LLM Stats 语言模型排行榜
查看 LLM Stats 首页公开表格前 15 名;完整榜单请访问原站。
| 排名 | 模型 / 开发机构 | LLM Stats Score | 推理 | 编程 | 智能体 | 详情 | |
|---|---|---|---|---|---|---|---|
| 01 | Claude Opus 5.5Anthropic | 60.3LLM Stats Score | 推理58.4 | 编程51.4 | 智能体45.7 | 推理58.4编程51.4智能体45.7 | 详情 |
| 02 | GPT-6 AstraOpenAI | 59.1LLM Stats Score | 推理57.2 | 编程48.5 | 智能体45.7 | 推理57.2编程48.5智能体45.7 | 详情 |
| 03 | Claude Sonnet 5.5Anthropic | 58.0LLM Stats Score | 推理56.6 | 编程48.8 | 智能体42.3 | 推理56.6编程48.8智能体42.3 | 来源 |
| 04 | Claude Opus 5Anthropic | 54.5LLM Stats Score | 推理54.1 | 编程40.7 | 智能体39.2 | 推理54.1编程40.7智能体39.2 | 详情 |
| 05 | Claude Mythos PreviewAnthropic | 54.4LLM Stats Score | 推理55.3 | 编程43.9 | 智能体36.0 | 推理55.3编程43.9智能体36.0 | 详情 |
| 06 | GPT-5.6 SolOpenAI | 54.1LLM Stats Score | 推理53.0 | 编程44.9 | 智能体40.4 | 推理53.0编程44.9智能体40.4 | 详情 |
| 07 | Claude Fable 5.1Anthropic | 53.8LLM Stats Score | 推理50.7 | 编程33.9 | 智能体39.2 | 推理50.7编程33.9智能体39.2 | 详情 |
| 08 | Muse Spark 1.3Meta | 53.8LLM Stats Score | 推理51.3 | 编程41.3 | 智能体39.5 | 推理51.3编程41.3智能体39.5 | 详情 |
| 09 | Claude Fable 5Anthropic | 53.7LLM Stats Score | 推理51.1 | 编程44.4 | 智能体39.6 | 推理51.1编程44.4智能体39.6 | 详情 |
| 10 | Kimi K3Moonshot AI | 52.4LLM Stats Score | 推理51.3 | 编程41.9 | 智能体38.1 | 推理51.3编程41.9智能体38.1 | 详情 |
| 11 | GPT-6.1 SolOpenAI | 52.0LLM Stats Score | 推理42.2 | 编程38.4 | 智能体38.1 | 推理42.2编程38.4智能体38.1 | 来源 |
| 12 | GLM-5.3Z.ai | 52.0LLM Stats Score | 推理51.4 | 编程41.4 | 智能体38.3 | 推理51.4编程41.4智能体38.3 | 详情 |
| 13 | Atria Dawn PreviewShanghai AI Laboratory | 51.6LLM Stats Score | 推理50.0 | 编程35.0 | 智能体37.7 | 推理50.0编程35.0智能体37.7 | 详情 |
| 14 | Qwen3.8 MaxAlibaba | 51.5LLM Stats Score | 推理50.0 | 编程38.5 | 智能体36.9 | 推理50.0编程38.5智能体36.9 | 详情 |
| 15 | DeepSeek-V4.1-FlashDeepSeek | 51.2LLM Stats Score | 推理48.7 | 编程42.9 | 智能体39.8 | 推理48.7编程42.9智能体39.8 | 详情 |