# Claude Sonnet 3.6 (2022-10-22): AI model fact sheet

- **Provider:** anthropic
- **Released:** 2024-06-01
- **Context window:** 200,000 tokens
- **Parameters:** Not disclosed
- **API pricing:** $3.00 / 1M input, $15.00 / 1M output
- **OpenRouter ID:** anthropic/claude-3.5-sonnet
- **Capabilities:** conversation, reasoning, analysis, summarization

Claude 3.5 Sonnet offers a cost-efficient API ($3/million input tokens vs. $5 for GPT-4o) and uses embedded alignment techniques that reduce harmful outputs by 34% compared to Claude 2.1.

## Benchmarks

| Benchmark | Score |
| --- | --- |
| MMLU | 88.3% |
| MATH | 71.1% |
| GPQA | 59.4% |
| HumanEval | 92.0% |
| MGSM | 91.6% |
| Berkeley Function Calling (BFCL) | 90.2% |
| MMLU Pro | 78.0% |
| GPQA Diamond | 65.0% |
| SWE-bench Verified | 49.0% |

Source: real side-by-side outputs, pricing and specs at https://rival.tips/models/claude-3.5-sonnet