自动生成页面。 本页由 AI 自动撰写和翻译,并由软件对照来源进行核查,无人工编辑。SI-IQ 是基于公开基准测试结果构建的指数,不是智商测试。 工作原理
Anthropic 模型 SI-IQ 排名
我们的数据中，Anthropic 有 26 个模型具备独立基准测试成绩。排名最高的是 Claude Opus 5.5，SI-IQ 为 144。
模型
| 1 | Claude Opus 5.5 Anthropic | 144141–148 | 8 |
| 2 | Claude Sonnet 5.5 Anthropic | 140137–143 | 8 |
| 3 | Claude Fable 5.1 Anthropic | 140136–143 | 8 |
| 4 | Claude Fable 5 Anthropic | 138134–141 | 8 |
| 5 | Claude Opus 5 Anthropic | 136133–140 | 8 |
| 6 | Claude Opus 4.8 Anthropic | 132129–135 | 8 |
| 7 | Claude Haiku 5.5 Anthropic | 129126–132 | 8 |
| 8 | Claude Opus 4.7 Anthropic | 127124–130 | 9 |
| 9 | Claude Sonnet 5 Anthropic | 126123–129 | 8 |
| 10 | Claude Opus 4.6 Anthropic | 123120–126 | 9 |
| 11 | Claude Opus 4.5 Anthropic | 115111–118 | 10 |
| 12 | Claude Sonnet 4.6 Anthropic | 113108–118 | 7 |
| 13 | Claude Sonnet 4.5 Anthropic | 110107–113 | 11 |
| 14 | Claude Haiku 4.5 Anthropic | 10499–108 | 7 |
| 15 | Claude 3.7 Sonnet Anthropic | 9995–103 | 5 |
| 16 | Claude Opus 4 Anthropic | 9893–102 | 5 |
| 17 | Claude Sonnet 4 Anthropic | 9793–101 | 5 |
| 18 | Claude Opus 4.1 Anthropic | 105102–109 | 6 数据不足 |
| 19 | Claude 3.5 Sonnet (October 2024) Anthropic | 7671–80 | 4 数据不足 |
| 20 | Claude 3.5 Sonnet Anthropic | 7166–76 | 3 数据不足 |
| 21 | Claude 3.5 Haiku Anthropic | 6762–72 | 4 数据不足 |
| 22 | Claude 3 Opus Anthropic | 6560–70 | 5 数据不足 |
| 23 | Claude 3 Sonnet Anthropic | 5449–59 | 3 数据不足 |
| 24 | Claude 2.1 Anthropic | 5240–64 | 2 数据不足 |
| 25 | Claude 3 Haiku Anthropic | 5045–56 | 3 数据不足 |
| 26 | Claude 2 Anthropic | 4842–53 | 3 数据不足 |
数据来源: Aider polyglot leaderboard data (Apache-2.0); Arena leaderboard dataset on Hugging Face (CC BY 4.0); Berkeley Function Calling Leaderboard, Gorilla project (Apache-2.0); Epoch AI, ‘Capabilities & benchmarking’ (CC BY 4.0); API list prices via LiteLLM's price table (MIT); each price links to the developer's pricing page; Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter..