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
A dated competition, not a fixed set: each sitting is a different instrument and contamination rises once problems are published.
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。
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 | 95.2 | percent | think max, pass@1 | 2026-04-22 · document_publication | DeepSeek-V4-Pro |
| DeepSeek-V4-Flash | 94.8 | percent | think max, pass@1 | 2026-06-25 · document_publication | DeepSeek-V4 |
| Qwen3.5-397B-A17B | 94.8 | percent | thinking (temp 0.6, top_p 0.95, top_k 20) | 2026-02-16 · document_publication | Qwen3.5-397B-A17B |
| Qwen3.5-397B-A17B | 92.7 | percent | thinking (temp 0.6, top_p 0.95, top_k 20) | 2026-02-16 · document_publication | Qwen3.5-397B-A17B |
| GLM-5.1 | 94.0 | percent | HMMT Nov. 2025, as reported | 2026-04-03 · document_publication | GLM-5.1 |
| GLM-5.2 | 94.4 | percent | HMMT Nov. 2025, temp 1.0, top_p 0.95, max gen 163840 tokens, GPT-5.5 (medium) judge | 2026-06-16 · document_publication | GLM-5.2 |
| GLM-5 | 96.9 | percent | HMMT Nov. 2025, temp 1.0, top_p 0.95, GPT-5.2 (medium) judge | 2026-02-11 · document_publication | GLM-5 |