High-end Claude for difficult coding, planning, and slower expert reasoning
发布日期2026年2月5日
参数规模—
上下文长度1.0M
许可证Proprietary
知识截止2025年5月31日
Benchmarks
评测成绩
| 评测基准 | 类别 | 分数 | 来源 |
|---|---|---|---|
| SWE-Atlas Codebase QnA (Claude Code) | code | 71.9 | 来源 |
| Terminal-Bench | reasoning code | 70.2 | 来源 |
| SWE-Bench Pro | code | 51.9 | 来源 |
| Artificial Analysis Coding Agent Index | code | 51.3 | 来源 |
| SWE-Atlas Test Writing (Claude Code) | code | 36.7 | 来源 |
| SWE-Atlas Test Writing (Mini-SWE-Agent) | code | 36.1 | 来源 |
| SWE-Atlas Refactoring | code | 35.6 | 来源 |
| SWE-Atlas Codebase QnA (Claude Code) | code | 33.3 | 来源 |
| SWE-Atlas Codebase QnA (Mini-SWE-Agent) | code | 30.0 | 来源 |
| SWE-Bench Pro (Claude Code) | code | 11.8 | 来源 |
Pricing
API 价格对比
| 服务商 | 输入价 | 输出价 | 上下文 | 吞吐(tok/s) | 延迟(s) | 函数调用 | 代码执行 | 联网搜索 |
|---|---|---|---|---|---|---|---|---|
| 302.AI | $5.00 | $25.00 | 1.0M | — | — | ✓ | ✗ | ✗ |
| Abacus | $5.00 | $25.00 | 1.0M | — | — | ✓ | ✗ | ✗ |
| AIHubMix | $5.00 | $25.00 | 1.0M | — | — | ✓ | ✗ | ✗ |
| Anthropic | $5.00 | $25.00 | 1.0M | — | — | ✓ | ✗ | ✗ |
| Auriko | $5.00 | $25.00 | 1.0M | — | — | ✓ | ✗ | ✗ |
| Azure | $5.00 | $25.00 | 1.0M | — | — | ✓ | ✗ | ✗ |
| Azure Cognitive Services | $5.00 | $25.00 | 1.0M | — | — | ✓ | ✗ | ✗ |
| FreeModel | $5.00 | $25.00 | 1.0M | — | — | ✓ | ✗ | ✗ |
| FrogBot | $5.00 | $25.00 | 200K | — | — | ✓ | ✗ | ✗ |
| Jiekou.AI | $5.00 | $25.00 | 1.0M | — | — | ✓ | ✗ | ✗ |
| LLM Gateway | $5.00 | $25.00 | 1.0M | — | — | ✓ | ✗ | ✗ |
| Neon | $5.00 | $25.00 | 1.0M | — | — | ✓ | ✗ | ✗ |
| OpenCode Zen | $5.00 | $25.00 | 1.0M | — | — | ✓ | ✗ | ✗ |
| Pioneer | $5.00 | $25.00 | 1.0M | — | — | ✓ | ✗ | ✗ |
| Venice AI | $6.00 | $30.00 | 1.0M | — | — | ✓ | ✗ | ✗ |
价格单位：美元/百万 token，数据来自社区整理，仅供参考。