Model comparisonSo sánh model模型对比
anthropic/claude-sonnet-4-6 Details | |
|---|---|
| Overview | |
| Description | Anthropic's Claude Sonnet 4.6 offers strong coding, analysis, and reasoning in a balanced performance-cost tier with a 1M-token context window. |
| Category | Text Generation |
| Context length | 1M |
| Providers | 10 |
| Pricing (per 1M tokens) | |
| Input | $3.00 |
| Output | $15.00 |
| Capabilities | |
| Reasoning | – |
| Tool calling | |
| Vision | – |
| Streaming | |
| Token activity (30 days) | |
| Usage | |
| Artificial Analysis | |
| Intelligence | 34.3 |
| Coding | 43.0 |
| Benchmarks | |
| GPQA Diamond | 0.8 |
| HLE | 0.1 |
| IFEval | 0.4 |
| SWE-bench | 0.8 |
| τ²-bench Telecom | 0.8 |
| SciCode | 0.4 |
Benchmark data from Epoch AI (CC-BY 4.0).