AI 评测与排行榜，分别告诉你什么
分清评测基准、一次评测运行与排行榜，用它们回答各自适合的问题。
Model reports
MCP Atlas
Public and full splits are both reported under one name; the tool server set is part of the measurement.
评测信息与证据
- 来源
- Model reports
- 发布者
- 未收录
- 评测发布日期
- 2025-11-18
- 采集日期
- 未收录
- 模态
- 未收录
本站保留来源报告的结果，不代表独立复测。请先核对任务版本、评测协议、分数单位和报告日期；不同运行条件不能直接合并为统一排名。
原始资料
报告成绩 8
按来源中的观察顺序展示，顺序不代表排名。日期保留原始精度。
| 模型 | 数值 | 单位 | 协议 | 报告日期与口径 | 来源 |
|---|---|---|---|---|---|
| DeepSeek-V4-Pro | 73.6 | percent | think max, pass@1 | 2026-04-22 · document_publication | DeepSeek-V4-Pro |
| DeepSeek-V4-Flash | 69.0 | percent | think max, pass@1 | 2026-06-25 · document_publication | DeepSeek-V4 |
| Gemini 3.1 Pro | 69.2 | percent | Thinking (High) | 2026-02-19 · document_publication | Gemini 3.1 Pro |
| Kimi K3 | 84.2 | percent | reasoning=max | 2026-06-13 · document_publication | Kimi K3 |
| Hy4 preview | 83.7 | percent | as printed in the report's benchmark table | 2026-08-28 · document_publication | Hy4 preview |
| GLM-5.1 | 71.8 | percent | as reported | 2026-04-03 · document_publication | GLM-5.1 |
| GLM-5.2 | 76.8 | percent | think mode, 500-task public subset, 10-min timeout, Gemini-3.0-Pro judge | 2026-06-16 · document_publication | GLM-5.2 |
| GLM-5 | 67.8 | percent | think mode, 500-task public subset, 10-min timeout, Gemini 3 Pro judge | 2026-02-11 · document_publication | GLM-5 |