# Claude 3.7 Thinking Sonnet: AI model fact sheet

- **Provider:** anthropic
- **Released:** 2025-02-26
- **Context window:** 200,000 tokens
- **Parameters:** Not disclosed
- **API pricing:** $6.00 / 1M input, $30.00 / 1M output
- **OpenRouter ID:** anthropic/claude-3.7-sonnet:thinking
- **Capabilities:** conversation, reasoning, analysis, summarization

Claude 3.7 Thinking Sonnet exposes the full chain-of-thought process during problem-solving, including error backtracking and alternative solution exploration. Scores 86.1% on GPQA Diamond benchmark for expert-level Q&A.

## Benchmarks

| Benchmark | Score |
| --- | --- |
| MMLU | 77.1% |
| GPQA Diamond | 84.8% |
| MATH | 96.2% |
| AIME | 80.0% |
| HellaSwag (10-shot) | 89.0% |

Source: real side-by-side outputs, pricing and specs at https://rival.tips/models/claude-3.7-sonnet-thinking