analysis

Claude 3 Opus is Anthropic's most powerful model with versatile capabilities ranging from complex reasoning to advanced problem-solving.

## Benchmarks

| Benchmark | Score |
| --- | --- |
| MMLU | 86.8% |
| GPQA | 50.4% |
| MATH | 60.1% |
| HumanEval | 84.9% |
| MMMU | 59.4% |

Source: real side-by-side outputs, pricing and specs at https://rival.tips/models/claude-3-opus